Dissertations / Theses on the topic 'REAL TIME RECOGNITION'
To see the other types of publications on this topic, follow the link: REAL TIME RECOGNITION.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'REAL TIME RECOGNITION.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Cao, Hua. "Real Time Traffic Recognition." Thesis, Uppsala University, Department of Information Technology, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-89414.
Full textAbstract:
The rapid growth of Internet in size and complexity, and frequent emergence of new network applications have made it necessary to develop techniques that can monitor and control the traffic. Efficient and accurate recognition of traffic is the key to the management in real time. This thesis work accomplishes the performance evaluation and optimization of a traffic recognition tool called Traffic Analyzer Module (TAM) which implements a technique that is based on passively observing and identifying signature patterns of the packet payload at the application layer, says signature-based payload recognition. This technique has two highlighted features. Firstly, in contrast to most of previous works which perform classification with offline trace files; this technique applies in online mode which can identify the traffic in real time. Secondly, instead of packet inspection, this technique adopts flow inspection, i.e. identifying traffic in terms of flows each of which consists of the well-known 5-tuple, which canproduce more accurate and reliable results.
To demonstrate this technique, its throughput is evaluated in online mode within a high bandwidth network. Besides throughput measurement, optimizing the recognition algorithm in order to improve its performance is also a task of this thesis work. The results of performance measurement demonstrate the feasibility and reliability of this technique, as well as indicate some clues for future work.
2
Morrill, Jeffrey P., and Jonathan Delatizky. "REAL-TIME RECOGNITION OF TIME-SERIES PATTERNS." International Foundation for Telemetering, 1993. http://hdl.handle.net/10150/608854.
Full textAbstract:
International Telemetering Conference Proceedings / October 25-28, 1993 / Riviera Hotel and Convention Center, Las Vegas, NevadaThis paper describes a real-time implementation of the pattern recognition technology originally developed by BBN [Delatizky et al] for post-processing of time-sampled telemetry data. This makes it possible to monitor a data stream for a characteristic shape, such as an arrhythmic heartbeat or a step-response whose overshoot is unacceptably large. Once programmed to recognize patterns of interest, it generates a symbolic description of a time-series signal in intuitive, object-oriented terms. The basic technique is to decompose the signal into a hierarchy of simpler components using rules of grammar, analogous to the process of decomposing a sentence into phrases and words. This paper describes the basic technique used for pattern recognition of time-series signals and the problems that must be solved to apply the techniques in real time. We present experimental results for an unoptimized prototype demonstrating that 4000 samples per second can be handled easily on conventional hardware.
3
Zhu, Jian Ke. "Real-time face recognition system." Thesis, University of Macau, 2005. http://umaclib3.umac.mo/record=b1636556.
Full text
4
Amplianitis, Konstantinos. "3D real time object recognition." Doctoral thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät, 2017. http://dx.doi.org/10.18452/17717.
Full textAbstract:
Die Objekterkennung ist ein natürlicher Prozess im Menschlichen Gehirn. Sie ndet im visuellen Kortex statt und nutzt die binokulare Eigenschaft der Augen, die eine drei- dimensionale Interpretation von Objekten in einer Szene erlaubt. Kameras ahmen das menschliche Auge nach. Bilder von zwei Kameras, in einem Stereokamerasystem, werden von Algorithmen für eine automatische, dreidimensionale Interpretation von Objekten in einer Szene benutzt. Die Entwicklung von Hard- und Software verbessern den maschinellen Prozess der Objek- terkennung und erreicht qualitativ immer mehr die Fähigkeiten des menschlichen Gehirns. Das Hauptziel dieses Forschungsfeldes ist die Entwicklung von robusten Algorithmen für die Szeneninterpretation. Sehr viel Aufwand wurde in den letzten Jahren in der zweidimen- sionale Objekterkennung betrieben, im Gegensatz zur Forschung zur dreidimensionalen Erkennung. Im Rahmen dieser Arbeit soll demnach die dreidimensionale Objekterkennung weiterent- wickelt werden: hin zu einer besseren Interpretation und einem besseren Verstehen von sichtbarer Realität wie auch der Beziehung zwischen Objekten in einer Szene. In den letzten Jahren aufkommende low-cost Verbrauchersensoren, wie die Microsoft Kinect, generieren Farb- und Tiefendaten einer Szene, um menschenähnliche visuelle Daten zu generieren. Das Ziel hier ist zu zeigen, wie diese Daten benutzt werden können, um eine neue Klasse von dreidimensionalen Objekterkennungsalgorithmen zu entwickeln - analog zur Verarbeitung im menschlichen Gehirn.Object recognition is a natural process of the human brain performed in the visual cor- tex and relies on a binocular depth perception system that renders a three-dimensional representation of the objects in a scene. Hitherto, computer and software systems are been used to simulate the perception of three-dimensional environments with the aid of sensors to capture real-time images. In the process, such images are used as input data for further analysis and development of algorithms, an essential ingredient for simulating the complexity of human vision, so as to achieve scene interpretation for object recognition, similar to the way the human brain perceives it. The rapid pace of technological advancements in hardware and software, are continuously bringing the machine-based process for object recognition nearer to the inhuman vision prototype. The key in this eld, is the development of algorithms in order to achieve robust scene interpretation. A lot of recognisable and signi cant e ort has been successfully carried out over the years in 2D object recognition, as opposed to 3D. It is therefore, within this context and scope of this dissertation, to contribute towards the enhancement of 3D object recognition; a better interpretation and understanding of reality and the relationship between objects in a scene. Through the use and application of low-cost commodity sensors, such as Microsoft Kinect, RGB and depth data of a scene have been retrieved and manipulated in order to generate human-like visual perception data. The goal herein is to show how RGB and depth information can be utilised in order to develop a new class of 3D object recognition algorithms, analogous to the perception processed by the human brain.
5
David, Afshin. "Real-time methods for face recognition." Thesis, University of Ottawa (Canada), 1996. http://hdl.handle.net/10393/9664.
