To see the other types of publications on this topic, follow the link: FAME ANALYSIS.
Dissertations / Theses on the topic 'FAME ANALYSIS'
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 'FAME ANALYSIS.'
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
Sekora, Nicholas Scott Lawrence Katheryn Kay Scott. "Identification of plant-parasitic nematodes using FAME analysis." Auburn, Ala, 2009. http://hdl.handle.net/10415/1806.
Full text
2
Fransson, Rasmus. "Determination of FAME in Gasoline : A Fuel Quality Analysis." Thesis, Högskolan i Borås, Akademin för textil, teknik och ekonomi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-21212.
Full textAbstract:
Gasoline is produced by distilling petroleum oil. This is done at a refinery, where a lot of other products are produced as well. With increasing interest in bio-fuels the fuel companies started to produce substances such as biodiesel as well as the petroleum-based fuels. These products are then transported to where they are going to be used or sold, there included both gasoline, which is a petroleum-based fuel, and biodiesel (FAME), which in Sweden is based on rapeseed oil. If the vessel for transporting gasoline, or pipeline/connections filling and emptying the tanks, has previously been used for biodiesel, there is a risk of contaminating the gasoline with biodiesel. This contamination can have a lot of different effects such as either clogging filters or injectors in both gasoline- and ethanol-based engines, or even change the properties and therefore quality of the fuel. To ensure that the results from tests and research involving gasoline can be used and compared with each other, the quality of the fuel must have the same properties throughout all tests. This is controlled by taking samples on a regular basis and analyzing the quality and level of impurities in the fuel used in that specific test. Screening for FAME is therefore necessary which is where this thesis becomes relevant. This thesis was carried out with the purpose to develop a new or verify an already developed method to quantify FAME in gasoline. To determine the FAME content, a standard gas chromatography method, IP 585, was used. It was changed to fit in this application, since it was originally made to determine FAME content in diesel, not gasoline. It was concluded that it was possible to determine the FAME content in gasoline when IP 585 was used as is. There were some possible alternatives to IP 585 and they will be discussed in the literature study.Bensin framställs genom destillation av råolja. Detta görs på ett raffinaderi där ett flertal andra produkter också utvinns. På senare tid har ögonen öppnats för "biobränslen", bland annat biodiesel. Det händer därför att detta också framställs på samma plats som bensinen. Dessa produkter säljs sedan och brukar fraktas i stora tankar till företagen som köpt dem. Ifall tankarna vid transport eller rören bränslet går igenom till tankarna först använts till biodiesel och sedan används till bensin finns det stor risk att en del biodiesel hamnar i bensinen. Detta kan leda till en rad olika problem. Ett exempel är att biodieseln kan sätta igen och förstöra injektorer i bensin- och etanolmotorer. Det kan även påverka testresultat i olika testriggar, vilket är ett av fallen på Volvo. Ifall bränslet inte bibehåller samma kvalitet för varje test det används i leder det till svårigheter vid jämförelser och resultatens riktighet. Det blir därför nödvändigt att kontrollera bensinens innehåll, där inräknat screening av FAME. Detta arbete utfördes med syftet att utveckla en ny eller verifiera en redan beprövad metod för att bestämma koncentrationen FAME i bensin. För att mäta koncentrationen FAME användes en standardmetod till GC-MS, IP 585. Den modifierades något för att passa in i denna applikation då den från början var gjord för kvantifiering i diesel och inte bensin. Slutsatsen drogs att det är möjligt att mäta koncentrationen FAME i bensin med IP 585 använd som den är. Det fanns möjliga alternativ till metoden, dessa bemöts i litteraturstudien.
3
Ilya, Musabirov. "Deconstructing Fame : An Analysis of eSports Brand Value. The Case of Dota 2." Thesis, Uppsala universitet, Medier och kommunikation, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-296411.
Full text
4
Mandavha, Uyuenendiwannyi. "Analysis of carbonaceous solid deposits from thermal stressing of FAMEs and FAME/diesel blends at different temperatures in a continuous flow reactor." Master's thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/20091.
Full textAbstract:
Fuel deposits are carbon-rich high molecular weight species that are formed from the degradation of fuel. Diesel deposits may form on vital parts of a vehicle's engine or fuel system such as the fuel injectors. Once these deposits have formed, they can block the spray holes of the injector and may also cause moving parts within the injector to stick. Diesel deposits can cause engine failure, engine malfunction and affect engine performance. This study aims to investigate early stage deposits, formed in laboratory reactors, in particular a flow reactor. This was performed in order to gain insight into the processes by which these deposits form and what factors influence their formation. A flow reactor and closed sand bath reactor were employed to produce carbonaceous deposits, with the aim being that these might be similar to those formed in diesel injectors. The solid deposits were analysed using a Temperature Programmed Oxidation (TPO), Transmission Electron Microscopy (TEM) and Scanning Electron Microscopy (SEM). Soluble deposit precursors from the stressed fuels were assessed using ultraviolet visible spectroscopy (UV-Vis) and electrospray ionisation-mass spectroscopy (ESI-MS) in order to provide further insight into the chemical processes preceding deposit formation. The test fuels stressed in this study were an EN 590 reference diesel and two fatty acid methyl esters (FAMES), viz. rapeseed methyl ester (RME100) and soya methyl ester (SME100). Binary blends of 80 % EN 590 diesel and 20 %RME (RME20), 80 % EN 590 diesel and 20 % SME(SME20), 50 % EN 590 diesel and 50 % SME (SME50) and 93 % EN 590 diesel and 7 % SME (SME7) (v/v) were also investigated. Aerated fuels were thermally stressed at 300°C and 400°C for 5h in the presence of oxygen in a continuous flow reactor. This study represents the first application of the flow reactor methodology to systems that contain fatty acids methyl esters (FAMEs).
5
Westberg, Emilie. "Qualitative and Quantitative Analysis of Biodiesel Deposits Formed on a Hot Metal Surface." Thesis, Linköpings universitet, Institutionen för fysik, kemi och biologi, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-95617.
Full textAbstract:
This thesis aims to investigate the formation of deposits from thermally degraded biodiesel on a hot metal surface under the influence of sodium or copper contaminations. Biodiesel or Fatty Acid Methyl Esters (FAMEs) is a widely utilized biofuel with the potential to replace fossil fuels, however, issues regarding the thermal and oxidative stability prevent the progress of biodiesel for utilization as vehicle fuel. The thermal degradation of biodiesel causes formation of deposits often occurring in the fuel injectors, which could result in reduced engine efficiency, increased emissions and engine wear. However, still have no standard method for evaluation of a fuels’ tendency to form deposits been developed. In this study biodiesel deposits have been formed on aluminum test tubes utilizing a Hot Liquid Process Simulator (HLPS), an instrument based on the principle of the Jet Fuel Thermal Oxidation Tester (JFTOT). Quantitative and qualitative analyses have been made utilizing an array of techniques including Scanning Electron Microscopy (SEM), Gas Chromatography Mass Spectrometry (GCMS) and Attenuated Total Reflectance Fourier Transform Infrared Spectrometry (ATR-FTIR). A multi-factorial trial investigating the effects of sodium hydroxide and copper contaminations at trace levels and the impact of a paraffin inhibitor copolymer additive on three different FAME products, two derived from rapeseed oil and one from waste cooking oil as well as a biodiesel blend with mineral diesel, was conducted.The results exhibited that FAMEs are the major precursor to deposit formation in diesel fuel. The SEM analyses exploited the nature of FAME deposits forming porous structures on hot metal surfaces. Sodium hydroxide proved to participate in the deposit formation by forming carboxylic salts. However, the copper contamination exhibited no enhancing effect on the deposits, possibly due to interference of the blank oil in which copper was received. The paraffin inhibitor functioning as a crystal modifier had significant reducing effect on the deposit formation for all biodiesel samples except for the FAME product derived from waste cooking oil. Further studies are needed in order to investigate the influence of glycerin and water residues to the biodiesel deposit formation. Mechanisms involving oxidative or thermal peroxide formation, polymerization and disintegration have been suggested as degradation pathways for biodiesel. The involvement of oxidation intermediates, peroxides, was confirmed by the experiments performed in this thesis. However, the mechanisms of biodiesel deposit formation are complex and hard to study as the deposits are seemingly insoluble. Nevertheless, ATR-FTIR in combination with JFTOT-processing has potential as standard method for evaluation of deposit forming tendencies of biodiesel.
