Dissertations / Theses on the topic 'Biometric performance'

Biometrics is constantly evolving technology which has been widely used in many official and commercial identification applications. In fact in recent years biometric-based authentication techniques received more attention due to increased concerns in security. Most biometric systems that are currently in use typically employ a single biometric trait. Such systems are called unibiometric systems. Despite considerable advances in recent years, there are still challenges in authentication based on a single biometric trait, such as noisy data, restricted degree of freedom, intra-class variability, non-universality, spoof attack and unacceptable error rates. Some of the challenges can be handled by designing a multimodal biometric system. Multimodal biometric systems are those which utilize or are capable of utilizing, more than one physiological or behavioural characteristic for enrolment, verification, or identification. In this thesis, we propose a novel fusion approach at a hybrid level between iris and online signature traits. Online signature and iris authentication techniques have been employed in a range of biometric applications. Besides improving the accuracy, the fusion of both of the biometrics has several advantages such as increasing population coverage, deterring spoofing activities and reducing enrolment failure. In this doctoral dissertation, we make a first attempt to combine online signature and iris biometrics. We principally explore the fusion of iris and online signature biometrics and their potential application as biometric identifiers. To address this issue, investigations is carried out into the relative performance of several statistical data fusion techniques for integrating the information in both unimodal and multimodal biometrics. We compare the results of the multimodal approach with the results of the individual online signature and iris authentication approaches. This dissertation describes research into the feature and decision fusion levels in multimodal biometrics.

Abstract INDIVIDUAL-TECHNOLOGY FIT: MATCHING INDIVIDUAL CHARACTERISTICS AND FEATURES OF BIOMETRIC INTERFACE TECHNOLOGIES WITH PERFORMANCE By ADRIANE B. RANDOLPH MAY 2007 Committee Chair: Dr. Melody Moore Jackson Major Department: Computer Information Systems The term biometric literally means “to measure the body”, and has recently been associated with physiological measures commonly used for personal verification and security applications. In this work, biometric describes physiological measures that may be used for non-muscularly controlled computer applications, such as brain-computer interfaces. Biometric interface technology is generally targeted for users with severe motor disabilities which may last long-term due to illness or injury or short-term due to temporary environmental conditions. Performance with a biometric interface can vary widely across users depending upon many factors ranging from health to experience. Unfortunately, there is no systematic method for pairing users with biometric interface technologies to achieve the best performance. The current methods to accommodate users through trial-and-error result in the loss of valuable time and resources as users sometimes have diminishing abilities or suffer from terminal illnesses. This dissertation presents a framework and methodology that links user characteristics and features of biometric interface technologies with performance, thus expediting the technology-fit process. The contributions include an outline of the underlying components of capturing and representing individual user characteristics and the impact on the performance of basic interaction tasks using a methodology called biometric user profiling. In addition, this work describes a methodology for objectively measuring an individual’s ability to control a specific biometric interface technology such as one based on measures of galvanic skin response or neural activity. Finally, this work incorporates these concepts into a new individual-technology fit framework for biometric interface technologies stemming from literature on task-technology fit. Key words: user profiles, biometric user profiling, biometric interfaces, fit, individual-technology fit, galvanic skin response, functional near-infrared, brain-computer interface

Thesis (M.S. in Information Technology Management)--Naval Postgraduate School, December 2006.
Thesis Advisor(s): Alex Bordetsky. "December 2006." Includes bibliographical references (p. 71-74). Also available in print.

Thesis (Ph. D.)--Georgia State University, 2007.
Title from file title page. Melody Moore, committee chair; Detmar Straub, Veda Storey, Bruce Walker, committee members. Electronic text (166 p. : ill. (some col.)) : digital, PDF file. Description based on contents viewed Nov. 5, 2007. Includes bibliographical references (p. 160-164).