Full textAbstract:
Identification of individuals on the basis of facial features is the most natural method of distinguishing one individual from another. Automating such a process, based upon quantifiable measures, is of great interest in a variety of applications, such as passport identification and automatic teller machine verification. The most crucial aspect of such applications is their tolerance with respect to variations in facial expressions and the noise introduced by the operating environment. In this thesis, various face recognition methods are evaluated under conditions of real-time response, varying operating factors, and implementation feasibility. The approaches are based on histogram mapping, wavelet transform, Karhunen and Loeve transform, and optical correlation techniques. A brief review of the basic concepts in optics is first presented. This is followed by a detailed review of optical methods in pattern recognition. A comprehensive background of algorithmic approaches for face recognition is described. A detailed analysis of the photobook system, which is based on the Karhunen and Loeve transform (KLT), is presented. It is argued that, even though the KLT possesses many useful attributes in image processing applications, the performance of KLT face recognition systems is based entirely upon the initial training set. A method for choosing the proper training set is presented. Novel statistical methods that exploit the stationary behaviour of the operating environment are introduced. It is shown that under the condition that control may be exercised on the operating environment, these methods provide a satisfactory result in real-time. The application of histogram, moment, and 2-D discrete wavelet transforms in statistical methods is described. A novel optical correlation based system is presented. It is shown that such a system tolerates changes in facial expressions and can operate under real time constraints.
6
Liaqat, Ahmad Gull. "Mobile Real-Time License Plate Recognition." Thesis, Linnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-15944.
Full textAbstract:
License plate recognition (LPR) system plays an important role in numerous applications, such as parking accounting systems, traffic law enforcement, road monitoring, expressway toll system, electronic-police system, and security systems. In recent years, there has been a lot of research in license plate recognition, and many recognition systems have been proposed and used. But these systems have been developed for computers. In this project, we developed a mobile LPR system for Android Operating System (OS). LPR involves three main components: license plate detection, character segmentation and Optical Character Recognition (OCR). For License Plate Detection and character segmentation, we used JavaCV and OpenCV libraries. And for OCR, we used tesseract-ocr. We obtained very good results by using these libraries. We also stored records of license numbers in database and for that purpose SQLite has been used.
7
Papageorgiu, Dimitrios. "Cursive script recognition in real time." Thesis, University of Sussex, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.317243.
Full text
8
Ord, Leslie B. "Real-time stereo image matching for a real time photogrammetry system." Thesis, University of Aberdeen, 1997. http://digitool.abdn.ac.uk/R?func=search-advanced-go&find_code1=WSN&request1=AAIU603183.
Full textAbstract:
With the development of powerful, relatively low cost, digital image processing hardware capable of handling multiple image streams, it has become possible to implement affordable digital photogrammetry systems based on this technology. In addition, high speed versions of this hardware have the ability to manipulate these image streams in 'realtime', enabling the photogrammetry systems developed to expand their functionality from the off-line surveying of conventional photogrammetry to more time-critical domains such as object tracking and control systems. One major hurdle facing these 'real-time' photogrammetry systems is the need to extract the corresponding points from the multiple input images in order that they may be processed and measurements obtained. Even a highly skilled operator is not capable of manually processing the images in such a time that the speed of operation of the system would not be severely compromised. Thus an automatic system of matching these points is required. The use of automated point matching in the field of photogrammetry has been extensively investigated in the past. The objective has, however, been primarily to reduce the need for trained operators employed in the extraction of data from conventional photogrammetric studies and in the automation of data extraction from large data sets. The work presented here attempts to adapt these methods to the more time dominated problem of 'real-time' image matching.
9
Pettersson, Johan. "Real-time Object Recognition on a GPU." Thesis, Linköping University, Department of Electrical Engineering, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-10238.
Full textAbstract:
Shape-Based matching (SBM) is a known method for 2D object recognition that is rather robust against illumination variations, noise, clutter and partial occlusion.
The objects to be recognized can be translated, rotated and scaled.
The translation of an object is determined by evaluating a similarity measure for all possible positions (similar to cross correlation).
The similarity measure is based on dot products between normalized gradient directions in edges.
Rotation and scale is determined by evaluating all possible combinations, spanning a huge search space.
A resolution pyramid is used to form a heuristic for the search that then gains real-time performance.
For SBM, a model consisting of normalized edge gradient directions, are constructed for all possible combinations of rotation and scale.
We have avoided this by using (bilinear) interpolation in the search gradient map, which greatly reduces the amount of storage required.
SBM is highly parallelizable by nature and with our suggested improvements it becomes much suited for running on a GPU.
This have been implemented and tested, and the results clearly outperform those of our reference CPU implementation (with magnitudes of hundreds).
It is also very scalable and easily benefits from future devices without effort.
An extensive evaluation material and tools for evaluating object recognition algorithms have been developed and the implementation is evaluated and compared to two commercial 2D object recognition solutions.
The results show that the method is very powerful when dealing with the distortions listed above and competes well with its opponents.
10
Khan, Taha. "Real-Time Recognition System for Traffic Signs." Thesis, Högskolan Dalarna, Datateknik, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:du-3486.
Full textAbstract:
The aim of this thesis project is to develop the Traffic Sign Recognition algorithm for real time. Inreal time environment, vehicles move at high speed on roads. For the vehicle intelligent system itbecomes essential to detect, process and recognize the traffic sign which is coming in front ofvehicle with high relative velocity, at the right time, so that the driver would be able to pro-actsimultaneously on instructions given in the Traffic Sign. The system assists drivers about trafficsigns they did not recognize before passing them. With the Traffic Sign Recognition system, thevehicle becomes aware of the traffic environment and reacts according to the situation.The objective of the project is to develop a system which can recognize the traffic signs in real time.The three target parameters are the system’s response time in real-time video streaming, the trafficsign recognition speed in still images and the recognition accuracy. The system consists of threeprocesses; the traffic sign detection, the traffic sign recognition and the traffic sign tracking. Thedetection process uses physical properties of traffic signs based on a priori knowledge to detect roadsigns. It generates the road sign image as the input to the recognition process. The recognitionprocess is implemented using the Pattern Matching algorithm. The system was first tested onstationary images where it showed on average 97% accuracy with the average processing time of0.15 seconds for traffic sign recognition. This procedure was then applied to the real time videostreaming. Finally the tracking of traffic signs was developed using Blob tracking which showed theaverage recognition accuracy to 95% in real time and improved the system’s average response timeto 0.04 seconds. This project has been implemented in C-language using the Open Computer VisionLibrary.
11
DAMASCHIN, MIHAI. "A real-time hand pose recognition system." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-142438.