6
Pisac, Claudia A. "An experimental study of combustion characteristics of fatty acid methyl ester biodiesel." Thesis, University of Hertfordshire, 2014. http://hdl.handle.net/2299/14641.
Full textAbstract:
The thesis presents an experimental investigation of combustion performance and emissions of waste cooking oil (WCO) based biodiesel. To evaluate the comparative performance of biodiesel and diesel, combustions tests were conducted using Continuous Combustion rig (CCR) and Land Rover VM diesel engine. Firstly, physical properties of WCO biodiesel and diesel samples were measured in the laboratory. Elemental analysis of WCO biodiesel showed that there are differences between the functional groups in diesel and biodiesel which lead to major differences in the combustion characteristics of the two fuel types. It was found that biodiesel had 10% lower carbon content, almost no sulphur content for biodiesel and up to 12% more oxygen content compared with diesel. This explains the lower caloric value for WCO biodiesel (up to l8 %) compared with diesel. However, higher oxygen content and double bounds in WCO biodiesel increase its susceptibility to oxidation. The CCR test results showed an increase in combustion gas temperature with the increases in biodiesel blend ratio in diesel. This was due to a faster reaction rate for biodiesel than that of diesel leading to a faster brakeage of the hydrocarbon chain to release more heat. The engine tests were performed to measure the torque and emissions for different engine speeds and loads. In general a decrease in engine torque with up to 9% for biodiesel was observed, which was due to the lower calorific value of biodiesel compared with that of diesel. The brake specific fuel consumption (BSFC) increased as the biodiesel blend ratio in diesel increases due a greater mass of fuel being injected at a given injection pressure, compared with diesel. Using WCO blends ratio up to 75% in diesel showed a reduction in exhaust emission compared with diesel, however, at the cost of increased fuel consumption. A common conclusion can be drawn in favour of the WCO biodiesel as being a greener alternative to petro-diesel when used in blend with diesel. However, due to large variations in the biomass used for biodiesel production could lead to variations in physical and chemical properties between biodiesel produced from different biomass. Therefore more stringent standards need to be imposed for biodiesel quality in order to diminish the effect of variation in physicochemical properties on engine performance and emissions. The future work in developing standard test procedures for establishing fuel properties and limits/targets would be beneficial in using a large amount of waste cooking oil in the production of biodiesel, thus contributing to reduction in CO2 and waste minimisation.
7
Pacheco, Fábio Luiz Camacho. "Identificação bacteriana por derivação de ácidos graxos extraídos de células íntegras." Universidade de São Paulo, 2009. http://www.teses.usp.br/teses/disponiveis/9/9139/tde-28092009-143513/.
Full textAbstract:
As salas limpas são amplamente empregadas em indústrias farmacêuticas destinadas a fabricar medicamentos e dispositivos estéreis. Nós empregamos coloração de Gram e cromatografia gasosa de ésteres metílicos de ácidos graxos extraídos de células íntegras de microrganismos ambientais para caracterizar e identificar bactérias isoladas em 50 salas limpas diferentes projetadas para a fabricação de medicamentos estéreis e para fornecer um perfil de ácidos graxos das espécies mais comuns de bactérias isoladas. Uma análise estatística nos permitiu corroborar estudos anteriores e confirmar que cocos Gram positivos é o grupo mais relevante de microrganismos presentes nas salas limpas avaliadas. A espécie predominante é Micrococcus luteus, isolada de salas classe B e de pessoal, seguida de Staphylococcus cohnii em classe C, Bacillus subtilis em classe A e Staphylococcus hominis em classe D. Os perfis de ácidos graxos destas bactérias são, na maioria, consistentes com as bibliotecas padrão. Nós também tentamos estabelecer uma correlação entre a estação do ano e o nível de contaminação, embora a análise de variância tenha mostrado que não há diferença significativa entre o nível de contaminação no decorrer das estações. Além do mais, análises repetidas com um aumento gradual de massa celular nos permitiram concluir que a quantidade ótima de material celular necessário para extração de ácidos graxos varia com a espécie de bactéria. Finalmente, um estudo comparativo de algumas bactérias incubadas em diferentes temperaturas confirmou que o perfil de ácidos graxos é altamente influenciado pela temperatura. Portanto, nós acreditamos que este trabalho possa contribuir para identificar e compreender a comunidade bacteriana de algumas salas limpas farmacêuticas.Clean rooms are largely employed in pharmaceutical companies whose purpose is to produce sterile drugs and devices. We employed Gram staining and gas chromatography of fatty acid methyl esters extracted from whole cells of environmental isolates to characterize and identify bacteria isolated in each of 50 different clean rooms designed for the manufacturing of sterile medicinal products and to provide a fatty acid profile of the most common species of isolated bacteria. Statistical analysis allowed us to corroborate previous studies and confirm that Gram-positive cocci are the most relevant group of microorganisms inside the studied clean rooms. The predominant species is Micrococcus luteus, isolated from Grade B zones and from personnel, followed by Staphylococcus cohnii in Grade C, Bacillus subtilis in Grade A and S. hominis in Grade D. Fatty acid profiles of these bacteria are, to a great extent, consistent with standard libraries. We also attempted to establish a correlation between season and level of contamination, although variance analysis showed that there is no significant difference on the level of contamination throughout seasons. Furthermore, repeated analysis with a gradual increase in cell mass allowed us to conclude that the optimal amount of cell material depends on the species of the bacteria studied. Finally, a comparative study with some bacteria incubated in different temperatures confirmed that fatty acid profile is highly influenced by temperature. Therefore, we believe that this work can contribute to identify and understand the bacterial community of some pharmaceutical clean rooms.
8
Cornish, Yvonne. "George Robert Fitzgerald (1748?-1786) and the nature of eighteenth-century celebrity culture : an analysis of the language, character and representation of late eighteenth-century celebrity drawn from literary sources." Thesis, University of Oxford, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.670130.
Full text
9
Bahceci, Humeyra. "Fatty Acid Methyl Ester Analysis Of Bacterial Isolates From Salt Lake, Turkey And Characterization Of Their Extracellular Enzymes." Master's thesis, METU, 2004. http://etd.lib.metu.edu.tr/upload/3/12605483/index.pdf.
Full textAbstract:
In this study, 11 bacterial isolates from Salt Lake,Turkey were identified by using fatty acid methyl ester (FAME) analysis. They were screened for production of industrially important enzymes xylanase, cellulase, α
-amylase and protease. These enzymes were characterized in terms of enzyme activity, stability, optimum temperature and optimum pH. One of the isolates was identified as Bacillus pumilus, and two of them were identified as Bacillus subtilis. Other isolates were determined to be Bacillus licheniformis. All the isolates were determined to produce xylanase. Optimum temperatures and optimum pH values of xylanases were 50-55 °
C and pH 7.0-8.0. Xylanases were quite stable up to pH 8.0 and 70 °
C. Isolates were not significant cellulase producers. Four of the isolates did not produce any cellulase enzyme and the rest produced negligible amounts of cellulase. Therefore, xylanases from the isolates were promising for pulp and paper industry, which requires cellulase free and stable xylanases. All the isolates produced appreciable quantities of &
#945
-amylase. Optimum temperatures and optimum pH values of &
#945
-amylases 60-80 °
C and pH 7.0-8.0. &
#945
-Amylases were quite stable up to pH 9.0 and 80 °
C. &
#945
-Amylases from the isolates were promising for starch processing industry, which requires &
#945
-amylases stable at high temperatures and for detergent industry, which requires &
#945
-amylases stable at alkaline pH values. Considerable protease productions were achieved by all the isolates. TTG 2 was the best protease producer with 271 U/ml. Optimum temperatures and optimum pH values of proteases were 50-60 °
C and pH 7.0-7.4. Proteases were quite stable up to pH 9.0 and 80 °
C. Proteases from the isolates were promising for detergent and leather industry, in which proteases must be stable at alkaline pH values.
