Tesis sobre el tema "FAKE VIDEOS"
Siga este enlace para ver otros tipos de publicaciones sobre el tema: FAKE VIDEOS.
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "FAKE VIDEOS".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Zou, Weiwen. "Face recognition from video". HKBU Institutional Repository, 2012. https://repository.hkbu.edu.hk/etd_ra/1431.
Texto completo
2
LI, Songyu. "A New Hands-free Face to Face Video Communication Method : Profile based frontal face video reconstruction". Thesis, Umeå universitet, Institutionen för tillämpad fysik och elektronik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-152457.
Texto completoResumen
This thesis proposes a method to reconstruct a frontal facial video basedon encoding done with the facial profile of another video sequence.The reconstructed facial video will have the similar facial expressionchanges as the changes in the profile video. First, the profiles for boththe reference video and for the test video are captured by edge detection.Then, asymmetrical principal component analysis is used to model thecorrespondence between the profile and the frontal face. This allows en-coding from a profile and decoding of the frontal face of another video.Another solution is to use dynamic time warping to match the profilesand select the best matching corresponding frontal face frame for re-construction. With this method, we can reconstructed the test frontalvideo to make it have the similar changing in facial expressions as thereference video. To improve the quality of the result video, Local Lin-ear Embedding is used to give the result video a smoother transitionbetween frames.
3
Liu, Yiran. "Consistent and Accurate Face Tracking and Recognition in Videos". Ohio University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1588598739996101.
Texto completo
4
Cheng, Xin. "Nonrigid face alignment for unknown subject in video". Thesis, Queensland University of Technology, 2013. https://eprints.qut.edu.au/65338/1/Xin_Cheng_Thesis.pdf.
Texto completoResumen
Non-rigid face alignment is a very important task in a large range of applications but the existing tracking based non-rigid face alignment methods are either inaccurate or requiring person-specific model. This dissertation has developed simultaneous alignment algorithms that overcome these constraints and provide alignment with high accuracy, efficiency, robustness to varying image condition, and requirement of only generic model.
5
Jin, Yonghua. "A video human face tracker". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0032/MQ62226.pdf.
Texto completo
6
Arandjelović, Ognjen. "Automatic face recognition from video". Thesis, University of Cambridge, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.613375.
Texto completo
7
Omizo, Ryan Masaaki. "Facing Vernacular Video". The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1339184415.
Texto completo
8
Hadid, A. (Abdenour). "Learning and recognizing faces: from still images to video sequences". Doctoral thesis, University of Oulu, 2005. http://urn.fi/urn:isbn:9514277597.
Texto completoResumen
Abstract
Automatic face recognition is a challenging problem which has received much attention during recent years due to its many applications in different fields such as law enforcement, security applications, human-machine interaction etc. Up to date there is no technique that provides a robust solution for all situations and different applications.
From still gray images to face sequences (and passing through color images), this thesis provides new algorithms to learn, detect and recognize faces. It also analyzes some emerging directions such as the integration of facial dynamics in the recognition process.
To recognize faces, the thesis proposes a new approach based on Local Binary Patterns (LBP) which consists of dividing the facial image into small regions from which LBP features are extracted and concatenated into a single feature histogram efficiently representing the face image. Then, face recognition is performed using a nearest neighbor classifier in the computed feature space with Chi-square as a dissimilarity metric. The extensive experiments clearly show the superiority of the proposed method over the state-of the-art algorithms on FERET tests.
To detect faces, another LBP-based representation which is suitable for low-resolution images, is derived. Using the new representation, a second-degree polynomial kernel SVM classifier is trained to detect frontal faces in complex gray scale images. Experimental results using several complex images show that the proposed approach performs favorably compared to the state-of-art methods. Additionally, experiments with detecting and recognizing low-resolution faces are carried out to demonstrate that the same facial representation can be efficiently used for both the detection and recognition of faces in low-resolution images.
To detect faces when the color cue is available, the thesis proposes an approach based on a robust model of skin color, called a skin locus, which is used to extract the skin-like regions. After orientation normalization and based on verifying a set of criteria (face symmetry, presence of some facial features, variance of pixel intensities and connected component arrangement), only facial regions are selected.
To learn and visualize faces in video sequences, the recently proposed algorithms for unsupervised learning and dimensionality reduction (LLE and ISOMAP), as well as well known ones (PCA, SOM etc.) are considered and investigated. Some extensions are proposed and a new approach for selecting face models from video sequences is developed. The approach is based on representing the face manifold in a low-dimensional space using the Locally Linear Embedding (LLE) algorithm and then performing K-means clustering.
To analyze the emerging direction in face recognition which consists of combining facial shape and dynamic personal characteristics for enhancing face recognition performance, the thesis considers two factors (face sequence length and image quality) and studies their effects on the performance of video-based systems which attempt to use a spatio-temporal representation instead of a still image based one. The extensive experimental results show that motion information enhances automatic recognition but not in a systematic way as in the human visual system.
Finally, some key findings of the thesis are considered and used for building a system for access control based on detecting and recognizing faces.
9
Fernando, Warnakulasuriya Anil Chandana. "Video processing in the compressed domain". Thesis, University of Bristol, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.326724.
Texto completo
10
Wibowo, Moh Edi. "Towards pose-robust face recognition on video". Thesis, Queensland University of Technology, 2014. https://eprints.qut.edu.au/77836/1/Moh%20Edi_Wibowo_Thesis.pdf.
Texto completoResumen
This thesis investigates face recognition in video under the presence of large pose variations. It proposes a solution that performs simultaneous detection of facial landmarks and head poses across large pose variations, employs discriminative modelling of feature distributions of faces with varying poses, and applies fusion of multiple classifiers to pose-mismatch recognition. Experiments on several benchmark datasets have demonstrated that improved performance is achieved using the proposed solution.
11
Canavan, Shaun. "Face recognition by multi-frame fusion of rotating heads in videos /". Connect to resource online, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1210446052.
Texto completo
12
Herrmann, Christian [Verfasser]. "Video-to-Video Face Recognition for Low-Quality Surveillance Data / Christian Herrmann". Karlsruhe : KIT Scientific Publishing, 2018. http://www.ksp.kit.edu.
Texto completo
13
Yaprakkaya, Gokhan. "Face Identification, Gender And Age Groups Classifications For Semantic Annotation Of Videos". Thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12612848/index.pdf.
Texto completoResumen
This thesis presents a robust face recognition method and a combination of methods for gender identification and age group classification for semantic annotation of videos. Local binary pattern histogram which has 256 bins and pixel intensity differences are used as extracted facial features for gender classification. DCT Mod2 features and edge detection results around facial landmarks are used as extracted facial features for age group classification. In gender classification module, a Random Trees classifier is trained with LBP features and an adaboost classifier is trained with pixel intensity differences. DCT Mod2 features are used for training of a Random Trees classifier and LBP features around facial landmark points are used for training another Random Trees classifier in age group classification module. DCT Mod2 features of the detected faces morped by two dimensional face morphing method based on Active Appearance Model and Barycentric Coordinates are used as the inputs of the nearest neighbor classifier with weights obtained from the trained Random Forest classifier in face identification module. Different feature extraction methods are tried and compared and the best achievements in the face recognition module to be used in the method chosen. We compared our classification results with some successful earlier works results in our experiments performed with same datasets and got satisfactory results.
14
Canavan, Shaun J. "Face Recognition by Multi-Frame Fusion of Rotating Heads in Videos". Youngstown State University / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1210446052.
Texto completo
15
Tolley, Rebecca. "No Foolin? Fake News and A.I. Manipulation of Audio, Video, and Images". Digital Commons @ East Tennessee State University, 2019. https://dc.etsu.edu/etsu-works/5700.
Texto completo
16
Nilsson, Linus. "Object Tracking and Face Recognition in Video Streams". Thesis, Umeå universitet, Institutionen för datavetenskap, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-58076.