Full textAbstract:
This thesis work aimed to reimplement and improve an existing system for hand pose recognition from monocular video data. The resulting system is light, multi-platform and easily extensible because of its modularity. It relies on treating the problem of hand pose estimation as a nearest neighbour look-up in a database of synthetically generated hand images. Its main characteristics are the use of HOGs (Histogram of Oriented Gradients) as features and employing temporal consistency for greater reliability and robustness. The paper also makes a review of the current hand pose recognition research and gives arguments for our choices of implementation both in terms of design and actual technology used.Arbetet med den här uppsatsen ämnade till att bygga om och förbättra ett befintligt system för handposeestimering. Det framtagna systemet är lättviktigt och plattformsoberoende samt lätt att utöka tack vare dess modularitet. Problemet med att estimera handposer behandlas som ett närmaste-grannsökning i en databas av syntetiskt framtagna bilder på händer. Systemets huvudsakliga egenskaper är användandet av HOGs (Histogram of Oriented Gradient) samt temporal konsistens för ökad pålitlighet och stabilitet. Uppsatsen innehåller också en studie av nuvarande forskning inom området och presenterar argument för vår implementation avseende både vilken design och vilken teknik som använts.
12
Hunter, Julia. "Real-Time Recognition of Motion Behaviour Patterns." Thesis, University of Essex, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.522079.
Full text
13
Benkrid, A. "Real time TLM vocal tract modelling." Thesis, University of Nottingham, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.352958.
Full text
14
Zhu, Hong Min. "Real-time hand gesture recognition using motion tracking." Thesis, University of Macau, 2010. http://umaclib3.umac.mo/record=b2182870.
Full text
15
Irmak, Hasan. "Real Time Traffic Sign Recognition System On Fpga." Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12612360/index.pdf.
Full textAbstract:
In this thesis, a new algorithm is proposed for the recognition of triangular, circular and rectangular traffic signs and it is implemented on an FPGA platform. The system can recognize 32 different traffic signs with high recognition accuracy.
In the proposed method, first the image is segmented into red and blue regions, and according to the area of the each segment, the dominant color is decided. Then, Laplacian of Gaussian (LoG) based edge detection is applied to the segmented image which is followed by Hough Transform for shape extraction. Then, recognition based on Informative Pixel Percentage (IPP) matching is executed on the extracted shapes.
The Traffic Sign Recognition (TSR) system is implemented on Virtex 5 FX70T FPGA, which has an embedded PPC440 processor. Some modules of TSR algorithm are designed in the FPGA logic while remaining modules are designed in the PPC440 processor. Work division between FPGA and PPC440 is carried out considering their capabilities and shortcomings of FPGA and processor. Benefits of using an FPGA with an embedded processor are exploited to optimize the system.
16
Moy, Milyn C. (Milyn Cecilia) 1975. "Real-time hand gesture recognition in complex environments." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/50054.
Full textAbstract:
Thesis (S.B. and M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.Includes bibliographical references (leaves 65-68).
by Milyn C. Moy.
S.B.and M.Eng.
17
Wang, Xuelu. "Human Action Recognition from Gradient Boundary Histograms." Thesis, Université d'Ottawa / University of Ottawa, 2017. http://hdl.handle.net/10393/35931.
Full textAbstract:
This thesis presents a framework for automatic recognition of human actions in un- controlled, realistic video data with fixed cameras, such as surveillance videos. In this thesis, we divide human action recognition into three steps: description, representation, and classification of local spatio-temporal features. The bag-of-features model was used to build the classifier. Fisher Vectors were also studied. We focus on the potential of the methods, with the joint optimization of two constraints: the classification precision and its efficiency.
On the performance side, a new local descriptor, called Gradient Boundary Histograms (GBH), is adopted. It is built on simple spatio-temporal gradients, which can be computed quickly. We demonstrate that GBH can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large datasets. Our evaluation shows that compared to HOG descriptors, which are based solely on spatial gradient, GBH descriptor preserves the recognition precision even in difficult situation.
Since surveillance video captured with fixed cameras is the emphasis of our study, removing the background before action recognition is helpful for improving efficiency. We first preprocess the video data by applying HOG to detect humans. GBH descriptor is then used at reduced spatial resolutions, which yields both high efficiency and low memory usage; in addition, we apply PCA to reduce the feature dimensions, which results in fast matching and an accelerated classification process.
Experiments our methods achieved good performance in recognizing precision, while simultaneously highlighting effectiveness and efficiency.
18
Pan, Wenbo. "Real-time human face tracking." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0018/MQ55535.pdf.
Full text
19
Fountain, A. M. "Real-time image processing for industrial inspection." Thesis, University of Southampton, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.356523.
Full text
20
Gunaydin, Ali Gokay. "A Constraint Based Real-time License Plate Recognition System." Master's thesis, METU, 2007. http://etd.lib.metu.edu.tr/upload/12608195/index.pdf.
Full textAbstract:
License Plate Recognition (LPR) systems are frequently utilized in various access controls and security applications. In this thesis, an experimental constraint based real-time License Plate Recognition system is designed, and implemented in Java platform. Many of the available constraint based methods worked under strict restrictions such as plate color, fixed illumination and designated routes, whereas, only the license plate geometry and format constraints are used in this developed system. These constraints are built on top of the current Turkish license plate
regulations. The plate localization algorithm is based on vertical edge features where constraints are used to filter out non-text regions. Vertical and horizontal projections are used for character segmentation and Multi Layered Perceptron
(MLP) based Optical Character Recognition (OCR) module has been implemented for character identification. The extracted license plate characters are validated against possible license plate formats during the recognition process. The system is tested both with Turkish and foreign license plate images
including various plate orientation, image quality and size. An accuracy of 92% is achieved for license plate localization and %88 for character segmentation and recognition.
21
Ulrich, Markus. "Hierarchical real-time recognition of compound objects in images." München : Beck, 2003. http://www.loc.gov/catdir/toc/fy0607/2004457892.html.
Full text
22
Nordlöf, Jonas. "Comparative Analysis of Models for Real-Time Pattern Recognition." Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-96781.