10
Sinnig, Julia [Verfasser], Christoph [Akademischer Betreuer] Burmann, Christoph [Gutachter] Burmann, and Tilo [Gutachter] Halaszovich. "The Role of Origin of Fame in Influencer Branding : a Comparative Analysis of German and Russian Consumers / Julia Sinnig ; Gutachter: Christoph Burmann, Tilo Halaszovich ; Betreuer: Christoph Burmann." Bremen : Staats- und Universitätsbibliothek Bremen, 2019. http://d-nb.info/118624884X/34.
Full text
11
Sinnig, Julia Verfasser], Christoph [Akademischer Betreuer] [Burmann, Christoph [Gutachter] Burmann, and Tilo [Gutachter] Halaszovich. "The Role of Origin of Fame in Influencer Branding : a Comparative Analysis of German and Russian Consumers / Julia Sinnig ; Gutachter: Christoph Burmann, Tilo Halaszovich ; Betreuer: Christoph Burmann." Bremen : Staats- und Universitätsbibliothek Bremen, 2019. http://d-nb.info/118624884X/34.
Full text
12
Shaffer, Anne, Monica Whitehead, Molly Davis, Diana Morelen, and Cynthia Suveg. "A Model‐Based Cluster Analysis of Maternal Emotion Regulation and Relations to Parenting Behavior." Digital Commons @ East Tennessee State University, 2018. https://doi.org/10.1111/famp.12326.
Full textAbstract:
In a diverse community sample of mothers (N = 108) and their preschool‐aged children (Mage = 3.50 years), this study conducted person‐oriented analyses of maternal emotion regulation (ER) based on a multimethod assessment incorporating physiological, observational, and self‐report indicators. A model‐based cluster analysis was applied to five indicators of maternal ER: maternal self‐report, observed negative affect in a parent–child interaction, baseline respiratory sinus arrhythmia (RSA), and RSA suppression across two laboratory tasks. Model‐based cluster analyses revealed four maternal ER profiles, including a group of mothers with average ER functioning, characterized by socioeconomic advantage and more positive parenting behavior. A dysregulated cluster demonstrated the greatest challenges with parenting and dyadic interactions. Two clusters of intermediate dysregulation were also identified. Implications for assessment and applications to parenting interventions are discussed.
13
Bordei, Cristina. "Face analysis using polynomials." Thesis, Poitiers, 2016. http://www.theses.fr/2016POIT2259/document.
Full textAbstract:
Considéré comme l'un des sujets de recherche les plus actifs et visibles de la vision par ordinateur, de la reconnaissance des formes et de la biométrie, l'analyse faciale a fait l'objet d'études approfondies au cours des deux dernières décennies. Le travail de cette thèse a pour objectif de proposer de nouvelles techniques d'utilisation de représentations de texture basées polynômes pour l'analyse faciale.La première partie de cette thèse est dédiée à l'intégration de bases de polynômes dans les modèles actifs d'apparence. Nous proposons premièrement une manière d'utiliser les coefficients polynomiaux dans la modélisation de l'apparence. Ensuite, afin de réduire la complexité du modèle nous proposons de choisir et d'utiliser les meilleurs coefficients en tant que représentation de texture. Enfin, nous montrons comment ces derniers peuvent être utilisés dans un algorithme de descente de gradient.La deuxième partie de la thèse porte sur l'utilisation des bases polynomiales pour la détection des points/zones d'intérêt et comme descripteur pour la reconnaissance des expressions faciales. Inspirés par des techniques de détection des singularités dans des champ de vecteurs, nous commençons par présenter un algorithme utilisé pour l'extraction des points d'intérêt dans une image. Puis nous montrons comment les bases polynomiales peuvent être utilisées pour extraire des informations sur les expressions faciales. Puisque les coefficients polynomiaux fournissent une analyse précise multi-échelles et multi-orientation et traitent le problème de redondance efficacement ils sont utilisés en tant que descripteurs dans un algorithme de classification d'expression facialeAs one of the most active and visible research topic in computer vision, pattern recognition and biometries, facial analysis has been extensively studied in the past two decades. The work in this thesis presents novel techniques to use polynomial basis texture representations for facial analysis. The first part of this thesis, is dedicated to the integration of polynomial bases in the Active Appearance Models - a set of statistical tools that proved to be very efficient in modeling faces. First we propose a way to use the coefficients obtained after polynomial projections in the appearance modeling. Then, in order to reduce model complexity we proposed to select and use as a texture representation the strongest polynomial coefficients. Finally we show how in addition to the texture representation polynomial coefficients can be used in a gradient descent algorithm since polynomial decomposition is equivalent to a filter bank.The second part of the thesis concems the use of the polynomial bases for interesting points and areas detection and as a descriptor for facial expression recognition. We start by presenting an algorithm used for accurate image keypoints localization inspired by techniques of singularities detection in a vector field. Our approach consists in two major steps: the calculation of an image vector field of normals and the keypoint selection within the field both presented in a multi-scale multi resolution scheme. Finally we show how polynomial bases can be used to extract informations about facial expressions. Polynomial coefficients are used as descriptors in an facial expression classification algorithm
14
Al-Dahoud, Ahmad. "The computational face for facial emotion analysis: Computer based emotion analysis from the face." Thesis, University of Bradford, 2018. http://hdl.handle.net/10454/17384.
Full textAbstract:
Facial expressions are considered to be the most revealing way of understanding the human psychological state during face-to-face communication. It is believed that a more natural interaction between humans and machines can be undertaken through the detailed understanding of the different facial expressions which imitate the manner by which humans communicate with each other.
In this research, we study the different aspects of facial emotion detection, analysis and investigate possible hidden identity clues within the facial expressions. We study a deeper aspect of facial expressions whereby we try to identify gender and human identity - which can be considered as a form of emotional biometric - using only the dynamic characteristics of the smile expressions. Further, we present a statistical model for analysing the relationship between facial features and Duchenne (real) and non-Duchenne (posed) smiles. Thus, we identify that the expressions in the eyes contain discriminating features between Duchenne and non-Duchenne smiles.
Our results indicate that facial expressions can be identified through facial movement analysis models where we get an accuracy rate of 86% for classifying the six universal facial expressions and 94% for classifying the common 18 facial action units. Further, we successfully identify the gender using only the dynamic characteristics of the smile expression whereby we obtain an 86% classification rate. Likewise, we present a framework to study the possibility of using the smile as a biometric whereby we show that the human smile is unique and stable.Al-Zaytoonah University
15
Buchala, Samarasena. "Computational analysis of face images." Thesis, University of Hertfordshire, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.431938.
Full text
16
Amin, Syed Hassan. "Analysis of 3D face reconstruction." Thesis, Imperial College London, 2009. http://hdl.handle.net/10044/1/6163.
Full textAbstract:
This thesis investigates the long standing problem of 3D reconstruction from a single 2D face image. Face reconstruction from a single 2D face image is an ill posed problem involving estimation of the intrinsic and the extrinsic camera parameters, light parameters, shape parameters and the texture parameters. The proposed approach has many potential applications in the law enforcement, surveillance, medicine, computer games and the entertainment industries. This problem is addressed using an analysis by synthesis framework by reconstructing a 3D face model from identity photographs. The identity photographs are a widely used medium for face identi cation and can be found on identity cards and passports. The novel contribution of this thesis is a new technique for creating 3D face models from a single 2D face image. The proposed method uses the improved dense 3D correspondence obtained using rigid and non-rigid registration techniques. The existing reconstruction methods use the optical ow method for establishing 3D correspondence. The resulting 3D face database is used to create a statistical shape model. The existing reconstruction algorithms recover shape by optimizing over all the parameters simultaneously. The proposed algorithm simplifies the reconstruction problem by using a step wise approach thus reducing the dimension of the parameter space and simplifying the opti- mization problem. In the alignment step, a generic 3D face is aligned with the given 2D face image by using anatomical landmarks. The texture is then warped onto the 3D model by using the spatial alignment obtained previously. The 3D shape is then recovered by optimizing over the shape parameters while matching a texture mapped model to the target image. There are a number of advantages of this approach. Firstly, it simpli es the optimization requirements and makes the optimization more robust. Second, there is no need to accurately recover the illumination parameters. Thirdly, there is no need for recovering the texture parameters by using a texture synthesis approach. Fourthly, quantitative analysis is used for improving the quality of reconstruction by improving the cost function. Previous methods use qualitative methods such as visual analysis, and face recognition rates for evaluating reconstruction accuracy. The improvement in the performance of the cost function occurs as a result of improvement in the feature space comprising the landmark and intensity features. Previously, the feature space has not been evaluated with respect to reconstruction accuracy thus leading to inaccurate assumptions about its behaviour. The proposed approach simpli es the reconstruction problem by using only identity images, rather than placing eff ort on overcoming the pose, illumination and expression (PIE) variations. This makes sense, as frontal face images under standard illumination conditions are widely available and could be utilized for accurate reconstruction. The reconstructed 3D models with texture can then be used for overcoming the PIE variations.