Texto completoResumen
The goal with this project was to improve an existing face recognition system for video streams by using adaptive object tracking to track faces between frames. The knowledge of what faces occur and do not occur in subsequent frames was used to filter false faces and to better identify real ones. The recognition ability was tested by measuring how many faces were found and how many of them were correctly identified in two short video files. The tests also looked at the number of false face detections. The results were compared to a reference implementation that did not use object tracking. Two identification modes were tested: the default and strict modes. In the default mode, whichever person is most similar to a given image patch is accepted as the answer. In strict mode, the similarity also has to be above a certain threshold. The first video file had a fairly high image quality. It had only frontal faces, one at a time. The second video file had a slightly lower image quality. It had up to two faces at a time, in a larger variety of angles. The second video was therefore a more difficult case. The results show that the number of detected faces increased by 6-21% in the two video files, for both identification modes, compared to the reference implementation. In the meantime, the number of false detections remained low. In the first video file, there were fewer than 0.009 false detections per frame. In the second video file, there were fewer than 0.08 false detections per frame. The number of faces that were correctly identified increased by 8-22% in the two video files in default mode. In the first video file, there was also a large improvement in strict mode, as it went from recognising 13% to 85% of all faces. In the second video file, however,neither implementation managed to identify anyone in strict mode. The conclusion is that object tracking is a good tool for improving the accuracy of face recognition in video streams. Anyone implementing face recognition for video streams should consider using object tracking as a central component.
17
Lindström, Lucas. "Towards a Video Annotation System using Face Recognition". Thesis, Umeå universitet, Institutionen för datavetenskap, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-85251.
Texto completoResumen
A face recognition software framework was developed to lay the foundation for a future video annotation system. The framework provides a unified and extensible interface to multiple existing implementations of face detection and recognition algorithms from OpenCV and Wawo SDK. The framework supports face detection with cascade classification using Haar-like features, and face recognition with Eigenfaces, Fisherfaces, local binary pattern histograms, the Wawo algorithm and an ensemble method combining the output of the four algorithms. An extension to the cascade face detector was developed that covers yaw rotations. CAMSHIFT object tracking was combined with an arbitrary face recognition algorithm to enhance face recognition in video. The algorithms in the framework and the extensions were evaluated on several different test databases with different properties in terms of illumination, pose, obstacles, background clutter and imaging conditions. The results of the evaluation show that the algorithmic extensions provide improved performance over the basic algorithms under certain conditions.
18
Tuvskog, Johanna. "Evaluation of Face Recognition Accuracy in Surveillance Video". Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166758.
Texto completoResumen
Automatic Face Recognition (AFR) can be useful in the forensic field when identifying people in surveillance footage. In AFR systems it is common to use deep neural networks which perform well if the quality of the images keeps a certain level. This is a problem when applying AFR on surveillance data since the quality of those images can be very poor. In this thesis the CNN FaceNet has been used to evaluate how different quality parameters influence the accuracy of the face recognition. The goal is to be able to draw conclusions about how to improve the recognition by using and avoiding certain parameters based on the conditions. Parameters that have been experimented with are angle of the face, image quality, occlusion, colour and lighting. This has been achieved by using datasets with different properties or by alternating the images. The parameters are meant to simulate different situations that can occur in surveillance footage that is difficult for the network to recognise. Three different models have been evaluated with different amount of embeddings and different training data. The results show that the two models trained on the VGGFace2 dataset performs much better than the one trained on CASIA-WebFace. All models performance drops on images with low quality compared to images with high quality because of the training data including mostly high-quality images. In some cases, the recognition results can be improved by applying some alterations in the images. This could be by using one frontal and one profile image when trying to identify a person or occluding parts of the shape of the face if it gets recognized as other persons with similar face shapes. One main improvement would be to extend the training datasets with more low-quality images. To some extent, this could be achieved by different kinds of data augmentation like artificial occlusion and down-sampled images.
19
Finlay, Katharine. "Let me finish: Gendered conversational dominance in video-mediated communication". Scholarship @ Claremont, 2015. http://scholarship.claremont.edu/scripps_theses/532.
Texto completoResumen
Previous research has demonstrated that men and women employ different speech styles that result in an uneven power dynamic. To better understand the increasingly common interactions that take place using video-mediated communication, such as Skype and Google Hangout, the present research examines these gendered patterns in video-mediated communication (VMC). Mixed-gender dyads will be formed and ask to complete a desert survival task via VMC or in person while software analyzes their use of aggressive positive, and tentative language, as well as measuring speaking time for each party. Interpersonal perception and the use of intrusive interruptions and will also be examined. Drawing from research in Social Information Processing Theory, it is expected that users compensate for the difficulties of a communication medium in order to achieve a normal interaction. As such, men are anticipated to use more intrusive interruptions, aggressive language, and speak more than women, regardless of condition. Women are anticipated to use more positive and tentative language in both VMC and face-to-face conditions. Dominant language is also expected to mediate the relationship between gender and perceived dominance. Future research should examine the effect of race in these interactions, as well as how this dynamic effects gender non-conforming persons.
20
Jönsson, Jade y louise weidenstolpe. "Manipulation i rörligt format - En studie kring deepfake video och dess påverkan". Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20776.
Texto completoResumen
Med deepfake-teknologi kan det skapas manipulerade videor där det produceras falska bilder och ljud som framställs vara verkliga. Deepfake-teknologin förbättras ständigt och det kommer att bli svårare att upptäcka manipulerade videor online. Detta kan innebära att en stor del mediekonsumenter omedvetet exponeras för tekniken när de använder sociala medier. Studiens syfte är att undersöka unga vuxnas medvetenhet, synsätt och påverkan av deepfake videor. Detta eftersom deepfake-teknologin förbättras årligen och problemen med tekniken växer samt kan få negativa konsekvenser i framtiden om den utnyttjas på fel sätt. Insamlingen av det empiriska materialet skedde genom en kvantitativ metod i form av en webbenkät och en kvalitativ metod med tre fokusgrupper. Slutsatsen visade på att det finns ett större antal unga vuxna som inte är medvetna om vad en deepfake video är, dock existerar det en viss oro för deepfake-teknologin och dess utveckling. Det upplevs att det finns risker för framtiden med teknologin i form av hot mot demokratin och politik, spridning av Fake news, video-manipulation samt brist på källkritik. De positiva aspekterna är att tekniken kan användas i sammanhang av humor, inom film- och TV-industrin samt sjukvård. Ytterligare en slutsats är att unga vuxna kommer att vara mer källkritiska till innehåll de exponeras av framöver, dock kommer de med stor sannolikhet ändå att påverkas av deepfake-teknologin i framtiden.Manipulated videos can be created with deepfake technology, where fake images and sounds are produced and seem to be real. Deepfake technology is constantly improving and it will be more problematic to detect manipulated video online. This may result in a large number of media consumers being unknowingly exposed to deepfake technology while using social media. The purpose of this study is to research young adults' awareness, approach and impact of deepfake videos. The deepfake technology improves annually and more problems occur, which can cause negative consequences in the future if it’s misused. The study is based on a quantitative method in the form of a web survey and a qualitative method with three focus groups. The conclusion shows that there’s a large number of young adults who are not aware of what a deepfake video is, however there’s some concern about deepfake technology and its development. It’s perceived that there can be risks in the future with the technology in terms of threats to democracy and politics, distribution of Fake news, video manipulation and lack of source criticism. The positive aspects are that the technology can be used for entertainment purposes, in the film and television industry also in the healthcare department. Another conclusion is that young adults will be more critical to the content they are exposed to in the future, but likely be affected by deepfake technology either way.
21
Tsishkou, Dzmitry. "Face detection, matching and recognition for semantic video understanding". Ecully, Ecole centrale de Lyon, 2005. http://www.theses.fr/2005ECDL0044.
Texto completoResumen
The objective of this work can be summarized as follows : to propose face detection and recognition in video solution that is enough fast, accurate and reliable to be implemented in the semantic video understanding system that is capable of replacing human expert in a variety of multimedia indexing applications. Meanwhile we assume that the research results that were raised during this work are complete enough to be adapted or modified as a part of other image processing, pattern recognition and video indexing and analysis systems.
22
Yilmazturk, Mehmet Celaleddin. "Online And Semi-automatic Annotation Of Faces In Personal Videos". Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12611936/index.pdf.
Texto completoResumen
Video annotation has become an important issue due to the rapidly increasing amount of video available. For efficient video content searches, annotation has to be done beforehand, which is a time-consuming process if done manually. Automatic annotation of faces for person identification is a major challenge in the context of content-based video retrieval. This thesis work focuses on the development of a semi-automatic face annotation system which benefits from online learning methods. The system creates a face database by using face detection and tracking algorithms to collect samples of the encountered faces in the video and by receiving labels from the user. Using this database a learner model is trained. While the training session continues, the system starts offering labels for the newly encountered faces and lets the user acknowledge or correct the suggested labels hence a learner is updated online throughout the video. The user is free to train the learner until satisfactory results are obtained. In order to create a face database, a shot boundary algorithm is implemented to partition the video into semantically meaningful segments and the user browses through the video from one shot boundary to the next. A face detector followed by a face tracker is implemented to collect face samples within two shot boundary frames. For online learning, feature extraction and classification methods which are computationally efficient are investigated and evaluated. Sequential variants of some robust batch classification algorithms are implemented. Combinations of feature extraction and classification methods have been tested and compared according to their face recognition accuracy and computational performances.