Full textAbstract:
The different applications for optical character recognition in real-time applications will most likely increase in the future as innovations as autonomous vehicles or elder care robots become a reality. This analysis therefore aims to evaluate different "off-the-shelf" models that can be used in these applications. Four different classifiers have been combined with three different feature extraction procedures, giving a total of twelve models, have been used in the analysis. The evaluated classifiers are Artificial neural networks (ANN), -nearest neighbour ( NN), Support vector machines (SVM) and Random forest, while the raw image, wavelets and principle component analysis (PCA) were used as feature extraction procedure. The analysis used handwritten numerals from the MNIST-library as training and test data. Four different properties have been studied; these are dependencies of training data, accuracy of prediction, time for prediction and robustness against noise. The ANN classifier was the fastest, SVM had the highest accuracy, NN was the most robust against noise while the Random forest model had the highest accuracy when smaller training sets were used. Using principal-components as features to the classifiers increased the model robustness against noise.
23
Wright, P. T. "Algorithms for the recognition of handwriting in real-time." Thesis, Open University, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.234272.
Full text
24
Yin, Ying Ph D. Massachusetts Institute of Technology. "Real-time continuous gesture recognition for natural multimodal interaction." Thesis, Massachusetts Institute of Technology, 2014. http://hdl.handle.net/1721.1/91036.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
81
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 147-154).
I have developed a real-time continuous gesture recognition system capable of dealing with two important problems that have previously been neglected: (a) smoothly handling two different kinds of gestures: those characterized by distinct paths and those characterized by distinct hand poses; and (b) determining how and when the system should respond to gestures. The novel approaches in this thesis include: a probabilistic recognition framework based on a flattened hierarchical hidden Markov model (HHMM) that unifies the recognition of path and pose gestures; and a method of using information from the hidden states in the HMM to identify different gesture phases (the pre-stroke, the nucleus and the post-stroke phases), allowing the system to respond appropriately to both gestures that require a discrete response and those needing a continuous response. The system is extensible: new gestures can be added by recording 3-6 repetitions of the gesture; the system will train an HMM model for the gesture and integrate it into the existing HMM, in a process that takes only a few minutes. Our evaluation shows that even using only a small number of training examples (e.g. 6), the system can achieve an average F1 score of 0.805 for two forms of gestures. To evaluate the performance of my system I collected a new dataset (YANG dataset) that includes both path and pose gestures, offering a combination currently lacking in the community and providing the challenge of recognizing different types of gestures mixed together. I also developed a novel hybrid evaluation metric that is more relevant to real- time interaction with different gesture flows.
by Ying Yin.
Ph. D.
25
Ho, Purdy P. (Purdy Pinpin) 1977. "Rotation invariant real-time face detection and recognition system." Thesis, Massachusetts Institute of Technology, 2001. http://hdl.handle.net/1721.1/86709.
Full text
26
Moreira, Thierry Pinheiro 1990. "Real-time human action recognition based on motion shapes." [s.n.], 2014. http://repositorio.unicamp.br/jspui/handle/REPOSIP/275509.
Full textAbstract:
Orientador: Hélio PedriniDissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação
Made available in DSpace on 2018-08-25T12:27:06Z (GMT). No. of bitstreams: 1 Moreira_ThierryPinheiro_M.pdf: 1679150 bytes, checksum: 2bd22b1849bd7a34a85e6b5ba649bbf2 (MD5) Previous issue date: 2014
Resumo: Reconhecimento de ações humanas em vídeos é uma área de conhecimento em expansão. Há uma vasta gama de possíveis aplicações, incluindo interface de usuários, vigilância, casas inteligentes e monitoramento de saúde. A maioria delas requer respostas em tempo real. No entanto, há um equilíbrio entre tempo de processamento e eficácia do reconhecimento, sendo que eficácia compreende acurácia e robustez em múltiplas situações. Duas contribuições são apresentadas neste trabalho. A primeira é um método de obtenção de informação relevante de movimento em vídeos, mesmo usando uma subtração de fundo simples, por meio da união de uma janela deslizante de figuras. A segunda é um descritor simples e rápido, baseado em silhuetas ou, genericamente, em figuras de movimento, que alcança o estado da arte na acurácia em tempo real. Ele é construído a partir das posições relativas de pontos de interesse escolhidos como pontos extremos nas figuras de movimento. O método foi testado em três bases de dados públicas e os resultados experimentais são comparados com outros da literatura. Algumas bases possuem disponíveis silhuetas segmentadas manualmente, permitindo a análise de cada contribuição separadamente. Em todos os casos, as características foram extraídas em altas taxas de quadros por segundo
Abstract: Human action recognition in videos is an expanding area of knowledge. There is a wide range of possible applications, including user interface, surveillance, smart homes and health monitoring. Most of them require real time responses, however, there is a trade-off between processing time and effectiveness of the recognition, where effectiveness comprises accuracy and robustness in a number of situations. Two main contributions are presented in this work. The first one is a method for obtaining relevant motion information from videos, even by making use of poorly extracted foreground, by joining a temporal window of shapes. The second one is a simple and fast descriptor, based on silhouettes or, generically, on motion shapes, that achieves state-of-the-art accuracy in real time. It is built from the relative positions of interest points chosen as extreme points on the motion shapes. The method is tested on three public data sets and the experimental results are compared against others from the literature. Some data sets have manually segmented silhouettes available, allowing to analyze each contribution separately. In all cases, the features are extracted at high frame rates
Mestrado
Ciência da Computação
Mestre em Ciência da Computação
27
Qi, Ying. "Novel Optical Technique for Real-Time Pattern/Image Recognition." Thesis, Virginia Tech, 2002. http://hdl.handle.net/10919/36446.
Full textAbstract:
We propose a novel real-time joint-Transform correlation (JTC) technique for
optical pattern recognition.
To replace the film recording aspect of performing optical correlation,
conventional real-time joint-Transform correlation (JTC) optical systems make use of a
spatial light modulator (SLM) located in the Fourier plane to record the interference
intensity to achieve real-time processing. However, the use of a SLM in the Fourier
plane, is a major drawback in these systems since SLMs are limited in resolution, phase
uniformity and contrast ratio. Thus, they are not desirable for robust applications. In this
thesis, we developed a hybrid (optical/electronic) processing technique to achieve real-time
joint-Transform correlation (JTC). The technique employs acousto-optic
heterodyning scanning. The proposed real-time JTC system does not require a SLM in
the Fourier plane as in conventional real-time JTC systems. This departure from the
conventional scheme is extremely important, as the proposed approach does not depend
on SLM issues. We have developed the theory of the technique and substantiated it with
optical experimental as well as computer simulation results.Master of Science
28
Pandya, Jatan K. "Real Time Badge Detection and Recognition for Bicycle Racing." The Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1306867373.