17
Wang, Wei. "Human Face and Behavior Analysis." Doctoral thesis, Università degli studi di Trento, 2018. https://hdl.handle.net/11572/367945.
Full textAbstract:
Human face and behavior analysis are very important research topics in the field of computer vision and they have broad applications in our everyday life. For instance, face alignment, face aging, face expression analysis and action recognition have been well studied and applied for security and entertainment. With these face analyzing techniques (e.g., face aging), we could enhance the performance of cross-age face verification system which now has been used for banks and electronic devices to recognize their clients. With the help of action recognition system, we could better summarize the user uploaded videos or generate logs for surveillance videos. This could help us retrieve the videos more accurately and easily.
The dictionary learning and neural networks are powerful machine learning models for these research tasks. Initially, we focus on the multi-view action recognition task. First, a class-wise dictionary is pre-trained which encourages the sparse representations of the between-class videos from different views to lie close by. Next, we integrate the classifiers and the dictionary learning model into a unified model to learn the dictionary and classifiers jointly.
For face alignment, we frame the standard cascaded face alignment problem as a recurrent process by using a recurrent neural network. Importantly, by combining a convolutional neural network with a recurrent one we alleviate hand-crafted features to learn task-specific features. For human face aging task, it takes as input a single image and automatically outputs a series of aged faces. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transitional states. In this way, the intermediate aged faces between the age groups can be generated. Towards this target, we employ a recurrent neural network. The hidden units in the RFA are connected autoregressively allowing the framework to age the person by referring to the previous aged faces. For smile video generation, one person may smile in different ways (e.g., closing/opening the eyes or mouth). This is a one-to-many image-to-video generation problem, and we introduce a deep neural architecture named conditional multi-mode network (CMM-Net) to approach it. A multi-mode recurrent generator is trained to induce diversity and generate K different sequences of video frames.
18
Wang, Wei. "Human Face and Behavior Analysis." Doctoral thesis, University of Trento, 2018. http://eprints-phd.biblio.unitn.it/2925/1/phd_thesis.pdf.
Full textAbstract:
Human face and behavior analysis are very important research topics in the field of computer vision and they have broad applications in our everyday life. For instance, face alignment, face aging, face expression analysis and action recognition have been well studied and applied for security and entertainment. With these face analyzing techniques (e.g., face aging), we could enhance the performance of cross-age face verification system which now has been used for banks and electronic devices to recognize their clients. With the help of action recognition system, we could better summarize the user uploaded videos or generate logs for surveillance videos. This could help us retrieve the videos more accurately and easily.
The dictionary learning and neural networks are powerful machine learning models for these research tasks. Initially, we focus on the multi-view action recognition task. First, a class-wise dictionary is pre-trained which encourages the sparse representations of the between-class videos from different views to lie close by. Next, we integrate the classifiers and the dictionary learning model into a unified model to learn the dictionary and classifiers jointly.
For face alignment, we frame the standard cascaded face alignment problem as a recurrent process by using a recurrent neural network. Importantly, by combining a convolutional neural network with a recurrent one we alleviate hand-crafted features to learn task-specific features. For human face aging task, it takes as input a single image and automatically outputs a series of aged faces. Since human face aging is a smooth progression, it is more appropriate to age the face by going through smooth transitional states. In this way, the intermediate aged faces between the age groups can be generated. Towards this target, we employ a recurrent neural network. The hidden units in the RFA are connected autoregressively allowing the framework to age the person by referring to the previous aged faces. For smile video generation, one person may smile in different ways (e.g., closing/opening the eyes or mouth). This is a one-to-many image-to-video generation problem, and we introduce a deep neural architecture named conditional multi-mode network (CMM-Net) to approach it. A multi-mode recurrent generator is trained to induce diversity and generate K different sequences of video frames.
19
Patrick, William Charles. "Investigation, Analysis, and Modeling of Longwall Face-to-Face Transfers." Diss., This resource online, 1993. http://scholar.lib.vt.edu/theses/available/etd-06092008-112841/.
Full textAbstract:
Thesis (Ph. D.)--Virginia Polytechnic Institute and State University, 1993.Vita. Abstract. Attached pocket for diagrams. Includes bibliographical references (leaves 155-162). Also available via the Internet.
20
Mahmood, Muhammad Tariq. "Face Detection by Image Discriminating." Thesis, Blekinge Tekniska Högskola, Avdelningen för för interaktion och systemdesign, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4352.
Full textAbstract:
Human face recognition systems have gained a considerable attention during last few years. There are very many applications with respect to security, sensitivity and secrecy. Face detection is the most important and first step of recognition system. Human face is non rigid and has very many variations regarding image conditions, size, resolution, poses and rotation. Its accurate and robust detection has been a challenge for the researcher. A number of methods and techniques are proposed but due to a huge number of variations no one technique is much successful for all kinds of faces and images. Some methods are exhibiting good results in certain conditions and others are good with different kinds of images. Image discriminating techniques are widely used for pattern and image analysis. Common discriminating methods are discussed.SIPL, Mechatronics, GIST 1 Oryong-Dong, Buk-Gu, Gwangju, 500-712 South Korea tel. 0082-62-970-2997
21
Wei, Xiaozhou. "3D facial expression modeling and analysis with topographic information." Diss., Online access via UMI:, 2008.
Find full text
22
Liu, Feng. "Face Gear Design and Compliance Analysis." The Ohio State University, 2004. http://rave.ohiolink.edu/etdc/view?acc_num=osu1392373365.
Full text
23
Alfonso, Miñambres Javier de. "Face recognition using principal component analysis." Master's thesis, Universidade de Aveiro, 2010. http://hdl.handle.net/10773/10221.
Full textAbstract:
Mestrado em Engenharia Electrónica e TelecomunicaçõesThe purpose of this dissertation was to analyze the image processing method known as Principal Component Analysis (PCA) and its performance when applied to face recognition. This algorithm spans a subspace (called facespace) where the faces in a database are represented with a reduced number of features (called feature vectors). The study focused on performing various exhaustive tests to analyze in what conditions it is best to apply PCA. First, a facespace was spanned using the images of all the people in the database. We obtained then a new representation of each image by projecting them onto this facespace. We measured the distance between the projected test image with the other projections and determined that the closest test-train couple (k-Nearest Neighbour) was the recognized subject. This first way of applying PCA was tested with the Leave{One{Out test. This test takes an image in the database for test and the rest to build the facespace, and repeats the process until all the images have been used as test image once, adding up the successful recognitions as a result. The second test was to perform an 8{Fold Cross{Validation, which takes ten images as eligible test images (there are 10 persons in the database with eight images each) and uses the rest to build the facespace. All test images are tested for recognition in this fold, and the next fold is carried out, until all eight folds are complete, showing a different set of results. The other way to use PCA we used was to span what we call Single Person Facespaces (SPFs, a group of subspaces, each spanned with images of a single person) and measure subspace distance using the theory of principal angles. Since the database is small, a way to synthesize images from the existing ones was explored as a way to overcoming low successful recognition rates. All of these tests were performed for a series of thresholds (a variable which selected the number of feature vectors the facespaces were built with, i.e. the facespaces' dimension), and for the database after being preprocessed in two different ways in order to reduce statistically redundant information. The results obtained throughout the tests were within what expected from what can be read in literature: success rates of around 85% in some cases. Special mention needs to be made on the great result improvement between SPFs before and after extending the database with synthetic images. The results revealed that using PCA to project the images in the group facespace is very accurate for face recognition, even when having a small number of samples per subject. Comparing personal facespaces is more effective when we can synthesize images or have a natural way of acquiring new images of the subject, like for example using video footage. The tests and results were obtained with a custom software with user interface, designed and programmed by the author of this dissertation.