Kritickým prvkem biometrického systému pro rozpoznávání otisků prstů je proces snímání. Kvalita snímku totiž ovlivňuje všechny další části systému počínaje zpracováním obrazu, přes extrakci rysů až po samotné rozhodnutí. Přestože bylo navrženo několik metod určování kvality snímku, chybějící formální specifikace kvality otisku nedovoluje ověřit jejich přesnost. Tato diplomová práce se zabývá hodnocením metod určujících kvalitu biometrického signálu otisku prstu. Popisuje jednotlivé faktory ovlivňující kvalitu spolu se současnými přístupy používanými pro její odhad. V práci je rovněž vysvětlena evaluační technika navržená za účelem porovnání schopnosti jednotlivých metod předpovědět výkon biometrického systému. Několik metod pro odhad kvality bylo implementováno a ohodnoceno touto technikou.

We report on the design, implementation and performance issues of the DRUBIS (Distributed Rhodes University Biometric Identification System) experimentation framework. The Principal Component Analysis (PCA) face-recognition approach is used as a case study. DRUBIS is a flexible experimentation framework, distributed over a number of modules that are easily pluggable and swappable, allowing for the easy construction of prototype systems. Web services are the logical means of distributing DRUBIS components and a number of prototype applications have been implemented from this framework. Different popular PCA face-recognition related experiments were used to evaluate our experimentation framework. We extract recognition performance measures from these experiments. In particular, we use the framework for a more indepth study of the suitability of the DFFS (Difference From Face Space) metric as a means for image classification in the area of race and gender determination.

Ce travail de thèse explore l'usage biométrique de la parole dont les applications sont très nombreuses (sécurité, environnements intelligents, criminalistique, surveillance du territoire ou authentification de transactions électroniques). La parole est soumise à de nombreuses contraintes fonction des origines du locuteur (géographique, sociale et culturelle) mais également fonction de ses objectifs performatifs. Le locuteur peut être considéré comme un facteur de variation de la parole, parmi d'autres. Dans ce travail, nous présentons des éléments de réponses aux deux questions suivantes :- Tous les extraits de parole d'un même locuteur sont-ils équivalents pour le reconnaître ?- Comment se structurent les différentes sources de variation qui véhiculent directement ou indirectement la spécificité du locuteur ? Nous construisons, dans un premier temps, un protocole pour évaluer la capacité humaine à discriminer un locuteur à partir d'un extrait de parole en utilisant les données de la campagne NIST-HASR 2010. La tâche ainsi posée est difficile pour nos auditeurs, qu'ils soient naïfs ou plus expérimentés.Dans ce cadre, nous montrons que ni la (quasi)unanimité des auditeurs ni l'auto-évaluation de leurs jugements ne sont des gages de confiance dans la véracité de la réponse soumise.Nous quantifions, dans un second temps, l'influence du choix d'un extrait de parole sur la performance des systèmes automatiques. Nous avons utilisé deux bases de données, NIST et BREF ainsi que deux systèmes de RAL, ALIZE/SpkDet (LIA) et Idento (SRI). Les systèmes de RAL, aussi bienfondés sur une approche UBM-GMM que sur une approche i-vector montrent des écarts de performances importants mesurés à l'aide d'un taux de variation autour de l'EER moyen, Vr (pour NIST, VrIdento = 1.41 et VrALIZE/SpkDet = 1.47 et pour BREF, Vr = 3.11) selon le choix du fichier d'apprentissage utilisé pour chaque locuteur. Ces variations de performance, très importantes, montrent la sensibilité des systèmes automatiques au choix des extraits de parole, sensibilité qu'il est important de mesurer et de réduire pour rendre les systèmes de RAL plus fiables.Afin d'expliquer l'importance du choix des extraits de parole, nous cherchons les indices les plus pertinents pour distinguer les locuteurs de nos corpus en mesurant l'effet du facteur Locuteur sur la variance des indices (h2). La F0 est fortement dépendante du facteur Locuteur, et ce indépendamment de la voyelle. Certains phonèmes sont plus discriminants pour le locuteur : les consonnes nasales, les fricatives, les voyelles nasales, voyelles orales mi-fermées à ouvertes.Ce travail constitue un premier pas vers une étude plus précise de ce qu'est le locuteur aussi bien pour la perception humaine que pour les systèmes automatiques. Si nous avons montré qu'il existait bien une différence cepstrale qui conduisait à des modèles plus ou moins performants, il reste encore à comprendre comment lier le locuteur à la production de la parole. Enfin, suite à ces travaux, nous souhaitons explorer plus en détail l'influence de la langue sur la reconnaissance du locuteur. En effet, même si nos résultats indiquent qu'en anglais américain et en français, les mêmes catégories de phonèmes sont les plus porteuses d'information sur le locuteur, il reste à confirmer ce point et à évaluer ce qu'il en est pour d'autres langues