Full text
29
Ulrich, Markus. "Hierarachical real-time recognition of compound objects in images /." Munchen : Verlag der Bayerischen Akademie der Wissenschaften in Kommission beim Verlags C.H. Beck, 2003. http://www.loc.gov/catdir/toc/fy0607/2004457892.html.
Full text
30
Wang, Zhao Qi. "Real-time optical intensity correlation using photorefractive BSO." Thesis, Abertay University, 1995. https://rke.abertay.ac.uk/en/studentTheses/f1330975-bc23-4532-ac7b-8aeb9cad8c81.
Full textAbstract:
Real-time optical intensity correlation using a photorefractive BSO crystal and a liquid crystal television is implemented. The underlying physics basis is considered, some specific techniques to improve the operation are proposed, and several optical pattern recognition tasks are achieved. Photorefractive BSO is used as the holographic recording medium in the real-time intensity correlator. To improve the dynamic holographic recording, a moving grating technique is adopted. The nonlinear effects of moving gratings at large fringe modulation are experimentally investigated, and are compared with numerical predictions. Optical bias is adopted to overcome the difficulty of a large drop in the optimum fringe velocity with moving gratings. The effects of optical bias on the optimum fringe velocity and on the diffraction efficiency are studied. To overcome the inherent drawback of low discrimination of intensity correlation in optical pattern recognition, real-time edge-enhanced intensity correlation is achieved by means of nonlinear holographic recording in BSO. Real-time colour object recognition is achieved by using a commercially available and inexpensive colour liquid crystal television in the intensity correlator. Multi-class object recognition is achieved with a synthetic discriminant function filter displayed by the Epson liquid crystal display in the real-time intensity correlator. The phase and intensity modulation properties of the Epson liquid crystal display are studied. A further research topic which uses the Epson liquid crystal display to realize a newly designed spatial filter, the quantized amplitude-compensated matched filter, is proposed. The performance merits of the filter are investigated by means of computer simulations.
31
Dahhan, A. K. "Real-time microwave holography using glow discharge detectors." Thesis, Cardiff University, 1986. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.356739.
Full text
32
Jain, Shikha. "Real Time Face Recognition." Thesis, 2017. http://ethesis.nitrkl.ac.in/8863/1/2017_MT_SJain.pdf.
Full textAbstract:
Texture is the surface property that is used to identify and recognize objects. Texture identification and recognition is extensively opted in many real time applications like biomedical and aerial image analysis, airport security, person identity verification and so on. Local binary pattern (LBP) texture method is used for feature extraction method for face recognition. The basic LBP is elongate to expedite the analysis of texture using multiple scales by combining neighborhoods with different sizes. Many models proposed for texture analysis which are derivatives of LBP. The derivatives of LBPs are centre symmetric local binary pattern, advanced local binary pattern(ALBP), local texture pattern (LTP),local binary pattern variance(LBPV), dominant local binary pattern. Local binary pattern and its derivatives performance has been compared. Local binary pattern ,eigenface,and fisher face results also compared. The above three methods are implemented in hardware (Raspberry pi 3 model B). The real-time face recognition challenges such as illumination variation and facial expression variations are ranked by different LBP-based models. The above experiments were conducted on the ORL, YALE, PIE database.
33
Hsiao, Yu-Dian, and 蕭育典. "Real Time Face Recognition Systems." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/enfc9v.
Full textAbstract:
碩士龍華科技大學
電機工程系碩士班
105
In this thesis, it is to face recongnition systems used in the real time. Using webcam and Python to achieve. Python is an open source and cross-platform programming language, no matter which platform, can be painless transfer. Using Python to combine opencv can complete image processing, whether it is reading write and zoom in and out. It is very convenient to use Python to study machine-related methods. And the kits are open source software that will not be limited by copyright issues. According to the classification of supervised learning, the use of Python to write three main code, the machine learning is divided into three parts: prior data collection, training, practical application. Respectively, to complete the test, to be tested to get the conclusions of this study. The future hope to go to unsupervised learning to explore. And this study can be applied in the access control system or employee visitor system, you can have good results.
34
xhao, zetta, and 邵文斌. "Real-time Video Face Recognition." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/29387509264615627361.
Full textAbstract:
碩士元智大學
電機工程學系
94
Principal component analysis (PCA) and Linear Discriminate Analysis (LDA) are two powerful methods for face recognition. In this paper, a "modified Linear Discarnate Analysis" is proposed for recognizing faces directly from videos. The modified LDA method can gain better accuracy on face recognition than the normal LDA. The modified LDA tries to include more sub-classes in a category for improving the separation ability of the original LDA to recognize different faces in real time. Experiment results prove that the proposed method is a robust, accurate, and powerful tool for face recognition
35
Chang, Chin-Han, and 張景涵. "Real-time Finger Pointing Recognition System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/52030843017723852498.
Full textAbstract:
碩士國立清華大學
電機工程學系
93
In this thesis, we develop a real time finger pointing system. The novelty of our system is that we can develop a real-time single plane pointing system and stereo vision pointing system. Our system consists of (1) hand tracking (2) hand shape extraction (3) finger orientation calculation and (4) finger line finding. In the experiments, we show that our system will analyze each frame of video input within about 1/15 second and achieve a near-real-time system. The pointing accuracy of our system is measured by the success rate of 100 pointing of which the results are acceptable. In the experiments, we show that the success rate of our system is above 80%.
36
Liou, Cherng Jye, and 劉誠傑. "A Real-Time Face Recognition System." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/34715388413058209506.
Full textAbstract:
碩士國立臺灣大學
電機工程學系
85
Real-time face recognition from uncontrolled video sequences is adifficult problem. The difficulties come from large variation inface size, position, pose, expression, lighting condition andbackground. Also, the real-time constraint makes this problem moretough due to limited computation resources. In this thesis, we propose a fully automatic procedure that candetect faces, estimate the size of a face, segment the facefrom the scene by utilizing the knowledge about human motion.The searching operation for detecting faces is essentiallyone-dimension-based and thus is very efficient. The detected faceis tracked using the temporal consensus of head motion.During tracking the face, the system extracts features frommultiple views of the face regions by KLT. The extractedfeatures are clustered using a locally unsupervised and globallysupervised learning algorithm. We demonstrate that this systemcan recognize faces in real time with significant variation in headsize, facial expression, lighting condition, and background.Also, by introducing a rejection threshold for badly extracted features,the system can recognize all (100%) of the 88 persons in our database
37
Chiu, Chieh-Chuan, and 邱介川. "Real-time speech recognition Multimedia system." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/74367285495419381729.