O propósito desta Dissertação foi a aplicação da Analise em Componentes Principais (PCA, de acordo com as siglas em inglês), em sistemas para reconhecimento de faces. Esta técnica permite calcular um subespaço (chamado facespace, onde as imagens de uma base de dados são representadas por um número reduzido de características (chamadas feature vectors). O estudo realizado centrou-se em vários testes para analisar quais são as condições óptimas para aplicar o PCA. Para começar, gerou-se um faces- pace utilizando todas as imagens da base de dados. Obtivemos uma nova representação de cada imagem, após a projecção neste espaço, e foram medidas as distâncias entre as projecções da imagem de teste e as de treino. A dupla de imagens de teste-treino mais próximas determina o sujeito reconhecido (classificador vizinhos mais próximos). Esta primeira forma de aplicar o PCA, e o respectivo classificador, foi avaliada com as estratégias Leave{One{Out e 8{Fold Cross{Validation. A outra forma de utilizar o PCA foi gerando subespaços individuais (designada por SPF, Single Person Facespace), onde cada subespaço era gerado com imagens de apenas uma pessoa, para a seguir medir a distância entre estes espaços utilizando o conceito de ângulos principais. Como a base de dados era pequena, foi explorada uma forma de sintetizar novas imagens a partir das já existentes. Todos estes teste foram feitos para uma série de limiares (uma variável threshold que determinam o número de feature vectors com os que o faces- pace é construído) e diferentes formas de pre-processamento. Os resultados obtidos estavam dentro do esperado: taxas de acerto aproximadamente iguais a 85% em alguns casos. Pode destacar-se uma grande melhoria na taxa de reconhecimento após a inclusão de imagens sintéticas na base de dados. Os resultados revelaram que o uso do PCA para projectar imagens no subespaço da base de dados _e viável em sistemas de reconhecimento de faces, principalmente se comparar subespaço individuais no caso de base de dados com poucos exemplares em que _e possível sintetizar imagens ou em sistemas com captura de vídeo.
24
Hu, Guosheng. "Face analysis using 3D morphable models." Thesis, University of Surrey, 2015. http://epubs.surrey.ac.uk/808011/.
Full textAbstract:
Face analysis aims to extract valuable information from facial images. One effective approach for face analysis is the analysis by synthesis. Accordingly, a new face image synthesised by inferring semantic knowledge from input images. To perform analysis by synthesis, a genera- tive model, which parameterises the sources of facial variations, is needed. A 3D Morphable Model (3DMM) is commonly used for this purpose. 3DMMs have been widely used for face analysis because the intrinsic properties of 3D faces provide an ideal representation that is immune to intra-personal variations such as pose and illumination. Given a single facial input image, a 3DMM can recover 3D face (shape and texture) and scene properties (pose and illumination) via a fitting process. However, fitting the model to the input image remains a challenging problem. One contribution of this thesis is a novel fitting method: Efficient Stepwise Optimisation (ESO). ESO optimises sequentially all the parameters (pose, shape, light direction, light strength and texture parameters) in separate steps. A perspective camera and Phong reflectance model are used to model the geometric projection and illumination respectively. Linear methods that are adapted to camera and illumination models are proposed. This generates closed-form solu- tions for these parameters, leading to an accurate and efficient fitting. Another contribution is an albedo based 3D morphable model (AB3DMM). One difficulty of 3DMM fitting is to recover the illumination of the 2D image because the proportion of the albedo and shading contributions in a pixel intensity is ambiguous. Unlike traditional methods, the AB3DMM removes the illumination component from the input image using illumination normalisation methods in a preprocessing step. This image can then be used as input to the AB3DMM fitting that does not need to handle the lighting parameters. Thus, the fitting of the AB3DMM becomes easier and more accurate. Based on AB3DMM and ESO, this study proposes a fully automatic face recognition (AFR) system. Unlike the existing 3DMM methods which assume the facial landmarks are known, our AFR automatically detects the landmarks that are used to initialise our fitting algorithms. Our AFR supports two types of feature extraction: holistic and local features. Experimental results show our AFR outperforms state-of-the-art face recognition methods.
25
Huang, Jian. "Discriminant analysis algorithms for face recognition." HKBU Institutional Repository, 2006. http://repository.hkbu.edu.hk/etd_ra/655.
Full text
26
Zhao, Shuyan. "Face analysis under near infrared illumination." Göttingen Cuvillier, 2008. http://d-nb.info/990811492/04.
Full text
27
Rana, Santu. "Multilinear analysis of face image ensembles." Thesis, Curtin University, 2010. http://hdl.handle.net/20.500.11937/1662.
Full textAbstract:
Machine based face recognition is an important area of research that has attracted significant attention over the past few decades. Recently, multilinear models of face images have gained prominence as an alternative method for face recognition. Against linear techniques, multilinear models offer the advantage of having more complex models. Against kernel and manifold based non-linear techniques, the advantage lies in having more intuitive and computationally frugal modelling. In this thesis, we present an in-depth analysis and understanding of different properties associated with multilinear analysis and propose three different face recognition algorithms and a unified framework addressing open issues in face recognition.We first propose a face recognition algorithm primarily to address the limitations of the existing multilinear based algorithms in the form of their inability to handle test images that are in unseen conditions. The algorithm is based on the construction of a new representational basis multilinear eigenmodes, enabling representation and classification of faces at unseen conditions. Subsequently, we propose a second algorithm to address the high computational complexity of the first algorithm. We define a set of person-specific bases to represent person-specific images under all variations, and based on this propose an efficient recognition algorithm. Next, we propose a framework of face recognition based on an interpretation of the multilinear analysis as a factor analysis paradigm. We the reformulate all the multilinear based algorithms to link them to a single optimization framework. A theoretical comparison of these algorithms is performed revealing the fundamental differences between them and their applicability in different face recognition scenarios. Experiments performed to compare multilinear analysis based methods to the leading linear and non-linear techniques reveal the superiority of our second algorithm on both measures of recognition accuracy and test speed.Next, we address the issue of inadequate training samples that arise in many application scenarios. We introduce a novel “friendly-hostile” paradigm, in which we propose a mechanism to compensate for the low number of training samples of hostile people by learning the structure of face images from a large training set of the friendly people. The formulation is built on a novel synthesis paradigm that is based on the unique factorization properties of the multilinear analysis. Experimental results show significant performance gain in comparison to the conventional methods. We also discuss issues concerning unbalanced datasets, wherein some people may be under-represented than others in the training set. This results in different apriori bias per class, affecting conventional recognition algorithms. Based on theory and experiments we demonstrate that our algorithm does not get affected by any such imbalance in bias and produces consistent performance in all situations.
28
Wang, Jing. "Reconstruction and Analysis of 3D Individualized Facial Expressions." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32588.
Full textAbstract:
This thesis proposes a new way to analyze facial expressions through 3D scanned faces of real-life people. The expression analysis is based on learning the facial motion vectors that are the differences between a neutral face and a face with an expression. There are several expression analysis based on real-life face database such as 2D image-based Cohn-Kanade AU-Coded Facial Expression Database and Binghamton University 3D Facial Expression Database. To handle large pose variations and increase the general understanding of facial behavior, 2D image-based expression database is not enough. The Binghamton University 3D Facial Expression Database is mainly used for facial expression recognition and it is difficult to compare, resolve, and extend the problems related detailed 3D facial expression analysis. Our work aims to find a new and an intuitively way of visualizing the detailed point by point movements of 3D face model for a facial expression.
In our work, we have created our own 3D facial expression database on a detailed level, which each expression model has been processed to have the same structure to compare differences between different people for a given expression.
The first step is to obtain same structured but individually shaped face models. All the head models are recreated by deforming a generic model to adapt a laser-scanned individualized face shape in both coarse level and fine level. We repeat this recreation method on different human subjects to establish a database. The second step is expression cloning. The motion vectors are obtained by subtracting two head models with/without expression. The extracted facial motion vectors are applied onto a different human subject’s neutral face. Facial expression cloning is proved to be robust and fast as well as easy to use. The last step is about analyzing the facial motion vectors obtained from the second step. First we transferred several human subjects’ expressions on a single human neutral face. Then the analysis is done to compare different expression pairs in two main regions: the whole face surface analysis and facial muscle analysis.