23
Emir, Alkazhami. "Facial Identity Embeddings for Deepfake Detection in Videos". Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-170587.
Texto completoResumen
Forged videos of swapped faces, so-called deepfakes, have gained a lot of attention in recent years. Methods for automated detection of this type of manipulation are also seeing rapid progress in their development. The purpose of this thesis work is to evaluate the possibility and effectiveness of using deep embeddings from facial recognition networks as base for detection of such deepfakes. In addition, the thesis aims to answer whether or not the identity embeddings contain information that can be used for detection while analyzed over time and if it is suitable to include information about the person's head pose in this analysis. To answer these questions, three classifiers are created with the intent to answer one question each. Their performances are compared with each other and it is shown that identity embeddings are suitable as a basis for deepfake detection. Temporal analysis of the embeddings also seem effective, at least for deepfake methods that only work on a frame-by-frame basis. Including information about head poses in the videos is shown to not improve a classifier like this.
24
Asghar, Muhammad Nabeel. "Feature based dynamic intra-video indexing". Thesis, University of Bedfordshire, 2014. http://hdl.handle.net/10547/338913.
Texto completoResumen
With the advent of digital imagery and its wide spread application in all vistas of life, it has become an important component in the world of communication. Video content ranging from broadcast news, sports, personal videos, surveillance, movies and entertainment and similar domains is increasing exponentially in quantity and it is becoming a challenge to retrieve content of interest from the corpora. This has led to an increased interest amongst the researchers to investigate concepts of video structure analysis, feature extraction, content annotation, tagging, video indexing, querying and retrieval to fulfil the requirements. However, most of the previous work is confined within specific domain and constrained by the quality, processing and storage capabilities. This thesis presents a novel framework agglomerating the established approaches from feature extraction to browsing in one system of content based video retrieval. The proposed framework significantly fills the gap identified while satisfying the imposed constraints of processing, storage, quality and retrieval times. The output entails a framework, methodology and prototype application to allow the user to efficiently and effectively retrieved content of interest such as age, gender and activity by specifying the relevant query. Experiments have shown plausible results with an average precision and recall of 0.91 and 0.92 respectively for face detection using Haar wavelets based approach. Precision of age ranges from 0.82 to 0.91 and recall from 0.78 to 0.84. The recognition of gender gives better precision with males (0.89) compared to females while recall gives a higher value with females (0.92). Activity of the subject has been detected using Hough transform and classified using Hiddell Markov Model. A comprehensive dataset to support similar studies has also been developed as part of the research process. A Graphical User Interface (GUI) providing a friendly and intuitive interface has been integrated into the developed system to facilitate the retrieval process. The comparison results of the intraclass correlation coefficient (ICC) shows that the performance of the system closely resembles with that of the human annotator. The performance has been optimised for time and error rate.
25
Sandri, Gustavo Luiz. "Automated non-contact heart rate measurement using conventional video cameras". reponame:Repositório Institucional da UnB, 2016. http://dx.doi.org/10.26512/2016.02.D.21118.
Texto completoResumen
Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Elétrica, 2016.Conforme o sangue flui através do corpo de um indivíduo, ele muda a forma como a luz é irradiada pela pele, pois o sangue absorve luz de forma diferente dos outros tecidos. Essa sutil variação pode ser capturada por uma câmera e ser usada para monitorar a atividade cardíaca de uma pessoa. O sinal capturado pela câmera é uma onda que representa as variações de tonalidade da pele ao longo do tempo. A frequência dessa onda é a mesma frequência na qual o coração bate. Portanto, o sinal capturado pela câmera pode ser usado para estimar a taxa cardíaca de uma pessoa. Medir o pulso cardíaco remotamente traz mais conforto pois evita o uso de eletrodos. Também permite o monitoramento de uma pessoa de forma oculta para ser empregado em um detector de mentira, por exemplo. Neste trabalho nós propomos dois algoritmos para a estimação da taxa cardíaca sem contato usando câmeras convencionais sob iluminação não controlada. O primeiro algoritmo proposto é um método simples que emprega um detector de face que identifica a face da pessoa sendo monitorada e extrai o sinal gerado pelas mudanças no tom da pele devido ao fluxo sanguíneo. Este algoritmo emprega um filtro adaptativo para aumentar a energia do sinal de interesse em relação ao ruído. Nós mostramos que este algoritmo funciona muito bem para vídeos com pouco movimento. O segundo algoritmo que propomos é uma melhora do primeiro para torná-lo mais robusto a movimentos. Nós modificamos o método usado para definir a região de interesse. Neste algoritmo é utilizado um detector de pele para eliminar pixels do plano de fundo do vídeo, os frames dos vídeos são divididos em micro-regiões que são rastreados com um algoritmo de fluxo ótico para compensar os movimentos e um algoritmo de clusterização é aplicado para selecionar automaticamente as melhores micro-regiões para efetuar a estimação da taxa cardíaca. Propomos também um esquema de filtragem temporal e espacial para reduzir o ruído introduzido pelo algoritmo de fluxo ótico. Comparamos os resultados dos nossos algoritmos com um oxímetro de dedo comercial e mostramos que eles funcionam bem para situações desafiadoras.
As the blood flows through the body of an individual, it changes the way that light is irradiated by the skin, because blood absorbs light differently than the remaining tissues. This subtle variation can be captured by a camera and be used to monitor the heart activity of a person. The signal captured by the camera is a wave that represents the changes in skin tone along time. The frequency of this wave is the same as the frequency by which the heart beats. Therefore, the signal captured by the camera could be used to estimate a person’s heart rate. This remote measurement of cardiac pulse provides more comfort as it avoids the use of electrodes or others devices attached to the body. It also allows the monitoring of a person in a canceled way to be employed in lie detectors, for example. In this work we propose two algorithms for non-contact heart rate estimation using conventional cameras under uncontrolled illumination. The first proposed algorithm is a simple approach that uses a face detector to identify the face of the person being monitored and extract the signal generated by the changes in the skin tone due to the blood flow. This algorithm employs an adaptive filter to boost the energy of the interest signal against noise. We show that this algorithm works very well for videos with little movement. The second algorithm we propose is an improvement of the first one to make it more robust to movements. We modify the approach used to define the region of interest. In this algorithm we employ a skin detector to eliminate pixels from the background, divide the frames in microregions that are tracked using an optical flow algorithm to compensate for movements and we apply a clustering algorithm to automatically select the best micro-regions to use for heart rate estimation. We also propose a temporal and spatial filtering scheme to reduce noise introduced by the optical flow algorithm. We compared the results of our algorithms to an off-the-shelf fingertip pulse oximeter and showed that they can work well under challenging situations.
26
Johnson, Andrew. "Fragment Association Matching Enhancement (FAME) on a Video Tracker". Wright State University / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=wright1399465180.
Texto completo
27
Manohar, Vasant. "Video-Based Person Identification Using Facial Strain Maps as a Biometric". Scholar Commons, 2006. http://scholarcommons.usf.edu/etd/3797.
Texto completoResumen
Research on video-based face recognition has started getting increased attention in the past few years. Algorithms developed for video have an advantage from the availability of plentitude of frames in videos to extract information from. Despite this fact, most research in this direction has limited the scope of the problem to the application of still image-based approaches to some selected frames on which 2D algorithms are expected to perform well. It can be realized that such an approach only uses the spatial information contained in video and does not incorporate the temporal structure.Only recently has the intelligence community begun to approach the problem in this direction. Video-based face recognition algorithms in the last couple of years attempt to simultaneously use the spatial and temporal information for the recognition of moving faces. A new face recognition method that falls into the category of algorithms that adopt spatio-temporal representation and utilizes dynamic information extracted from video is presented. The method was designed based on the hypothesis that the strain pattern exhibited during facial expression provides a unique "fingerprint" for recognition. First, a dense motion field is obtained with an optical flow algorithm. A strain pattern is then derived from the motion field. In experiments with 30 subjects, results indicate that strain pattern is an useful biometric, especially when dealing with extreme conditions such as shadow light and face camouflage, for which conventional face recognition methods are expected to fail. The ability to characterize the face using the elastic properties of facial skin opens up newer avenues to the face recognition community in the context of modeling a face using features beyond visible cues.