Full textAbstract:
碩士國立中央大學
電機工程研究所
99
This thesis develops a real-time voice recognition multimedia system to provide simple but useful services. System detects whether commands were made or not by using automatic recording technology, then determining what kind of service is with keyword spotting technology. This technology implements recognition with sub-syllable models, which don’t need to repeat training, to improve the performance efficiency and portability. System uses a hierarchical structure for keyword spotting with TTS (Text To Speech) to let user familiar with system. The system achieved by the Borland C + + 6.0 Windows based interface to realize real-time recognition.
38
Tsao, Jen-Hung, and 曹仁鴻. "Real-time Traffic Sign Recognition Technology." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/26390495493952128860.
Full textAbstract:
碩士樹德科技大學
資訊工程系碩士班
101
This thesis presents a simple and fast method for recognition of traffic signs by shape features. Firstly, we transforma series of images from the RGB space into HSV space to locate the regions of the traffic signs with red color feature, as well as we erode remove redundant noisesby median filter. Secondly, we employ the ratio of the length and widthto remove traffic signs with regions with improper ratio.And then we use shape templates to identify the regions of traffic signsas candidate regions.For recognition of traffic signs, we extract the feature values from the contours ofstandard traffic signs contour in 36 directions and create a database of feature values.Finally, we calculate the feature values of the candidate regionsobtained real-time successive images for recognizing the content of traffic signs.In this thesis,our proposed method is fast and simple. Our configurationcould be utilized in real-time system for advanced safety vehicles (ASV) for improvingdriving safety. Keyword：recognition of traffic signs, shape features, advanced safety vehicles,driving safety.
39
Chiang, Bo-Cheng, and 江柏城. "Real Time Facial Expression Recognition System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/at3ezb.
Full textAbstract:
碩士國立臺灣科技大學
電機工程系
105
With new technological advances, interaction between human and machine has been varied. In this thesis, an interaction-oriented real-time facial expression recognition system is applied for the usage of interaction. Through image processing, face detection and expression recognition system is used to detect human face in the image and recognize the expression on the face. Further, we analyze the recognition results and output the corresponding speech to certain expression in order to interaction with the user. In this thesis, we proposed a real-time facial expression recognition system based on PC. The research has developed the expression recognition on the basis of face detection and finally can interact with user. The system consists of three parts: (1) Face candidate extraction, (2) Face verification & expression recognition, and (3) Machine reaction. In the first part, we extract the face candidate in the image using pre-processing method. The face candidate image is then classified in the second part by extracting Local Binary Pattern feature. The classification in the second part is done using two stages: (1) first, the candidate image is classified into face image or non-face image, (2) the face image is then classified into six type of expression. In the last part, the output speech is played according to the classified results produced in a time period. The system is implemented using C language and based on PC. In the experiments, we use a facial expression database to perform cross validation and recognition rate is 84.78%. Further, we use webcam as the input serial image and compare the recognition rate and run time differences between the non-deleting-blocks case and deleting-blocks case, which contain less expression information.
40
Chi, Heng-Yu, and 祁恒昱. "Real-time Mobile Visual Object Recognition in Real Scene." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/75246981222421018759.
Full textAbstract:
博士國立臺灣大學
電機工程學研究所
104
The popularization of mobile devices and the advancement of wearable devices make the augmented reality (AR) scenarios become feasible. However, the success of AR applications relies on a key technique, real-time visual object recognition in real scene. Therefore, in our dissertation, we developed a framework called SpAtialized Grid based structured learning for Real-scene Object recognition (SAGRO). The proposed SAGRO is not only able to locate the visual objects precisely but also achieves real-time performances. Based on the techniques of mobile visual object recognition, we presented two applications to improve user experiences in their daily life. First, we proposed a commercial item retrieval and recommendation system, UbiShop, on mobile phones, whereby users can timely get the related information of interesting commercial items by taking pictures of them. Users can also obtain recommendations on visually similar commercial items to help their buying selections. Moreover, observing the fact that more than 63 percent of the drivers in the United States in 2013 have been led astray because of receiving confusing GPS driving instructions, we presented a more intuitive driving instruction, iNavi, by detecting interesting regions from the sight of vehicle drivers to help them quickly and correctly recognize the turning points.
41
Wu, Chih-Jen, and 吳至仁. "Real-time Obstacle Detection and Sign Recognition." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/mtv62d.
Full textAbstract:
碩士國立成功大學
工程科學系碩博士班
90
Abstract An Autonomous Mobile Robot (AMR) offers various applications such as commodities moving or household cleaning could be a good personal assistant in our daily life. To achieve the purpose, a navigation system must be designed for leading the AMR moving in an unknown environment. In this thesis, computer vision techniques were employed for designing the AMR navigation system via computer vision techniques .Firstly, a stereo vision system has been set-up for detecting and locating the obstacles accurately in real-time. It used the concept of planar parallax of two CCD cameras. The planar parallax characteristic can quickly be used to detect the obstacles in the image plane. The method proposed by Shi and Tomasi has been used to extract the feature points and the distance between AMR and obstacles can be measured. With these messages, a map with obstacles in front of the AMR can be created for referenced. Secondly, an algorithm based on the Hausdorff distance was proposed for detecting the signs marked in the environment for some indicating purpose. By applying the previous result, the searching time for matching a special sign can be reduced largely.
42
HUNG-TSUNG, CHEN, and 陳宏宗. "Real Time Motorcycle Recognition and Tracking System." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/64472593123185623435.
Full textAbstract:
碩士國防大學中正理工學院
電子工程研究所
94
The development of the intelligent transportation system becomes a benchmark with developed country. The study of the intelligent system is becoming more and more important. Because the automobile industry is expanding, the traffic accident and traffic jam are frequently occurred. Therefore, how to solve the traffic issues becomes the important topic for the intelligent transportation system. In Taiwan, because the populations are concentrated in the big cities, the traffic jam is frequently occurred. The motorcycle becomes the most convenient transportation for the Taiwanese. However, the driver of a motorcycle is always injured when the traffic accident occurred. The study of this thesis proposes a motorcycle detection and recognition system. The system can extract the moving objects from the image sequence, and recognize the motorcycles from the moving objects. Experiments obtained by using complex road scenes are reported, which demonstrate the validity of the method in terms of robustness, accuracy, and time responses.