Com a popularização do uso da biometria, determinar a identidade de um indivíduo é uma atividade cada vez mais comum em diversos contextos: controle de acesso físico e lógico, controle de fronteiras, identificações criminais e forenses, pagamentos. Sendo assim, existe uma demanda crescente por Sistemas Automáticos de Identificação Biométrica (ABIS) cada vez mais rápidos, com elevada acurácia e que possam operar com um grande volume de dados. Este trabalho apresenta uma abordagem de implementação de uma central de confrontos para um ABIS de grande escala utilizando um framework de computação em memória. Foram realizados experimentos em uma base de dados real com mais de 50 milhões de impressões digitais em um cluster com até 16 nós. Os resultados mostraram a escalabilidade da solução proposta e a capacidade de operar em grandes bases de dados.
With the popularization of biometrics, personal identification is an increasingly common activity in several contexts: physical and logical access control, border control, criminal and forensic identification, payments. Thus, there is a growing demand for faster and accurate Automatic Biometric Identification Systems (ABIS) capable to handle a large volume of biometric data. This work presents an approach to implement a scalable cluster-based matching platform for a large-scale ABIS using an in-memory computing framework. We have conducted some experiments that involved a database with more than 50 million captured fingerprints, in a cluster up to 16 nodes. The results have shown the scalability of the proposed solution and the capability to handle a large biometric database.