28
REA, RAFFAELE. "Tele-Neuropsychological assessments in Alzheimer's disease: a comparison of ''face to face'' versus Video-Conferencing". Doctoral thesis, Università degli Studi di Camerino, 2014. http://hdl.handle.net/11581/401827.
Texto completoResumen
Telemedicine consists in the use of telecommunication technologies to provide healthcare services, overcoming geographic, temporal, social, and cultural barriers. Today telemedicine is a developed field which includes about 50 different subspecialties: neuropsychology is one of them. Allowing the objective evaluation of the cognitive state of individuals, neuropsychology is a discipline of wide application; it also contributes significantly to an early diagnosis of subjects suspected to develop cognitive impairments due to Alzheimer disease or other degenerative dementias. Subjects at risk, and subjects who have already develop the illness, would particularly benefit of a telehealth intervention, which allows to overcome the barriers of space and time, and to provide an evaluation, as well as the therapy monitoring. These aspects would be particularly important for subjects who live far from health institutions , as those of rural areas. Obviously, we need to be sure that the results of the Tele-Neuropsychological assessment are comparable to those obtained via the classic '' face to face '' administration. This is the purpose of this research. We aimed in fact to compare the performances obtained in the two conditions at the MMSE test and the ADAS Cog test. To this purpose, we submitted a group of subjects affected by mild to moderate Alzheimer disease with associated vascular damages, to MMSE and the ADAS COG test, and performed a statistical analysis of data through a two sided Student ''t'' test. We found that the administration modality had no significant impact on the results. In fact, no significant difference was found neither in the MMSE, or in the ADAS_Cog scores administered by telehealth versus ''face to face''. While the results obtained at the MMSE confirm some previous data, this is, at our knowledge, the first study done on the ADAS_Cog, a test. Even if the conditions we employed in this research are not entirely superposable to those of patients staying at home (we evaluated the feasibility of teleheath by locating the patient and his caregiver in another room of the memory clinic ), we are confident that telehealth methodology, by video-conferencing, is as much reliable as the face to face modality. The small number of the subjects evaluated represents an obvious limitation of this study and suggests further studies involving larger number of subjects. However, our preliminary results give support to the idea that by tehealth the screening and the follow-up of the cognitive impairments age associated is feasible and valid.
29
Masson, Nancy Cristina. "Geis, vidros e compositos de polifosfato de calcio, de ferro (III) e mistos". [s.n.], 1996. http://repositorio.unicamp.br/jspui/handle/REPOSIP/250330.
Texto completoResumen
Orientadores: Fernando Galembeck, Elizabeth Fatima de SouzaDissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Quimica
Made available in DSpace on 2018-07-21T17:17:20Z (GMT). No. of bitstreams: 1 Masson_NancyCristina_M.pdf: 5042756 bytes, checksum: 5701ff18599d4eff4bece73f9386107f (MD5) Previous issue date: 1996
Mestrado
30
Zheng, Yilin. "Text-Based Speech Video Synthesis from a Single Face Image". The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1572168353691788.
Texto completo
31
Arachchige, Somi Ruwan Budhagoda. "Face recognition in low resolution video sequences using super resolution /". Online version of thesis, 2008. http://hdl.handle.net/1850/7770.
Texto completo
32
Greco, Antonio. "Real-time face analysis for gender recognition on video sequences". Doctoral thesis, Universita degli studi di Salerno, 2018. http://hdl.handle.net/10556/2978.
Texto completoResumen
2016 - 2017This research work has been produced with the aim of performing gender recognition in real-time on face images extracted from real video sequences. The task may appear easy for a human, but it is not so simple for a computer vision algorithm. Even on still images, the gender recognition classifiers have to deal with challenging problems mainly due to the possible face variations, in terms of age, ethnicity, pose, scale, occlusions and so on. Additional challenges have to be taken into account when the face analysis is performed on images acquired in real scenarios with traditional surveillance cameras. Indeed, the people are unaware of the presence of the camera and their sudden movements, together with the low quality of the images, further stress the noise on the faces, which are affected by motion blur, different orientations and various scales. Moreover, the need of providing a single classification of a person (and not for each face image) in real-time imposes to design a fast gender recognition algorithm, able to track a person in different frames and to give the information about the gender quickly. The real-time constraint acquires even more relevance considering that one of the goals of this research work is to design an algorithm suitable for an embedded vision architecture. Finally, the task becomes even more challenging since there are not standard benchmarks and protocols for the evaluation of gender recognition algorithms. In this thesis the attention has been firstly concentrated on the analysis of still images, in order to understand which are the most effective features for gender recognition. To this aim, a face alignment algorithm has been applied to the face images so as to normalize the pose and optimize the performance of the subsequent processing steps. Then two methods have been proposed for gender recognition on still images. First, a multi-expert which combines the decisions of classifiers fed with handcrafted features has been evaluated. The pixel intensity values of face images, namely the raw features, the LBP histograms and the HOG features have been used to train three experts which takes their decision by taking into account, respectively, the information about color, texture and shape of a human face. The decisions of the single linear SVMs have been combined with a weighted voting rule, which demonstrated to be the most effective for the problem at hand. Second, a SVM classifier with a chi-squared kernel based on trainable COSFIRE filters has been fused with an expert which rely on SURF features extracted in correspondence of certain facial landmarks. The complementarity of the two experts has been demonstrated and the decisions have been combined with a stacked classification scheme. An experimental evaluation of all the methods has been carried out on the GENDER-FERET and the LFW datasets with a standard protocol, so allowing the possibility to perform a fair comparison of the results. Such evaluation proved that the couple COSFIRE-SURF is the one which achieves the best accuracy in all the cases (accuracy of 94.7% on GENDER-FERET and 99.4% on LFW), even compared with other state of the art methods. Anyway, the performance achieved by the multi-expert which rely on the fusion of RAW, LBP and HOG classifiers can also be considered very satisfying (accuracy of 93.0% on GENDER-FERET and 98.4% on LFW)...[edited by Author]
XXX ciclo
33
Venkatesan, Janani. "Video Data Collection for Continuous Identity Assurance". Scholar Commons, 2016. http://scholarcommons.usf.edu/etd/6424.
Texto completoResumen
Frequently monitoring the identity of a person connected to a secure system is an important component in a cyber-security system. Identity Assurance (IA) mechanisms which continuously confirm and verify users’ identity after the initial authentication process ensure integrity and security. Such systems prevent unauthorized access and eliminate the need of an authorized user to present credentials repeatedly for verification. Very few cyber-security systems deploy such IA modules. These IA modules are typically based on computer vision and machine learning algorithms. These algorithms work effectively when trained with representative datasets. This thesis describes our effort at collecting a small dataset of multi-view videos of typical work session of several subjects to serve as a resource for other researchers of IA algorithms to evaluate and compare the performance of their algorithms with those of others. We also present a Proof of Concept (POC) face matching algorithm and experimental results with this POC implementation for a subset of collected dataset.
34
Smith, Barbara M. "Supervising Teaching Candidates Using Face-to-Face and Virtual Observations: Perceptions and Preferences of Special Educators". BYU ScholarsArchive, 2018. https://scholarsarchive.byu.edu/etd/7353.
Texto completoResumen
Providing effective supervision of student teachers and interns is critical in preparing quality special education teachers. To decrease the time commitment of supervisors, researchers have suggested using virtual observations which are generally viewed as a valuable resource. This study examined the experience of teacher candidates supervised with a combination of face-to-face visits and video observations. Groups of university faculty (supervisors) and students (teacher candidates) from a western university participated with both methods of supervision over three years and provided feedback to researchers. Results highlighted participants<'> satisfaction with the supervision process, including advantages and concerns with each type and ways the combination of methods gave added value and efficiency. Benefits of using the combination of observation types, which was most valued by both supervisors and candidates, were convenience and flexibility of scheduling, opportunities for self-evaluation, and the nature and timeliness of feedback. Future research might focus on using the combination of supervision methods with licensure candidates in other groups of professionals and teachers or examine specific aspects of using the technology.
35
Kroos, Christian. "A system for video-based analysis of face motion during speech". Diss., lmu, 2004. http://nbn-resolving.de/urn:nbn:de:bvb:19-21453.