Through our work where smiling has been chosen for the experiment, we find our approach to analysis through face scanning a good way to visualize how differently people move their facial muscles for the same expression. People smile in a similar manner moving their mouths and cheeks in similar orientations, but each person shows her/his own unique way of moving. The difference between individual smiles is the differences of movements they make.
29
Pillet-Shore, Danielle Marguerite. "Coming together creating and maintaining social relationships through the openings of face-to-face interactions /." Diss., Restricted to subscribing institutions, 2008. http://proquest.umi.com/pqdweb?did=1619144141&sid=1&Fmt=2&clientId=1564&RQT=309&VName=PQD.
Full text
30
Olausson, Erik. "Face Recognition for Mobile Phone Applications." Thesis, Linköping University, Department of Science and Technology, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-11850.
Full textAbstract:
Att applicera ansiktsigenkänning direkt på en mobiltelefon är en utmanande uppgift, inte minst med tanke på den begränsade minnes- och processorkapaciteten samt den stora variationen med avseende på ansiktsuttryck, hållning och ljusförhållande i inmatade bilder.
Det är fortfarande långt kvar till ett färdigutvecklat, robust och helautomatiskt ansiktsigenkänningssystem för den här miljön. Men resultaten i det här arbetet visar att genom att plocka ut feature-värden från lokala regioner samt applicera en välgjord warpstrategi för att minska problemen med variationer i position och rotation av huvudet, är det möjligt att uppnå rimliga och användbara igenkänningsnivåer. Speciellt för ett halvautomatiskt system där användaren har sista ordet om vem personen på bilden faktiskt är.
Med ett galleri bestående av 85 personer och endast en referensbild per person nådde systemet en igenkänningsgrad på 60% på en svårklassificerad serie testbilder. Totalt 73% av gångerna var den rätta individen inom de fyra främsta gissningarna.
Att lägga till extra referensbilder till galleriet höjer igenkänningsgraden rejält, till nästan 75% för helt korrekta gissningar och till 83,5% för topp fyra. Detta visar att en strategi där inmatade bilder läggs till som referensbilder i galleriet efterhand som de identifieras skulle löna sig ordentligt och göra systemet bättre efter hand likt en inlärningsprocess.
Detta exjobb belönades med pris för "Bästa industrirelevanta bidrag" vid Svenska sällskapet för automatiserad bildanalys årliga konferens i Lund, 13-14 mars 2008.
Applying face recognition directly on a mobile phone is a challenging proposal due to the unrestrained nature of input images and limitations in memory and processor capabilities.
A robust, fully automatic recognition system for this environment is still a far way off. However, results show that using local feature extraction and a warping scheme to reduce pose variation problems, it is possible to capitalize on high error tolerance and reach reasonable recognition rates, especially for a semi-automatic classification system where the user has the final say.
With a gallery of 85 individuals and only one gallery image per individual available the system is able to recognize close to 60 % of the faces in a very challenging test set, while the correct individual is in the top four guesses 73% of the time.
Adding extra reference images boosts performance to nearly 75% correct recognition and 83.5% in the top four guesses. This suggests a strategy where extra reference images are added one by one after correct classification, mimicking an online learning strategy.
31
Bartlett, Marian Stewart. "Face image analysis by unsupervised learning and redundancy reduction /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 1998. http://wwwlib.umi.com/cr/ucsd/fullcit?p9907603.
Full text
32
Lee, Colin K. "Infrared face recognition." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2004. http://library.nps.navy.mil/uhtbin/hyperion/04Jun%5FLee%5FColin.pdf.
Full textAbstract:
Thesis (M.S. in Electrical Engineering)--Naval Postgraduate School, June 2004.Thesis advisor(s): Monique P. Fargues, Gamani Karunasiri. Includes bibliographical references (p. 135-136). Also available online.
33
Boulkenafet, Z. (Zinelabidine). "Face presentation attack detection using texture analysis." Doctoral thesis, Oulun yliopisto, 2018. http://urn.fi/urn:isbn:9789526219257.
Full textAbstract:
Abstract In the last decades, face recognition systems have evolved a lot in terms of performance. As a result, this technology is now considered as mature and is applied in many real world applications from border control to financial transactions and computer security. Yet, many studies show that these systems suffer from vulnerabilities to spoofing attacks, a weakness that may limit their usage in many cases. A face spoofing attack or presentation attack occurs when someone tries to masquerade as someone else by presenting a fake face in front of the face recognition camera. To protect the recognition systems against attacks of this kind, many face anti-spoofing methods have been proposed. These methods have shown good performances on the existing face anti-spoofing databases. However, their performances degrade drastically under real world variations (e.g., illumination and camera device variations). In this thesis, we concentrate on improving the generalization capabilities of the face anti-spoofing methods with a particular focus on the texture based techniques. In contrast to most existing texture based methods aiming at extracting texture features from gray-scale images, we propose a joint color-texture analysis. First, the face images are converted into different color spaces. Then, the feature histograms computed over each image band are concatenated and used for discriminating between real and fake face images. Our experiments conducted on three color spaces: RGB, HSV and YCbCr show that extracting the texture information from separated luminance chrominance color spaces (HSV and YCbCr) yields to better performances compared to gray-scale and RGB image representations. Moreover, to deal with the problem of illumination and image-resolution variations, we propose to extract this texture information from different scale images. In addition to representing the face images in different scales, the multi-scale filtering methods also act as pre-processing against factors such as noise and illumination. Although our obtained results are better than the state of the art, they are still far from the requirements of real world applications. Thus, to help in the development of robust face anti-spoofing methods, we collected a new challenging face anti-spoofing database using six camera devices in three different illumination and environmental conditions. Furthermore, we have organized a competition on the collected database where fourteen face anti-spoofing methods have been assessed and comparedTiivistelmä Kasvontunnistusjärjestelmien suorituskyky on parantunut huomattavasti viime vuosina. Tästä syystä tätä teknologiaa pidetään nykyisin riittävän kypsänä ja käytetään jo useissa käytännön sovelluksissa kuten rajatarkastuksissa, rahansiirroissa ja tietoturvasovelluksissa. Monissa tutkimuksissa on kuitenkin havaittu, että nämä järjestelmät ovat myös haavoittuvia huijausyrityksille, joissa joku yrittää esiintyä jonakin toisena henkilönä esittämällä kameralle jäljennöksen kohdehenkilön kasvoista. Tämä haavoittuvuus rajoittaa kasvontunnistuksen laajempaa käyttöä monissa sovelluksissa. Tunnistusjärjestelmien turvaamiseksi on kehitetty lukuisia menetelmiä tällaisten hyökkäysten torjumiseksi. Nämä menetelmät ovat toimineet hyvin tätä tarkoitusta varten kehitetyillä kasvotietokannoilla, mutta niiden suorituskyky huononee dramaattisesti todellisissa käytännön olosuhteissa, esim. valaistuksen ja käytetyn kuvantamistekniikan variaatioista johtuen. Tässä työssä yritämme parantaa kasvontunnistuksen huijauksen estomenetelmien yleistämiskykyä keskittyen erityisesti tekstuuripohjaisiin menetelmiin. Toisin kuin useimmat olemassa olevat tekstuuripohjaiset menetelmät, joissa tekstuuripiirteitä irrotetaan harmaasävykuvista, ehdotamme väritekstuurianalyysiin pohjautuvaa ratkaisua. Ensin kasvokuvat muutetaan erilaisiin väriavaruuksiin. Sen jälkeen kuvan jokaiselta kanavalta erikseen lasketut piirrehistogrammit yhdistetään ja käytetään erottamaan aidot ja väärät kasvokuvat toisistaan. Kolmeen eri väriavaruuteen, RGB, HSV ja YCbCr, perustuvat testimme osoittavat, että tekstuuri-informaation irrottaminen HSV- ja YCbCr-väriavaruuksien erillisistä luminanssi- ja krominanssikuvista parantaa suorituskykyä kuvien harmaasävy- ja RGB-esitystapoihin verrattuna. Valaistuksen ja kuvaresoluution variaation takia ehdotamme myös tämän tekstuuri-informaation irrottamista eri tavoin skaalatuista kuvista. Sen lisäksi, että itse kasvot esitetään eri skaaloissa, useaan skaalaan perustuvat suodatusmenetelmät toimivat myös esikäsittelynä sellaisia suorituskykyä heikentäviä tekijöitä vastaan kuten kohina ja valaistus. Vaikka tässä tutkimuksessa saavutetut tulokset ovat parempia kuin uusinta tekniikkaa edustavat tulokset, ne ovat kuitenkin vielä riittämättömiä reaalimaailman sovelluksissa tarvittavaan suorituskykyyn. Sen takia edistääksemme uusien robustien kasvontunnistuksen huijaamisen ilmaisumenetelmien kehittämistä kokosimme uuden, haasteellisen huijauksenestotietokannan käyttäen kuutta kameraa kolmessa erilaisessa valaistus- ja ympäristöolosuhteessa. Järjestimme keräämällämme tietokannalla myös kansainvälisen kilpailun, jossa arvioitiin ja verrattiin neljäätoista kasvontunnistuksen huijaamisen ilmaisumenetelmää
34
Wileman, James Michael. "Dynamic analysis of eccentric mechanical face seals." Diss., Georgia Institute of Technology, 1994. http://hdl.handle.net/1853/17343.