The relevance of faces in our daily lives is indisputable. We learn to recognize faces as newborns, and faces play a major role in interpersonal communication. The spectrum of computer vision research about face analysis includes, but is not limited to, face detection and facial attribute classification, which are the focus of this dissertation. The face is a primary biometric because by itself revels the subject's identity, while facial attributes (such as hair color and eye state) are soft biometrics because by themselves they do not reveal the subject's identity. In this dissertation, we proposed a real-time model for classifying 40 facial attributes, which preprocesses faces and then extracts 7 types of classical and deep features. These features were fused together to train 3 different classifiers. Our proposed model yielded 91.93% on the average accuracy outperforming 7 state-of-the-art models. We also developed a real-time model for classifying the states of human eyes and mouth (open/closed), and the presence/absence of eyeglasses in the wild. Our method begins by preprocessing a face by cropping the regions of interest (ROIs), and then describing them using RootSIFT features. These features were used to train a nonlinear support vector machine for each attribute. Our eye-state classifier achieved the top performance, while our mouth-state and glasses classifiers were tied as the top performers with deep learning classifiers. We also introduced a new facial attribute related to Middle Eastern headwear (called igal) along with its detector. Our proposed idea was to detect the igal using a linear multiscale SVM classifier with a HOG descriptor. Thereafter, false positives were discarded using dense SIFT filtering, bag-of-visual-words decomposition, and nonlinear SVM classification. Due to the similarity in real-life applications, we compared the igal detector with state-of-the-art face detectors, where the igal detector significantly outperformed the face detectors with the lowest false positives. We also fused the igal detector with a face detector to improve the detection performance. Face detection is the first process in any facial attribute classification pipeline. As a result, we reported a novel study that evaluates the robustness of current face detectors based on: (1) diffraction blur, (2) image scale, and (3) the IoU classification threshold. This study would enable users to pick the robust face detector for their intended applications.
Doctor of Philosophy
The relevance of faces in our daily lives is indisputable. We learn to recognize faces as newborns, and faces play a major role in interpersonal communication. Faces probably represent the most accurate biometric trait in our daily interactions. Thereby, it is not singular that so much effort from computer vision researchers have been invested in the analysis of faces. The automatic detection and analysis of faces within images has therefore received much attention in recent years. The spectrum of computer vision research about face analysis includes, but is not limited to, face detection and facial attribute classification, which are the focus of this dissertation. The face is a primary biometric because by itself revels the subject's identity, while facial attributes (such as hair color and eye state) are soft biometrics because by themselves they do not reveal the subject's identity. Soft biometrics have many uses in the field of biometrics such as (1) they can be utilized in a fusion framework to strengthen the performance of a primary biometric system. For example, fusing a face with voice accent information can boost the performance of the face recognition. (2) They also can be used to create qualitative descriptions about a person, such as being an "old bald male wearing a necktie and eyeglasses." Face detection and facial attribute classification are not easy problems because of many factors, such as image orientation, pose variation, clutter, facial expressions, occlusion, and illumination, among others. In this dissertation, we introduced novel techniques to classify more than 40 facial attributes in real-time. Our techniques followed the general facial attribute classification pipeline, which begins by detecting a face and ends by classifying facial attributes. We also introduced a new facial attribute related to Middle Eastern headwear along with its detector. The new facial attribute were fused with a face detector to improve the detection performance. In addition, we proposed a new method to evaluate the robustness of face detection, which is the first process in the facial attribute classification pipeline. Detecting the states of human facial attributes in real time is highly desired by many applications. For example, the real-time detection of a driver's eye state (open/closed) can prevent severe accidents. These systems are usually called driver drowsiness detection systems. For classifying 40 facial attributes, we proposed a real-time model that preprocesses faces by localizing facial landmarks to normalize faces, and then crop them based on the intended attribute. The face was cropped only if the intended attribute is inside the face region. After that, 7 types of classical and deep features were extracted from the preprocessed faces. Lastly, these 7 types of feature sets were fused together to train three different classifiers. Our proposed model yielded 91.93% on the average accuracy outperforming 7 state-of-the-art models. It also achieved state-of-the-art performance in classifying 14 out of 40 attributes. We also developed a real-time model that classifies the states of three human facial attributes: (1) eyes (open/closed), (2) mouth (open/closed), and (3) eyeglasses (present/absent). Our proposed method consisted of six main steps: (1) In the beginning, we detected the human face. (2) Then we extracted the facial landmarks. (3) Thereafter, we normalized the face, based on the eye location, to the full frontal view. (4) We then extracted the regions of interest (i.e., the regions of the mouth, left eye, right eye, and eyeglasses). (5) We extracted low-level features from each region and then described them. (6) Finally, we learned a binary classifier for each attribute to classify it using the extracted features. Our developed model achieved 30 FPS with a CPU-only implementation, and our eye-state classifier achieved the top performance, while our mouth-state and glasses classifiers were tied as the top performers with deep learning classifiers. We also introduced a new facial attribute related to Middle Eastern headwear along with its detector. After that, we fused it with a face detector to improve the detection performance. The traditional Middle Eastern headwear that men usually wear consists of two parts: (1) the shemagh or keffiyeh, which is a scarf that covers the head and usually has checkered and pure white patterns, and (2) the igal, which is a band or cord worn on top of the shemagh to hold it in place. The shemagh causes many unwanted effects on the face; for example, it usually occludes some parts of the face and adds dark shadows, especially near the eyes. These effects substantially degrade the performance of face detection. To improve the detection of people who wear the traditional Middle Eastern headwear, we developed a model that can be used as a head detector or combined with current face detectors to improve their performance. Our igal detector consists of two main steps: (1) learning a binary classifier to detect the igal and (2) refining the classier by removing false positives. Due to the similarity in real-life applications, we compared the igal detector with state-of-the-art face detectors, where the igal detector significantly outperformed the face detectors with the lowest false positives. We also fused the igal detector with a face detector to improve the detection performance. Face detection is the first process in any facial attribute classification pipeline. As a result, we reported a novel study that evaluates the robustness of current face detectors based on: (1) diffraction blur, (2) image scale, and (3) the IoU classification threshold. This study would enable users to pick the robust face detector for their intended applications. Biometric systems that use face detection suffer from huge performance fluctuation. For example, users of biometric surveillance systems that utilize face detection sometimes notice that state-of-the-art face detectors do not show good performance compared with outdated detectors. Although state-of-the-art face detectors are designed to work in the wild (i.e., no need to retrain, revalidate, and retest), they still heavily depend on the datasets they originally trained on. This condition in turn leads to variation in the detectors' performance when they are applied on a different dataset or environment. To overcome this problem, we developed a novel optics-based blur simulator that automatically introduces the diffraction blur at different image scales/magnifications. Then we evaluated different face detectors on the output images using different IoU thresholds. Users, in the beginning, choose their own values for these three settings and then run our model to produce the efficient face detector under the selected settings. That means our proposed model would enable users of biometric systems to pick the efficient face detector based on their system setup. Our results showed that sometimes outdated face detectors outperform state-of-the-art ones under certain settings and vice versa.