Texto completo
36
Connolly, Jean-François. "Adapting heterogeneous ensembles with particle swarm optimization for video face recognition". Mémoire, École de technologie supérieure, 2012. http://espace.etsmtl.ca/1066/1/CONNOLLY_Jean%2DFran%C3%A7ois.pdf.
Texto completoResumen
Lorsqu’appliquée à la reconnaissance de visages à partir de séquences vidéo, la classification consiste typiquement à comparer des échantillons d’origine inconnue à des modèles biométriques (i.e., modèles de visages d’individus) conçus à l’aide d’échantillons de référence acquis à l’aide d’un senseur quelconque durant un processus d’inscription. Bien que les classificateurs neuronaux et statistiques offrent une solution flexible à ce type de problème, leur performance est grandement affectée par la disponibilité de données de référence représentatives. L’implication de personnes réelles durant le processus d’acquisition de données biométriques fait en sorte que la collecte et l’analyse de celles-ci sont souvent coûteuses et laborieuses. Bien qu’un nombre limité de données soit initialement disponible, de nouvelles données peuvent être acquises au fil du temps. Toutefois, l’absence de contrôle sur les conditions d’opération de systèmes de reconnaissance de visages et sur la physiologie des sujets à reconnaître a pour effet de soumettre les classificateurs à des environnements de classification complexes et changeants dans le temps.
Cette thèse aborde le problème en proposant un système de classificateurs multiples adaptatif (AMCS, pour «adaptive multiclassifier system») qui permet un apprentissage incrémental de nouvelles données disponibles durant l’inscription et la mise à jour de modèles biométriques.
L’AMCS utilise une stratégie d’apprentissage incrémental supervisé fondée sur l’optimisation dynamique avec essaims de particules (DPSO, pour «dynamic particle swarm optimization») qui permet l’évolution d’un essaim de réseaux de neurones fuzzy ARTMAP (FAM) à l’aide de nouvelles données sans corrompre les connaissances acquises. En associant chaque particule dans un espace de recherche d’hyperparamètres à un réseau FAM, cette dernière adapte la plasticité (ou dynamique d’apprentissage) des classificateurs en co-optimisant tous leurs paramètres – hyperparamètres, poids synaptiques et architecture – afin de maximiser la performance (exactitude), tout en minimisant le coût computationnel et les ressources en mémoire nécessaires. La réalisation de l’AMCS est le résultat de l’étude et de la caractérisation de la relation entre les environnements de classification et l’optimisation définis à l’aide de cette approche.
Une version initiale de la stratégie d’apprentissage incrémental est appliquée à un système de classification adaptatif (ACS, pour «adaptive classification system»), où la performance d’un seul réseau de neurones FAM est maximisée. Dans ce contexte, il est démontré qu’il faut reconsidérer deux aspects de la définition originale d’un système de classification pouvant faire un apprentissage incrémental. Non seulement la dynamique d’apprentissage du classificateur doit être adaptée afin de maintenir un haut niveau de performance dans le temps, mais certaines données acquises précédemment doivent être utilisées durant cette adaptation. La validité de cette nouvelle définition est vérifiée en démontrant empiriquement que l’adaptation de réseaux FAMdurant un apprentissage incrémental constitue un problème d’optimisation dynamique de type III, où la valeur et la position des optima locaux changent dans le temps. Les résultats démontrent également la nécessité d’une mémoire à long terme (LTM, pour «long term memory») qui emmagasine certaines données acquises précédemment à des fins de validation et d’estimation des performances sans biais durant le processus d’apprentissage.
La stratégie d’apprentissage incrémental est ensuite modifiée afin de faire évoluer un essaim (ou une réserve) de réseaux FAM d’un AMCS avec la possibilité d’en faire un ensemble. Ceci permet d’aborder un facteur clé du bon fonctionnement de ceux-ci : la diversité des classificateurs. À l’aide de plusieurs indicateurs de corrélation et de diversité, il est démontré que la diversité génotype (i.e., d’hyperparamètres) dans l’environnement d’optimisation est corrélée avec la diversité des classificateurs dans l’environnement de classification. À partir de ce résultat, les propriétés d’algorithmes DPSO cherchant à maintenir la diversité génotype des particules afin de repérer et suivre les optima locaux sont utilisées pour générer et évoluer un essaim de classificateurs FAM diversifiés. Un algorithme de recherche glouton est alors utilisé afin de sélectionner efficacement un ensemble en fonction de la performance et de la diversité sans l’utilisation d’indicateurs de diversité des classificateurs, coûteux à l’utilisation. Tout
en ayant une performance comparable, les ensembles résultants utilisent seulement une fraction des ressources nécessaires aux méthodes de référence fondées sur des ensembles et/ou un apprentissage par groupe («batch»).
Finalement, après avoir principalement étudié la relation entre l’environnement de classification et l’espace de recherche, l’espace des objectifs est également considéré durant la conception d’une dernière version des AMCS et d’une stratégie d’apprentissage incrémental. Un algorithme d’optimisation avec essaim de particules par agrégation et nichage dynamique (ADNPSO, pour «aggregated dynamical niching particle swarm optimization») est présenté afin de
guider les réseaux FAMen fonction de deux objectifs : la performance des réseaux FAMet leur coût computationnel. Plutôt que de solutionner un problème d’optimisation multi-objectif afin d’en trouver le front de Pareto optimal, l’algorithme ADNPSO cherche à générer une réserve de classificateurs pour lesquels les diversités génotype et phénotype (i.e., d’objectifs) sont maximisées. L’algorithme ADNPSO guide alors les particules vers les différents fronts de Pareto locaux en utilisant l’information disponible dans l’espace de recherche. Les classificateurs
sont ensuite catégorisés selon leur taille et emmagasinés dans une archive spécialisée d’après un critère de non-dominance local. Ces deux composantes sont alors intégrées à l’AMCS avec une stratégie d’apprentissage incrémental fondée sur l’ADNPSO.
L’AMCS est prometteur. Utilisé conjointement avec la stratégie d’apprentissage fondée sur l’ADNPSO dans le but de créer un ensemble de réseaux FAM, celui-ci a offert une performance comparable à celle obtenue avec des méthodes d’ensembles utilisant des combinaisons d’optimisation mono-objectif et d’apprentissage incrémental, pour seulement une fraction du coût computationnel.
37
VEGA, PEDRO JUAN SOTO. "SINGLE SAMPLE FACE RECOGNITION FROM VIDEO VIA SATCKED SUPERVISED AUTO-ENCODER". PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2016. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=28102@1.
Texto completoResumen
PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIROCOORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
PROGRAMA DE EXCELENCIA ACADEMICA
Esta dissertação propõe e avalia estratégias baseadas nos Stacked Supervised Auto-encoders (SSAE) para representação de imagens faciais em aplicações de vídeo vigilância. O estudo foca na identificação de faces a partir de uma amostra por pessoa na galeria (single sample per person - SSPP). Variações em termos de pose, expressão facial, iluminação e oclusão são abordadas de duas formas. Primeiro, o SSAE extrai atributos das imagens de faces que são robustos contra tais variações. Segundo, exploram-se as múltiplas amostras que podem ser coletadas nas sequências de vídeo de uma pessoa (multiple samples per person probe - MSPPP). Os métodos propostos foram avaliados e comparados usando os bancos de vídeos Honda/UCSD e VIDTIMIT. Adicionalmente, foi estudada a influência de parâmetros relacionados com a arquitetura do SSAE utilizando o banco de imagens estáticas Extended Yale B. Os resultados demonstraram que as estratégias que exploram as MSPPP em combinação com o SSAE podem superar o desempenho de outros métodos SSPP, como os Padrões Binários Locais (LBP), para reconhecimento de faces em vídeos.
This work proposes and evaluates strategies based on Stacked Supervised Auto-encoders (SSAE) for face representation in video surveillance applications. The study focuses on the identification task with a single sample per person (SSPP) in the gallery. Variations in terms of pose, facial expression, illumination and occlusion are approached in two ways. First, the SSAE extracts features from face images, which are robust to such variations. Second, multiple samples per persons probes (MSPPP) that can be extracted from video sequences are exploited to improve recognition accuracy. The proposed methods were compared upon Honda/UCSD and VIDTIMIT video datasets. Additionally, the influence of the parameters related to SSAE architecture was studied using the Extended Yale B dataset. The experimental results demonstrated that strategies combining SSAE and MSPPP are able to outperform other SSPP methods, such as local binary patterns, in face recognition from video.