Full text
35
Riaz, Muhammed Shahjahan. "Analysis of discriminant features for face recognition." Thesis, Imperial College London, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.325242.
Full text
36
Chinthapalli, Vamsi Krishna. "Face shape analysis in people with epilepsy." Thesis, University College London (University of London), 2018. http://discovery.ucl.ac.uk/10043826/.
Full textAbstract:
Stereophotogrammetry and dense surface modelling are novel techniques that have been used to study face shape in genetic and neurodevelopmental disorders. In people with epilepsy, it has been recognised that the condition may be associated with underlying structural variants or malformations of cortical development in some cases. Here I recruited 869 people with epilepsy or unaffected relatives and control subjects to study face shape. I sought to explore whether face shape and symmetry, using new metrics for each, could help to predict those people with epilepsy who may have potential underlying genetic or structural causes. My reproducibility studies found that stereophotogrammetry and dense surface modelling were susceptible to error from changes in head position or face expression, but not from camera calibration, image acquisition and image landmarking. The next study found that in people with epilepsy, a measurement of atypical face shape, Face Shape Difference (FSD), was significantly increased in those with pathogenic structural variants compared to those without pathogenic structural variants. The FSD value was used to predict the presence of pathogenic structural variants with a sensitivity of 66- 80% and specificity of 65-78%. Body mass index affects face shape in a partly predictable manner. The effect of body mass index differences was controlled for in a further analysis. I then analysed facial asymmetry and showed that it was increased in people with developmental lesions in the brain but not in people with pathogenic structural variants. A final study showed that stereophotogrammetry, dense surface modelling, FSD and reflected FSD could be used to study a single genetic disorder associated with epilepsy, to find previously unrecognised face shape changes. Stereophotogrammetry and dense surface modelling therefore appear to be promising tools to aid both in discovery of underlying causes for epilepsy and in understanding of such causes in terms of facial development.
37
Patel, Vatsa Sanjay. "Masked Face Analysis via Multitask Deep Learning." University of Dayton / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1619637677725646.
Full text
38
Paras, Carrie. "An analysis of the multiple face phenomenon /." abstract and full text PDF (UNR users only), 2007. http://0-gateway.proquest.com.innopac.library.unr.edu/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:1446791.
Full textAbstract:
Thesis (M.A.)--University of Nevada, Reno, 2007."May, 2007." Includes bibliographical references (leaves 29-33). Library also has microfilm. Ann Arbor, Mich. : ProQuest Information and Learning Company, [2008]. 1 microfilm reel ; 35 mm. Online version available on the World Wide Web.
39
Duffner, Stefan. "Face image analysis with convolutional neural networks." [S.l. : s.n.], 2007. http://nbn-resolving.de/urn:nbn:de:bsz:25-opus-48350.
Full text
40
Clement, Stephen J. "Sparse shape modelling for 3D face analysis." Thesis, University of York, 2014. http://etheses.whiterose.ac.uk/8248/.
Full textAbstract:
This thesis describes a new method for localising anthropometric landmark points on 3D face scans. The points are localised by fitting a sparse shape model to a set of candidate landmarks. The candidates are found using a feature detector that is designed using a data driven methodology, this approach also informs the choice of landmarks for the shape model. The fitting procedure is developed to be robust to missing landmark data and spurious candidates. The feature detector and landmark choice is determined by the performance of different local surface descriptions on the face. A number of criteria are defined for a good landmark point and good feature detector. These inform a framework for measuring the performance of various surface descriptions and the choice of parameter values in the surface description generation. Two types of surface description are tested: curvature and spin images. These descriptions, in many ways, represent many aspects of the two most common approaches to local surface description. Using the data driven design process for surface description and landmark choice, a feature detector is developed using spin images. As spin images are a rich surface description, we are able to perform detection and candidate landmark labelling in a single step. A feature detector is developed based on linear discriminant analysis (LDA). This is compared to a simpler detector used in the landmark and surface description selection process. A sparse shape model is constructed using ground truth landmark data. This sparse shape model contains only the landmark point locations and relative positional variation. To localise landmarks, this model is fitted to the candidate landmarks using a RANSAC style algorithm and a novel model fitting algorithm. The results of landmark localisation show that the shape model approach is beneficial over template alignment approaches. Even with heavily contaminated candidate data, we are able to achieve good localisation for most landmarks.
41
Marra, Anton. "Disagreement in business negotiations : A qualitative study of BELF usage in face-to-face business negotiations." Thesis, Stockholms universitet, Engelska institutionen, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-133218.
Full textAbstract:
Knowledge of successful Business English as a lingua franca (BELF) has been recognized to be an essential element in overall business know-how (Kankaanranta & Louhiala-Salminen, 2010). In line with this notion, research has found that professionals use BELF and exploit a variety of discourse and pragmatic strategies that aid the process of cooperation and agreement so that mutual understanding can be reached (Firth, 1996; Kankaanranta & Planken, 2010; Pitzl, 2005). However, research has reported situations where business negotiators need to handle discord while maintaining a working rapport with the opposing party (e.g. Bjørge, 2012), indicating that the ability to produce the appropriate expression of disagreement is an imperative skill. Nonetheless, while there is now a better understanding of how business professionals establish common ground through using BELF, little work has been carried out on the subject on how professionals express disagreement in the same aspect (but see e.g. Bjørge, 2012; Stalpers, 1995). The present study aims to address this gap and expand the current knowledge on how business professionals express and handle disagreement in naturally-occurring face-to-face negotiations. The collected material consists of approximately 4 hours of BELF discourse recorded at a business convention in Germany. Fifteen disagreement episodes were identified, transcribed and analyzed using Conversation Analytic (CA) procedures. The present paper seeks to explore two aspects of the current topic, namely how business professionals (using BELF) express disagreement during business negotiations, and whether mitigation strategies are used when disagreement is expressed. The findings suggest that disagreements are solely content-related and are expressed in a variety of ways as they are coupled with a varied use of mitigation devices (i.e. delay and added support). Furthermore, there were instances of unmitigated expressions in the form of blunt contradictions. It is suggested that disagreements in BELF negotiations are required actions and may serve a dual purpose. The main goal of expressing disagreement is to increase clarity in cases where essential information may be misinterpreted or misguided; additionally, it indicates the speaker’s stance in the argument. Lastly, as there is a need for better knowledge of successful BELF, the present study is likely to be of interest for those who are engaged in the global business discourse community as well as researchers studying international business settings.
42
Gul, Ahmet Bahtiyar. "Holistic Face Recognition By Dimension Reduction." Master's thesis, METU, 2003. http://etd.lib.metu.edu.tr/upload/1056738/index.pdf.
Full textAbstract:
Face recognition is a popular research area where there are different
approaches studied in the literature. In this thesis, a holistic Principal
Component Analysis (PCA) based method, namely Eigenface method is
studied in detail and three of the methods based on the Eigenface method
are compared. These are the Bayesian PCA where Bayesian classifier is
applied after dimension reduction with PCA, the Subspace Linear
Discriminant Analysis (LDA) where LDA is applied after PCA and
Eigenface where Nearest Mean Classifier applied after PCA. All the
three methods are implemented on the Olivetti Research Laboratory
(ORL) face database, the Face Recognition Technology (FERET)
database and the CNN-TURK Speakers face database. The results are
compared with respect to the effects of changes in illumination, pose and
aging. Simulation results show that Subspace LDA and Bayesian PCA
perform slightly well with respect to PCA under changes in posehowever, even Subspace LDA and Bayesian PCA do not perform well under changes in illumination and aging although they perform better than PCA.