Voice recognition has become a more focused and researched field in the last century,and new techniques to identify speech has been introduced. A part of voice recognition isspeaker verification which is divided into Front-end and Back-end. The first componentis the front-end or feature extraction where techniques such as Mel-Frequency CepstrumCoefficients (MFCC) is used to extract the speaker specific features of a speech signal,MFCC is mostly used because it is based on the known variations of the humans ear’scritical frequency bandwidth. The second component is the back-end and handles thespeaker modeling. The back-end is based on the Gaussian Mixture Model (GMM) andGaussian Mixture Model-Universal Background Model (GMM-UBM) methods forenrollment and verification of the specific speaker. In addition, normalization techniquessuch as Cepstral Means Subtraction (CMS) and feature warping is also used forrobustness against noise and distortion. In this paper, we are going to build a speakerverification system and experiment with a variance in the amount of training data for thetrue speaker model, and to evaluate the system performance. And further investigate thearea of security in a speaker verification system then two methods are compared (GMMand GMM-UBM) to experiment on which is more secure depending on the amount oftraining data available.This research will therefore give a contribution to how much data is really necessary fora secure system where the False Positive is as close to zero as possible, how will theamount of training data affect the False Negative (FN), and how does this differ betweenGMM and GMM-UBM.The result shows that an increase in speaker specific training data will increase theperformance of the system. However, too much training data has been proven to beunnecessary because the performance of the system will eventually reach its highest point and in this case it was around 48 min of data, and the results also show that the GMMUBM model containing 48- to 60 minutes outperformed the GMM models.

With the usage of biometrics becoming commonly used in a variety of applications, keeping those biometrics private and secure is an important issue. Indeed, the convenience of using biometrics for authentication is counteracted by the fact that they cannot easily be modified or changed. This can have dire consequences to a person if their biometrics are leaked. In the past decades, various techniques have been proposed to solve this problem. Such techniques range from using and storing randomized templates, using homomorphic encryption, or using biometric encryption techniques such as fuzzy extractors. Fuzzy extractors are a construction that allows the extraction of cryptographic keys from noisy data like biometrics. The key can then be rebuilt from some helper data and another biometric, provided that it is similar enough to the biometrics used to generate the key. This can be achieved through various approaches like the use of a quantizer or an error correcting code. In this thesis, we consider specifically fuzzy extractors for facial images. The first part of this thesis focuses on improving the security, privacy and performance of the extractor for faces first proposed by Sutcu et al. Our improvements make their construction more resistant to partial and total leaks of secure information, as well as improve the performance in a biometric authentication setting. The second part looks at using low density lattice codes (LDLC) as a quantizer in the fuzzy extractor, instead of using component based quantization. Although LDLC have been proposed as a quantizer for a general fuzzy extractor, they have yet to be used or tested for continuous biometrics like face images. We present a construction for a fuzzy extractor scheme using LDLC and we analyze its performance on a publicly available data set of images. Using an LDLC quantizer on this data set has lower accuracy than the improved scheme from the first part of this thesis. On the other hand, the LDLC scheme performs better when the inputs have additive white Gaussian noise (AWGN), as we show through simulated data. As such, we expect it to perform well in general on data and biometrics with variance akin to a AWGN channel.