38
Rahman, Anis Ur. "Face perception in videos : contributions to a visual saliency model and its implementation on GPUs". Thesis, Grenoble, 2013. http://www.theses.fr/2013GRENT102/document.
Texto completoResumen
Les études menées dans cette thèse portent sur le rôle des visages dans l'attention visuelle. Nous avons cherché à mieux comprendre l'influence des visages dans les vidéos sur les mouvements oculaires, afin de proposer un modèle de saillance visuelle pour la prédiction de la direction du regard. Pour cela, nous avons analysé l'effet des visages sur les fixations oculaires d'observateurs regardant librement (sans consigne ni tâche particulière) des vidéos. Nous avons étudié l'impact du nombre de visages, de leur emplacement et de leur taille. Il est apparu clairement que les visages dans une scène dynamique (à l'instar de ce qui se passe sur les images fixes) modifie fortement les mouvements oculaires. En nous appuyant sur ces résultats, nous avons proposé un modèle de saillance visuelle, qui combine des caractéristiques classiques de bas-niveau (orientations et fréquences spatiales, amplitude du mouvement des objets) avec cette caractéristique importante de plus haut-niveau que constitue les visages. Enfin, afin de permettre des traitements plus proches du temps réel, nous avons développé une implémentation parallèle de ce modèle de saillance visuelle sur une plateforme multi-GPU. Le gain en vitesse est d'environ 130 par rapport à une implémentation sur un processeur multithreadStudies conducted in this thesis focuses on faces and visual attention. We are interested to better understand the influence and perception of faces, to propose a visual saliency model with face features. Throughout the thesis, we concentrate on the question, "How people explore dynamic visual scenes, how the different visual features are modeled to mimic the eye movements of people, in particular, what is the influence of faces?" To answer these questions we analyze the influence of faces on gaze during free-viewing of videos, as well as the effects of the number, location and size of faces. Based on the findings of this work, we propose model with face as an important information feature extracted in parallel alongside other classical visual features (static and dynamic features). Finally, we propose a multi-GPU implementation of the visual saliency model, demonstrating an enormous speedup of more than 132 times compared to a multithreaded CPU
39
Weidenstolpe, Louise y Jade Jönsson. "Manipulation i rörligt format - En studie kring deepfake video och dess påverkan". Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20573.
Texto completoResumen
Med deepfake-teknologi kan det skapas manipulerade videor där det produceras falska bilder och ljud som framställs vara verkliga. Deepfake-teknologin förbättras ständigt och det kommer att bli svårare att upptäcka manipulerade videor online. Detta kan innebära att en stor del mediekonsumenter omedvetet exponeras för tekniken när de använder sociala medier. Studiens syfte är att undersöka unga vuxnas medvetenhet, synsätt och påverkan av deepfake videor. Detta eftersom deepfake-teknologin förbättras årligen och problemen med tekniken växer samt kan få negativa konsekvenser i framtiden om den utnyttjas på fel sätt. Insamlingen av det empiriska materialet skedde genom en kvantitativ metod i form av en webbenkät och en kvalitativ metod med tre fokusgrupper. Slutsatsen visade på att det finns ett större antal unga vuxna som inte är medvetna om vad en deepfake video är, dock existerar det en viss oro för deepfake-teknologin och dess utveckling. Det upplevs att det finns risker för framtiden med teknologin i form av hot mot demokratin och politik, spridning av Fake news, video-manipulation samt brist på källkritik. De positiva aspekterna är att tekniken kan användas i sammanhang av humor, inom film- och TV-industrin samt sjukvård. Ytterligare en slutsats är att unga vuxna kommer att vara mer källkritiska till innehåll de exponeras av framöver, dock kommer de med stor sannolikhet ändå att påverkas av deepfake-teknologin i framtiden.Manipulated videos can be created with deepfake technology, where fake images and sounds are produced and seem to be real. Deepfake technology is constantly improving and it will be more problematic to detect manipulated video online. This may result in a large number of media consumers being unknowingly exposed to deepfake technology while using social media. The purpose of this study is to research young adults' awareness, approach and impact of deepfake videos. The deepfake technology improves annually and more problems occur, which can cause negative consequences in the future if it’s misused. The study is based on a quantitative method in the form of a web survey and a qualitative method with three focus groups. The conclusion shows that there’s a large number of young adults who are not aware of what a deepfake video is, however there’s some concern about deepfake technology and its development. It’s perceived that there can be risks in the future with the technology in terms of threats to democracy and politics, distribution of Fake news, video manipulation and lack of source criticism. The positive aspects are that the technology can be used for entertainment purposes, in the film and television industry also in the healthcare department. Another conclusion is that young adults will be more critical to the content they are exposed to in the future, but likely be affected by deepfake technology either way.
40
Kramer, Kathryn Daugherty. "The effects of video programming, face-to-face instruction, modeling, and feedback on nutritious and economical food purchases". Diss., Virginia Polytechnic Institute and State University, 1988. http://hdl.handle.net/10919/53560.
Texto completoResumen
Currently, there is a public health need for effective and economical strategies designed to influence appropriate dietary modifications in the general public (e.g., reduction of dietary fats). To address this need, this study applied the behavioral systems framework in its design and application to nutrition change.
The primary research question was to experimentally assess the differential impacts of a combined media and personal interaction condition (specifically using participant modeling procedures) to a condition that combined media and personal attention strategies. A no treatment condition was also employed. Previous research had shown robust changes with interventions that combined media and personal interaction. This study addressed whether those changes were due to the procedures or to the personal attention received. To examine this question, self-report data on foods purchased and data from supermarket receipts were collected from 45 households across the 3 conditions.
Results indicated that persons in the media and personal interaction condition did demonstrate significant changes in the desired direction in the percentage of total fat content in foods purchased. A comparable change was not noted in the other conditions. Thus, it was concluded that some combination of factors (i.e., modeling, reinforcement, feedback, and goal setting) in addition to the procedures used in the video and personal attention provided in the participant modeling, were responsible for the dramatic decreases in total fats. From this study, it was not possible to determine which of the psychological principles were most effective in inducing change.
In addition to the experimental findings, subject characteristics (e.g., beliefs, knowledge, health locus of control, skills, self-efficacy, etc.) was examined. The results did not lead to a general set of individual characteristics being related to nutritional outcome. Rather, the information contributed to a clearer understanding of the needs of the sample and the environmental constraints and inducements for nutritional change in that target group.
Given the threat of dietary fat to the health of the American public, the reduction in total fat found in this study was an important finding. The application of the behavioral systems framework provided the necessary information to enable the message of the video and the modeling, feedback, and goal setting components to be effective in changing total fats among a segment of the target sample.Ph. D.
41
Kramer, Annika. "Model based methods for locating, enhancing and recognising low resolution objects in video". Thesis, Curtin University, 2009. http://hdl.handle.net/20.500.11937/585.
Texto completoResumen
Visual perception is our most important sense which enables us to detect and recognise objects even in low detail video scenes. While humans are able to perform such object detection and recognition tasks reliably, most computer vision algorithms struggle with wide angle surveillance videos that make automatic processing difficult due to low resolution and poor detail objects. Additional problems arise from varying pose and lighting conditions as well as non-cooperative subjects. All these constraints pose problems for automatic scene interpretation of surveillance video, including object detection, tracking and object recognition.Therefore, the aim of this thesis is to detect, enhance and recognise objects by incorporating a priori information and by using model based approaches. Motivated by the increasing demand for automatic methods for object detection, enhancement and recognition in video surveillance, different aspects of the video processing task are investigated with a focus on human faces. In particular, the challenge of fully automatic face pose and shape estimation by fitting a deformable 3D generic face model under varying pose and lighting conditions is tackled. Principal Component Analysis (PCA) is utilised to build an appearance model that is then used within a particle filter based approach to fit the 3D face mask to the image. This recovers face pose and person-specific shape information simultaneously. Experiments demonstrate the use in different resolution and under varying pose and lighting conditions. Following that, a combined tracking and super resolution approach enhances the quality of poor detail video objects. A 3D object mask is subdivided such that every mask triangle is smaller than a pixel when projected into the image and then used for model based tracking. The mask subdivision then allows for super resolution of the object by combining several video frames. This approach achieves better results than traditional super resolution methods without the use of interpolation or deblurring.Lastly, object recognition is performed in two different ways. The first recognition method is applied to characters and used for license plate recognition. A novel character model is proposed to create different appearances which are then matched with the image of unknown characters for recognition. This allows for simultaneous character segmentation and recognition and high recognition rates are achieved for low resolution characters down to only five pixels in size. While this approach is only feasible for objects with a limited number of different appearances, like characters, the second recognition method is applicable to any object, including human faces. Therefore, a generic 3D face model is automatically fitted to an image of a human face and recognition is performed on a mask level rather than image level. This approach does not require an initial pose estimation nor the selection of feature points, the face alignment is provided implicitly by the mask fitting process.