43
"A real-time virtual-hand recognition system." 1999. http://library.cuhk.edu.hk/record=b5889833.
Full textAbstract:
by Tsang Kwok Hang Elton.Thesis submitted in: December 1998.
Thesis (M.Phil.)--Chinese University of Hong Kong, 1999.
Includes bibliographical references (leaves 78-83).
Abstract also in Chinese.
Chapter 1 --- Introduction --- p.1
Chapter 2 --- Virtual-hand Recognition --- p.5
Chapter 2.1 --- Hand model --- p.6
Chapter 2.1.1 --- Hand structure --- p.6
Chapter 2.1.2 --- Motions of the hand joints --- p.8
Chapter 2.2 --- Hand-tracking technologies --- p.9
Chapter 2.2.1 --- Glove-based tracking --- p.10
Chapter 2.2.2 --- Image-based tracking --- p.12
Chapter 2.3 --- Problems in virtual-hand recognition --- p.13
Chapter 2.3.1 --- Hand complexity --- p.13
Chapter 2.3.2 --- Human variations --- p.13
Chapter 2.3.3 --- Immature hand-tracking technologies --- p.14
Chapter 2.3.4 --- Time-varying signal --- p.14
Chapter 2.3.5 --- Efficiency --- p.14
Chapter 3 --- Previous Work --- p.16
Chapter 3.1 --- Posture and gesture recognition algorithms --- p.16
Chapter 3.1.1 --- Template Matching --- p.17
Chapter 3.1.2 --- Neural networks --- p.18
Chapter 3.1.3 --- Statistical classification --- p.20
Chapter 3.1.4 --- Discontinuity matching --- p.21
Chapter 3.1.5 --- Model-based analysis --- p.23
Chapter 3.1.6 --- Hidden Markov Models --- p.23
Chapter 3.2 --- Hand-input systems --- p.24
Chapter 3.2.1 --- Gesture languages --- p.25
Chapter 3.2.2 --- 3D modeling --- p.25
Chapter 3.2.3 --- Medical visualization --- p.26
Chapter 4 --- Posture Recognition --- p.28
Chapter 4.1 --- Fuzzy concepts --- p.28
Chapter 4.1.1 --- Degree of membership --- p.29
Chapter 4.1.2 --- Certainty factor --- p.30
Chapter 4.1.3 --- Evidence combination --- p.30
Chapter 4.2 --- Fuzzy posture recognition system --- p.31
Chapter 4.2.1 --- Objectives --- p.32
Chapter 4.2.2 --- System overview --- p.32
Chapter 4.2.3 --- Input parameters --- p.33
Chapter 4.2.4 --- Posture database --- p.36
Chapter 4.2.5 --- Classifier --- p.37
Chapter 4.2.6 --- Identifier --- p.40
Chapter 5 --- Performance Evaluation --- p.42
Chapter 5.1 --- Experiments --- p.42
Chapter 5.1.1 --- Accuracy analysis --- p.43
Chapter 5.1.2 --- Efficiency analysis --- p.46
Chapter 5.2 --- Discussion --- p.48
Chapter 5.2.1 --- Strengths and weaknesses --- p.48
Chapter 5.2.2 --- Summary --- p.50
Chapter 6 --- Posture Database Editor --- p.51
Chapter 6.1 --- System architecture --- p.51
Chapter 6.1.1 --- Hardware configuration --- p.51
Chapter 6.1.2 --- Software tools --- p.53
Chapter 6.2 --- User interface --- p.54
Chapter 6.2.1 --- Menu bar --- p.55
Chapter 6.2.2 --- Working frame and data frame --- p.56
Chapter 6.2.3 --- Control panel --- p.56
Chapter 7 --- An Application: 3D Virtual World Modeler --- p.59
Chapter 7.1 --- System Design --- p.60
Chapter 7.2 --- Common operations --- p.62
Chapter 7.3 --- Virtual VRML Worlds --- p.65
Chapter 8 --- Conclusion --- p.70
Chapter 8.1 --- Summaries on previous work --- p.70
Chapter 8.2 --- Contributions --- p.73
Chapter 9 --- Future Work --- p.75
Bibliography --- p.78
44
Chien-MingLi and 李健銘. "Real-Time Recognition of Hand Sign Language." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/39767876671735566782.
Full textAbstract:
碩士國立成功大學
工程科學系專班
98
The sign language is composed of hand gesture，position movement and direction. This study uses image processing to extract human being palm ,and uses Fisher Linear Discriminant method to recognize hand gesture, and saves a new state when hand gesture change. Real-time recognition of the sign language is performed using the changing hand state. Using Kalman filter to track the evocations of both hands, the system can distinguish between left and right hands, when both hands are interlaced. The system also uses KNN search method to determine the best gesture, avoiding A gesture sample which is similar to B gesture sample, causing incorrect gesture results. The system can recognize hands gesture eight times per second, the recognition rate is 96% with angle changes from 15° ~ -15°. So the system can continuously recognize the sign language. But the system is timely, so not considering the complexity of moving gesture.
45
Lin, Zheng-Xian, and 林政憲. "Real Time 3D Gesture Recognition using Cloudlet." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/87376591085378434272.
Full textAbstract:
碩士國立高雄應用科技大學
資訊工程系
104
A mobile-cloudlet architecture provides a practical platform for performing 3D gesture recognition on a mobile device. However, using mobile-cloudlet architecture to perform real-time 3D gesture recognition presents several challenges including resource limitations and long network delays. In this dissertation, we propose one approach for accelerating the execution of the 3D gesture recognition application by utilizing hand feature reduction. We study in detail one of these approaches, using the feature selection to perform pre-processing, and reduce the network transmission delay. Our experimental results show up to a 3x improvement in response time when the feature selection is used.
46
Chien, Hsiao-Yen, and 簡孝諺. "EEG-based Real-time Emotion Recognition System." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/263n8u.