43
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.
Full textAbstract:
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.
44
Joslin, Kelly L. "Art Appreciation in Face-to-Face and Online Settings: An Analysis of Course Effectiveness." University of Dayton / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1478709584805326.
Full text
45
Wei, Jianye. "Analysis and Characterisation of Interactions in Face-to-Face and Remote-Access Chemistry Laboratories." Thesis, Curtin University, 2019. http://hdl.handle.net/20.500.11937/79305.
Full textAbstract:
Laboratories have long been integral components in the undergraduate science curriculum. With the advancement of technologies, remote laboratories have been developed to complement or even replace some traditional face-to-face laboratories. This research investigated the process of learning in both face-to-face and remote laboratories by understanding interactions from the viewpoint of students, and their satisfaction levels. Findings from this research provide information for curriculum designers, laboratory instructors and students.
46
Plotnikov, Valeri. "An Analysis of Fare Collection Costs on Heavy Rail and Bus Systems in the U.S." Diss., Virginia Tech, 2001. http://hdl.handle.net/10919/29052.
Full textAbstract:
In this research, an effort is made to analyze the costs of fare collection on heavy rail and motorbus systems in the U.S. Since existing ticketing and fare collection (TFC) systems are major elements of transit infrastructure and there are several new alternative TFC technologies available on the market, the need to evaluate the performance of existing TFC systems arises. However, very little research has been done, so far, to assess impacts of TFC technologies on capital and operating expenses in public transit. The two objectives of this research are: (1) to formulate a conceptual evaluation framework and a plan to assess the operating costs of existing TFC systems in transit and (2) to analyze the operating expenses associated with existing TFC systems on heavy rail and motorbus transit in the U.S. with the aid of the evaluation framework and plan.
This research begins with a review of the current state of knowledge in the areas of transit TFC evaluation, the economics of public transit operations, and fare collection practices and technologies. It helps to determine the scope of work related to assessment of TFC operating costs on public transit and provides the basis for the development of a conceptual evaluation framework and an evaluation plan. Next, this research presents a systematic approach to define and describe alternative TFC systems and suggests that the major TFC system determinants are payment media, fare media, TFC equipment, and transit technology (mode). Following this is the development of measures of effectiveness to evaluate alternative TFC systems. These measures assess cost-effectiveness and labor-intensiveness of TFC operations. The development of TFC System Technology Index follows. This Index recognizes the fact that TFC systems may consist of different sets of TFC technologies both traditional and innovative. Finally, this research presents statistical results that support the hypothesis that TFC operating costs are related to transit demand, transit technology (mode) and TFC technologies. These results further suggest that: (1) TFC operating costs per unlinked passenger trip on heavy rail systems are higher than on motorbus systems and (2) TFC operating costs per unlinked passenger trip tend to increase as the use of non-electronic fare media increases. Actions for further research are also recommended.Ph. D.
47
Martínez, Brito Izacar Jesús. "Quantitative structure fate relationships for multimedia environmental analysis." Doctoral thesis, Universitat Rovira i Virgili, 2010. http://hdl.handle.net/10803/8590.
Full textAbstract:
Key physicochemical properties for a wide spectrum of chemical pollutants are unknown. This thesis analyses the prospect of assessing the environmental distribution of chemicals directly from supervised learning algorithms using molecular descriptors, rather than from multimedia environmental models (MEMs) using several physicochemical properties estimated from QSARs. Dimensionless compartmental mass ratios of 468 validation chemicals were compared, in logarithmic units, between: a) SimpleBox 3, a Level III MEM, propagating random property values within statistical distributions of widely recommended QSARs; and, b) Support Vector Regressions (SVRs), acting as Quantitative Structure-Fate Relationships (QSFRs), linking mass ratios to molecular weight and constituent counts (atoms, bonds, functional groups and rings) for training chemicals. Best predictions were obtained for test and validation chemicals optimally found to be within the domain of applicability of the QSFRs, evidenced by low MAE and high q2 values (in air, MAE≤0.54 and q2≥0.92; in water, MAE≤0.27 and q2≥0.92).Las propiedades fisicoquímicas de un gran espectro de contaminantes químicos son desconocidas. Esta tesis analiza la posibilidad de evaluar la distribución ambiental de compuestos utilizando algoritmos de aprendizaje supervisados alimentados con descriptores moleculares, en vez de modelos ambientales multimedia alimentados con propiedades estimadas por QSARs. Se han comparado fracciones másicas adimensionales, en unidades logarítmicas, de 468 compuestos entre: a) SimpleBox 3, un modelo de nivel III, propagando valores aleatorios de propiedades dentro de distribuciones estadísticas de QSARs recomendados; y, b) regresiones de vectores soporte (SVRs) actuando como relaciones cuantitativas de estructura y destino (QSFRs), relacionando fracciones másicas con pesos moleculares y cuentas de constituyentes (átomos, enlaces, grupos funcionales y anillos) para compuestos de entrenamiento. Las mejores predicciones resultaron para compuestos de test y validación correctamente localizados dentro del dominio de aplicabilidad de los QSFRs, evidenciado por valores bajos de MAE y valores altos de q2 (en aire, MAE≤0.54 y q2≥0.92; en agua, MAE≤0.27 y q2≥0.92).
48
Chen, Shaokang. "Robust discriminative principal component analysis for face recognition /." [St. Lucia, Qld.], 2005. http://www.library.uq.edu.au/pdfserve.php?image=thesisabs/absthe18934.pdf.
Full text
49
Martinkauppi, B. (Birgitta). "Face colour under varying illumination - analysis and applications." Doctoral thesis, University of Oulu, 2002. http://urn.fi/urn:isbn:9514267885.
Full textAbstract:
Abstract
The colours of objects perceived by a colour camera are dependent on the illumination conditions. For example, when the prevailing illumination condition does not correspond to the one used in the white balancing of the camera, the object colours can change their appearance due to the lack of colour constancy capabilities. Many methods for colour constancy have been suggested but so far their performance has been inadequate. Faces are common and important objects encountered in many applications. Therefore, this thesis is dedicated to studying face colours and their robust use under real world illumination conditions. The main thesis statement is "knowledge about an object's colour, like skin colour changes under different illumination conditions, can be used to develop more robust techniques against illumination changes".
Many face databases exist, and in some cases they contain colour images and even videos. However, from the point of view of this thesis these databases have several limitations: unavailability of spectral data related to image acquisition, undefined illumination conditions of the acquisition, and if illumination change is present it often means only change in illumination direction. To overcome these limitations, two databases, a Physics-Based Face Database and a Face Video Database were created. In addition to the images, the Physics-Based Face Database consists of spectral data part including skin reflectances, channel responsivities of the camera and spectral power distribution of the illumination. The images of faces are taken under four known light sources with different white balancing illumination conditions for over 100 persons. In addition to videos, the Face Video Database has spectral reflectances of skin for selected persons and images taken with the same measurement arrangement as in the Physics-Based Face Database. The images and videos are taken with several cameras.
The databases were used to gather information about skin chromaticities and to provide test material. The skin RGB from images were converted to different colour spaces and the result showed that the normalized colour coordinate was among the most usable colour spaces for skin chromaticity modelling. None of the colour spaces could eliminate the colour shifts in chromaticity. The obtained chromaticity constraint can be implemented as an adaptive skin colour modelling part of face tracking algorithms, like histogram backprojection or mean shift. The performances of these adaptive algorithms were superior compared to those using a fixed skin colour model or model adaptation based on spatial pixel selection. Of course, there are cases when the colour cue is not enough alone and use of other cues like motion or edge data would improve the result. It was also demonstrated that the skin colour model can be used to segment faces and the segmentation results depend on the background due to the method used. Also an application for colour correction using principal component analysis and a simplified dichromatic reflection model was shown to improve colour quality of seriously clipped images. The results of tracking, segmentation and colour correction experiments using the collected data validate the thesis statement.
50
Song, Qing. "Features and statistical classifiers for face image analysis." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0035/NQ62459.pdf.
Full text