42
El, Seuofi Sherif M. "Performance Evaluation of Face Recognition Using Frames of Ten Pose Angles". Youngstown State University / OhioLINK, 2007. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1198184813.
Texto completo
43
Dominguez, David Renato Carreta. "Modelo de anisotropia uniaxial aleatória infinita". reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 1993. http://hdl.handle.net/10183/149203.
Texto completoResumen
Contribui-se para a compreensão do modelo de anisotropia uniaxial aleatória, conhecido como "random-axis model" (RAM) que representa ligas de terra-rara com metal. Deu-se atenção especial ao limite de Ising (IRAM) do sistema que ocorre para anisotropia muito grande. Estudou-se a dependência da termodinâmica do IRAM com os seguintes parâmetros relevantes: i) a isotropia e a obliquidade (b) (em oposiÇão à anisotropia cubica) da distribuição dos eixos aleatórios; ii) a saturação, defmida como a razão entre dimensão de spin e conectividade da rede, a =p/ c . As variáveis relevantes são a magnetização e o parâmetro de ordem de vidro-de-spin. O último emerge da "fusão " das infinitas componentes transversais ao overlap, cuja direção é aquela da magnetização macroscópica. Como resultado principal encontramos que a natureza da fase ordenada altera-se substancialmente com b. Acima de um certo valor crítico bcM(T) aparecem estados de Mattis como mínimos globais não-degenerados, em oposição a estados diagonais para b menor que um valor crítico inferior bcn (T). Estados mixtós surgem no intervalo bcn ≤ b ≤ bCM. Enfatizou-se o caso de a finito, para o qual construiu-se diagramas de fases através da Teoria de Campo Médio (TCM), usando o método de réplicas. A conclusão central foi a diminuição da região ferromagnética com a. A fim de confirmar os resultados da termodinâmica obtivemos relações de recorrência para a dinâmica de relaxação, com realimentação (feedback). Para isso, além do Overlap e da Dispersão dos resíduos, introduziu-se um parâmetro de Autocorrelação. Foi possível construir as bacias de atração para essas três variáveis, caracterizando o regime estático.This is a contribution to the understanding of the model of random uniaxial anisotropy, also known as the random-axis model (RAM), which describes the properties of compounds of rare-earths with metals. Special attention has been given to the Ising limit (IRAM) of the system which occurs for large anisotropy. The dependence of the thermodynamics of the IRAM with the following relevant paramenters has been studied: i) the isotropy and off-cubical ordering (b) of the distribution of random axis (in contrast to cubic anisotropy); i i) the saturation, de:fined as the r a tio betweéri the spin dimension and lattice connectivity, a = p/ c. The relevant variables are the magnetization and the spin-glass order parameter. The latter appears as a "melting" of the in:finite transverse components to the overlap, whose direction is those of macroscopic magnetization. As a main result we find that the nature of the ordered phase is altered in an essential way with b. Above an upper cri ti cal value beM (T) there are Mattis states which appear as non-degenerate global mínima, in contrast to diagonal states for b below a lower criticai value bcn (T). Mixed states appear in the range bcn ≤ b ≤ bcm. Emphasis is made on the finite-a case, for which replica-symmetric meanfield theory is used to derive phase-diagrams. A central result is the reduction of the ferromagnetic phase with a. Recursion relations were derived for the dynamics in order to verify the thermodynamic results in th long-time limit. For that purpose, a selfcorrelation has been introduced, in addition to the usual overlap and dispersion of residues. Basins of attraction were obtained characterizing the static behaviour.
44
Bhattarai, Smrity. "Digital Architecture for real-time face detection for deep video packet inspection systems". University of Akron / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=akron1492787219112947.
Texto completo
45
Lieskovský, Pavol. "Parametrizace tváře pomocí videosekvence". Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2019. http://www.nusl.cz/ntk/nusl-400951.
Texto completoResumen
This work deals with the problem of face parameterization from the video of a speaking person and estimating Parkinson’s disease and the progress of its symptoms based on face parameters. It describes the syntax and function of the program that was created within this work and solves the problem of face parameterization. The program formats the processed data into a time series of parameters in JSON format. From these data, a dataset was created, based on which artificial intelligence models were trained to predict Parkinson’s disease and the progress of its symptoms. The process of model training and their results are documented within this work.
46
Huang, Kohsia Samuel. "Multilevel analysis of human body, face, and gestures with networked omni video array /". Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2005. http://wwwlib.umi.com/cr/ucsd/fullcit?p3167818.
Texto completo
47
Manohar, Vasant. "Facial skin motion properties from video : modeling and applications". [Tampa, Fla] : University of South Florida, 2009. http://purl.fcla.edu/usf/dc/et/SFE0003288.
Texto completo
48
Liarte, Danilo Barbosa. "Modelos estatísticos de campo médio para vidros de spins e fluidos complexos". Universidade de São Paulo, 2011. http://www.teses.usp.br/teses/disponiveis/43/43134/tde-29092011-144333/.
Texto completoResumen
Estudamos nesta tese três sistemas desordenados distintos das áreas de vidros de spins e fluidos complexos, por meio de modelos estatísticos no contexto da aproximação de campo médio. Analisamos os efeitos da inclusão de graus de liberdade elásticos sobre o diagrama de fases do modelo de Sherrington-Kirkpatrick, que é a versão de campo médio de um modelo popular de vidros de spins, paradigmas de sistemas com desordem temperada. Analisamos em seguida alguns problemas típicos da física dos fluidos complexos. Investigamos o diagrama de fases de um modelo de Maier-Saupe (MS), que é uma espécie de arquétipo das transições nemáticas, numa versão de rede muito simples, denominada modelo de Maier-Saupe-Zwanzig (MSZ), com a introdução de uma variável binária de desordem para representar uma mistura de discos e cilindros. Mostramos que o aparecimento de uma fase nemática biaxial, termodinamicamente estável, que tem sido intensamente procurada na literatura, depende da forma de tratamento das variáveis de desordem. Finalmente, utilizamos o modelo MSZ, na presença de termos elásticos não lineares e de elementos de desordem, a fim de reproduzir diversas características do comportamento termodinâmico dos elastômeros nemáticos, novos materiais poliméricos, com propriedades dos cristais líquidos nemáticos e das borrachas, tema de grande interesse na física da matéria mole.We study three distinct disordered systems in the areas of spin glasses and complex fluids, by means of mean-field statistical models. We first analyze the effects of compressibility on the phase diagram of the Sherrington-Kirkpatrick model, a mean-field version of a popular model of spin glasses, which are paradigmatic examples of systems with quenched disorder. We then analyze some typical problems in the area of physics of complex fluids. We investigate the phase diagram of a Maier-Saupe model (MS), which is a sort of archetype of nematic transitions, in a simple lattice version called Maier-Saupe-Zwanzig model (MSZ), with the introduction of a binary variable of disorder to mimic a mixture of rod-like and plate-like mesogens. We show that the emergence of a stable nematic biaxial phase, which has been intensely pursued in the literature, depends on the form of treatment of the disorder variables. Finally, we use the MSZ model, in the presence of non-linear elastic terms and elements of disorder, to reproduce several aspects of the thermodynamic behavior of nematic elastomers, new polymeric materials with the properties of liquid crystals and rubber, and of great importance in the area of soft-matter physics.
49
Santos, Fabricio Simão dos. "Novas ligas formadoras de fase amorfa do sistema Ni-Nb-Zr e seu comportamento mecânico". Universidade Federal de São Carlos, 2011. https://repositorio.ufscar.br/handle/ufscar/679.