Full textAbstract:
碩士國立臺北科技大學
資訊與財金管理系碩士班
105
Recently, many companies have produced smaller, cheaper and easy to use wearable brain-machine devices. This attracts that many scholars use the brain-machine as a research facility. In addition, smart phones are now popular, we can use smart devices to process data, or pass the data to back-end for analysis. This study proposes a set of algorithms to improve the problem of high similarity in many brainwave applications. We refer to existing applications and design new algorithms. Finally, the accuracy of the algorithms are verified experimentally. And real-time emotional identification prototype system are implemented. Users will be able to see their own emotional state and share it with friends and family via this system.
47
Lin, Shih-Chieh, and 林士傑. "Real-time Traffic Sign Detection and Recognition." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/b3qszz.
Full textAbstract:
碩士國立交通大學
電子研究所
106
This thesis proposes a real-time traffic sign detection and recognition system, which can achieve both real-time processing on a low-end industrial computer and decent performance under various environments. Many of the existing researches focus on achieving the best possible accuracy with no restriction on computation cost. We combine color and shape segmentation techniques to design our traffic sign detection scheme. We hope to take the respective advantages of color and shape segmentation methods. We use the faster color segmentation methods in the first part of our proposed system. In our system, the objective of color segmentation part is to greatly reduce the irrelevant data that will be sent to the shape segmentation part. The objective of shape segmentation is to identify the locations of traffic signs using the sign shape information. After placing bounding boxes on the traffic sign candidate locations, we extract the robust HOG features from the candidates and send the features to a pre-trained SVM classifier for traffic sign recognition. To ensure that our proposed method is applicable for real-world situations, we performed experiments on three popular datasets (GTSB, LTS and IEEE VIP cup) and we used a low-end industrial computer as the computational platform. Our system is able to achieve first-tier performance at a desirable high frame rate.
48
Chang, Chih-Chun, and 張智鈞. "Real-Time Music Score Recognition and Playing." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/frtp3v.
Full textAbstract:
碩士國立臺北科技大學
電機工程系研究所
97
This thesis presented a method for music score recognition. When a commercial webcam captures the music notes in a complex environment, there are two ways to play the recognized music score. One is played by the percussion robot. The other way is transformed the recognized music score to electronic music MIDI code and played by a music software. This thesis has two steps to recognize music score, the first one is the image processing techniques which detects music score in the complex environment and recognizes the music notes. The other is adding music theory to check the recognized music score and modify it as correct as possible. This research proposes the method of music score recognition fast and correctly. In the experiment, we have recognized 30 songs from printed piano scores. Moreover, the system can recognize the image of music score from the picture taken from the camera of cell phone. Based on the camera resolution and the complexity of music, the average accuracy is over 95% on an average.
49
GUPTA, MADHUR. "REAL TIME RECOGNITION OF COLORED AIR WRITTEN CHARACTERS." Thesis, 2018. http://dspace.dtu.ac.in:8080/jspui/handle/repository/16264.
Full textAbstract:
Character Recognition has been comprehensively studied in the last half century
and has advanced to a level, adequate to produce technology driven applications.
Now, the advancement in computational power enables the implementation iof the
present Character Recognition methodologies and also creates an increasing
demand ion many emerging application domains, which require more advanced
methodologies. Researchers have worked ion many methodologies for Recognizing
Text or Character from a handwritten or already computer printed piece of paper
to store the data obtained in digital form.
In this project our main aim was on recognizing characters in real time
from the user’s gesture when he is in his writing phase. For implementing the
aforesaid work the user’s gesture needed to be traced on a real time basis
for getting a base to recognize the letter which he is writing. The writing part is
realized on a paperless scheme in which the user only need to air write
the characters which he wants to write by just affixing any colored piece of
object to his finger. Tracing part of letters has been deployed on the
colored object which is being attached to the user’s finger. The gestures of
hand (object attached to it) in real time is captured using camera and is
simultaneously being fed to Matlab for further processing.
Our preliminary aim of detecting the colored object and then tracking is
performed using the color identifying algorithm, which uses background subtraction
strategy, noise filtering, binary image conversion and blob extraction to
iv
recognize a specific color in the video feed. Then the corresponding pixel on
the GUI (Graphic user interface) is being draw to track where all the color
has been. When a complete character is drawn, a signal is send to Matlab by the user
for the next part of recognizing that character. Further work of recognizing
the letters is carried out by using the traced part of the object. This traced
path on the GUI is sent in the form of an image for further processing to
extract the letters written on it. The part of extracting characters from this
image is performed using template matching technique. This technique uses a
database of characters and numbers, which needs to be stored
in their binary from in an M x N cell matrix to be used as templates for
comparison purpose. Further the traced image is gone through various
preprocessing steps such as Grayscale conversion, Filtering and Feature Extraction
which further includes Row detection, Character boundary detection, segmentation
and binary conversion. Finally the binary converted character is resized to M x N
cell and then correlation method is used for matching this with saved templates.
Finally the characters extracted from air written gestures is saved to a text file
and also gets displayed simultaneously.
This work might have applications in various domains such as interactive
learning sessions in classrooms which no longer will require tutor to be cling
to board; effortlessly making notes or writing any information and then saving
it only by air writing the gestures in one’s own way without even the need
of touching the keyboard, Such applications are beneficial for disabled people;
transmitting the relevant information from a distance in some form of encoded
character or symbols in utter need of secrecy for military purpose and many more.
50
Chang, Hsin-Chih, and 張馨之. "Real-time Hand Gesture Recognition for Visually Impaired." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/36720726961901372377.
Full textAbstract:
碩士國立中興大學
通訊工程研究所
101
Hand gesture in Human-Computer-Interaction is the most natural and easiest way to communicate. Furthermore, that is the easy way to achieve gesture control due to technology advancements. Thus, that’s the reason why hand gesture is a hot research topic recently. Moreover, Kinect for Xbox 360 of 3D depth sensing is usually being used to get hand gesture image. Because of cheap and depth image in high-quality, Kinect makes non-contact control easier to execute and body control more common in the games. In this paper, we propose hand gesture recognition method through combining hand gesture and Braille by using thumb, index finger and middle finger of both of hand to replace six dots of Braille. Braille let visually impaired people don’t need to re-learn and quickly adapt to operation. First of all, the procedure of method is convert depth image obtained from Kinect sensor into binary image by setting threshold, even though background is complex. The advantage of binary image is that the subsequent image processing becomes simple and rapid. Secondly, hand shape segmented by cutting hand’s wrist in the image after morphological image processing. Finally, executing hand gesture recognition with voice playback to provide authentication when fingertip detection finished.