Texto completoResumen
Made available in DSpace on 2016-06-02T19:10:05Z (GMT). No. of bitstreams: 1
3730.pdf: 2572602 bytes, checksum: 22ea795f7954d00c959f0b06c4adad81 (MD5)
Previous issue date: 2011-04-15Universidade Federal de Minas Gerais
Ni-based amorphizable alloys in the bulk form show a good combination of properties, with high mechanical strength and hardness, good ductility and excellent corrosion resistance. These alloys have been used in recent technological applications, for example, in pressure sensors and micro-geared motors. Particularly, Ni-Nb-Zr alloys with amorphous structure show, in addition to good mechanical properties, excellent corrosion resistance in acid medium due to the formation of a Nb- and Zr-rich passive film. In this context, the purpose of this project is to develop Ni-Nb-Zr alloys with high glass-forming ability (GFA) by using the topological λ criterion combined with the average electronegativity difference, Δe , and to carry out its mechanical characterization by nanoindentation. Ni45.5Nb23Zr31.5, Ni50Nb28Zr22, Ni57Nb17.5Zr25.5 and Ni79Nb8.5Zr12.5 alloys were selected and produced in the form of melt-spun ribbons and copper mold cast wedges. The samples were analyzed by inductively coupled plasma mass spectrometry (ICP-MS), scanning electron microscopy/energy dispersive spectroscopy (SEM/EDS), X-ray diffraction (XRD), differential scanning calorimetry (DSC) and nanoindentation. Results from the processing of wedge samples revealed the highest GFA for the Ni50Nb28Zr22 alloy, which presented 60% of amorphous fraction for a thickness of 200 μm and 23% for thickness of 320-480 μm. The alloy Ni45.5Nb23Zr31.5 showed the second highest GFA, making possible to obtain 14% of amorphous fraction for a thickness of 240 μm. The hardness and reduced elastic modulus of the ribbon samples increased in the following order: Ni45.5Nb23Zr31.5 < Ni50Nb28Zr22 < Ni57Nb17.5Zr25.5. For the Ni50Nb28Zr22 alloy, it was attained higher hardness and elastic modulus and lower plastic energy for the wedge compared to the ribbon, which can be ascribed to the higher amount of free volume in the structure of the amorphous ribbon. The compressive yield stress (σy,C) of this alloy was estimated to be 2.5 and 3.2 GPa for ribbon and wedge, respectively. viii
As ligas amorfizáveis de grande volume ou maciças à base de Ni apresentam boa combinação de propriedades, com altos valores de resistência mecânica e dureza, boa dutilidade e excelente resistência à corrosão. Essas ligas têm sido utilizadas em recentes aplicações tecnológicas, por exemplo, em sensores de pressão e em motores com microengrenagens. Especificamente, as ligas Ni-Nb-Zr com estrutura amorfa apresentam, além de boas propriedades mecânicas, excelente resistência à corrosão em meio ácido pela formação de um filme passivo rico em Nb e Zr. Nesse contexto, a proposta do presente trabalho é o desenvolvimento de ligas com alta tendência de formação de estrutura amorfa (TFA) do sistema Ni-Nb-Zr pela aplicação do critério topológico λ combinado com a diferença de eletronegatividade média, Δe , e sua caracterização mecânica por nanoindentação. Foram selecionadas as ligas Ni45,5Nb23Zr31,5, Ni50Nb28Zr22, Ni57Nb17,5Zr25,5 e Ni79Nb8,5Zr12,5, produzidas na forma de fita por melt-spinning e de cunha por fundição em molde de cobre. As amostras foram caracterizadas por espectrometria de massa por ionização acoplada por plasma (ICP-MS), microscopia eletrônica de varredura/espectroscopia de energia dispersiva (MEV/EDS), difratometria de raios X (DRX), calorimetria diferencial de varredura (DSC) e nanoindentação. Os resultados do processamento de amostras em forma de cunha apontaram maior TFA para a liga Ni50Nb28Zr22, que apresentou 60% de fração amorfa para uma espessura de 200 μm e 23% para espessura de 320-480 μm. A liga Ni45,5Nb23Zr31,5 apresentou a segunda maior TFA, possibilitando a obtenção de 14% de fração amorfa para uma espessura de 240 μm. A dureza e o módulo elástico reduzido das amostras de fita aumentaram na seguinte seqüência: Ni45,5Nb23Zr31,5 < Ni50Nb28Zr22 < Ni57Nb17,5Zr25,5. A liga Ni50Nb28Zr22 apresentou maior dureza, maior módulo elástico e menor energia plástica na forma de cunha do que na forma de fita, o que pode ser atribuído ao maior volume livre contido na estrutura da fita. A tensão de escoamento em compressão (σy,C) da liga Ni50Nb28Zr22 foi estimada em 2,5 e 3,2 GPa em forma de fita e de cunha, respectivamente.
50
Karlsson, Erik. "Fake it till you make it : En självstudie i instudering och tillämpning i jazz- och stråkorkester". Thesis, Karlstads universitet, Institutionen för konstnärliga studier (from 2013), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-78985.
Texto completoResumen
I följande studie kommer jag redovisa resultatet ifrån den självstudie som jag har bedrivit i syfte av att utforska huruvida min instuderingsprocess skiljer sig utifrån jazz- och klassisk repertoar på instrumentet kontrabas. Studien redovisar även hur jag erhåller och nyttjar den instuderade tekniken och materialet i de givna jazz- och stråkorkestertillfällena, samt om hur instuderingen skiljer sig i den mån av tidigare erfarenheter kunskaper. Studien tar form utifrån hur jag som erfaren jazzbassist instuderar och spelar i stråkorkester som novis i den miljön, samt hur jag fördjupar mitt instuderande till jazzensemblerna. I syfte att studien har ett stort fokus på instudering och ensemblespel så diskuteras även huruvida de olika ensemblekulterna skiljer sig i mån av styrning, inflytande och uttryck. Arbetet bearbetas genom videodokumentation som sker under instudering- och övningspass, samt ensembletillfällen. Matrealet bearbetas sedan genom transkription och analys där matre- alet kategoriseras efter olika kategorier i syfte att besvara mina frågeställningar. Arbetet utgår utifrån ett sociokulturellt perspektiv och där med har ett fokus på hur jag brukar kunskap och artefakter i olika kulturer och miljöer, samt hur jag lär mig utifrån de olika ensembleformerna. Resultatet i arbetet visar hur notläsningen i stråkorkestern är direkt kopplat till mitt gehör, och genom instudering av notmatrealet så betingas mitt gehör till min psykomotorik. Studien visar även huruvida mina bristande tekniska förutsättningar med redskapet stråken bidrar till att jag flyttar blicken ifrån noten till stråken, vilket får konsekvenser i mån av flöde och koncentrat- ion i spelandet. I mån av det musikaliskt flöde som befinner sig i orkestern så underlättas not- läsningen genom ensemblens harmoniska samspel och tempo. De olika ensembleformerna vi- sar sig skilja sig markant i mån av styrning och inflytande vilket kan kopplas till de ensemb- lernas skillnader i mån av storlek. Studien redovisar även hur brukandet av andra instrument bidrar till en större uppfattning av repertoaren till jazzensemblen, vilket får positiva fördelar i mån av gehör, improvisation och formkänsla.In the following study I will report the results from the self-study i have conducted in order to explore whether my study process differs based on jazz and classical repertoire on the instru- ment double bass. The study also reports whether I obtain and use the studied technique and the material in the given jazz and string orchestra occasions, and how the study differs to the extent of previous experience knowledge. The study takes the form of how I, as an experienced jazz bassist study and play in string or- chestras as a novice in that environment, and how I deepen my study of the jazz ensembles. In order that the study has a great focus on study and ensemble play, it will also be discussed whether the different ensemble cultures differ in terms of control, influence and expression. The work is processed through video documentation that takes place during study and practice sessions, as well as ensemble occasions for the purpose of follow-up. The video documentation will be processed through transcription and analysis where the material is categorized according to different categories in order to answer lesser questions. The work is based on a socio-cultural perspective and with a focus on how I use knowledge and artifacts in different musical cultures and environments, and how I learn based on the different ensemble forms. The result of the work shows how the note reading in the string orchestra is directly connected to my hearing, and by studying the sheet music, my hearing is conditioned to my psychomotor skills. The study also shows whether less technical deficiencies with the implement strings contribute to moving the gaze from the note to the strings, which has consequences in terms of flow and concentra- tion. As far as the musical flow in the orchestra is concerned, the note reading is facilitated by the ensemble's harmonious interaction and tempo. The different ensemble forms appear to differ markedly in terms of control and influence which can be linked to the differences of the ensem- bles in terms of size. The study also shows how the use of other instruments contributes to a greater perception of the repertoire of the jazz ensemble, which receives positive benefits as far as hearing, improvisation and sense of form are concerned.