The increasing prevalence of myopia over the past few decades and its association with potential ocular complications make myopia an important research topic. The present work is concerned with the structural and functional characteristics of a group of myopic and emmetropic individuals. The technical experiments in this work investigated firstly the effect of instrument alignment on peripheral refraction measurements and revealed that the corneal vertex was an acceptable alignment position of the Shin-Nippon NVision-K 5001 autorefractor, allowing consistent alignment with other instruments used in this research. Secondly, spectacles could be used to provide comparable vision to contact lenses in the visual performance studies. In the main experimental parts of this work, visual performance and multiple aspects of ocular structure were assessed across a wide range of eccentricities along the horizontal and vertical meridians within the same eyes. The structural properties of the myopic eye were measured through central and peripheral autorefraction, and through cornea to retina dimensions using non-contact biometry. In addition, the central and peripheral resolution acuities of myopic and emmetropic eyes for high and low contrast levels were investigated. Our structural and functional measurements revealed relatively prolate myopic eyes with reduced high contrast resolution acuity, compared to emmetropic eyes. Moreover, multiple regression analyses were performed at the fovea and outermost retinal eccentricities common to all core experiments but revealed no strong relationship between the structure and function of the myopic eye. Finally, regarding asymmetry, the nasal and superior retinae were found to be longer and to perform better in comparison to the temporal and superior retinae respectively.

CHAPTER 2: The objective of this research was to evaluate the effects of fasting time on bromatology carcass, biometrics organ, water intake and performance of broiler chickens. We conducted a randomized design consisting of four days of fasting after hatching (0, 12, 24 and 36 hours) and four replications. Therefore, 640 birds were distributed in sixteen boxes containing 20 females and 20 males each. Water consumption was greater the longer the duration of fasting and was greater weight loss from hatching to the accommodation. There was also the weight loss on the yolk sac. Fasting influenced the relative weight of all organs of the digestive tract except esophagus + craw that remained unchanged. With increasing fasting time increased the relative weight of the esophagus+craw, proventriculus+gizzard, intestine+ pancreas, intestine and liver+gallbladder. However, food science and animal performance were not affected by fasting. CHAPTER 3: The objective of this research was to evaluate the effect of maltodextrin on performance and biometry of the digestive organs in chicks underwent four fasting time. Was performed a completely randomized design consisting of three treatments (1 - control, 2 - 4% sugar; 3-4% maltodextrin 20) and four times of fasting after hatching (0, 12, 24 and 36 hours) with four replications , 1920 birds in total of both sexes. The results showed that both the maltodextrin as sugar stimulated the consumption of water and after 24 hours, the group that has not been pass of fasting and was approved with maltodextrin obtained with greater weight of the small intestine and pancreas, besides a greater length of the gastrointestinal tract. The performance at 42 days was not influenced by the use of additives, however, the viability suffered positive influence after seven days of life.
CAPÍTULO 2: Objetivou-se com esta pesquisa avaliar os efeitos do tempo de jejum sobre a bromatologia da carcaça, biometria dos órgãos, consumo de água e desempenho zootécnico de frangos de corte. Foi realizado um delineamento inteiramente casualizado composto por quatro períodos de jejum pós-eclosão (0, 12, 24 e 36 horas) e quatro repetições. Para tanto, 640 aves foram distribuídas em dezesseis boxes, contendo 20 fêmeas e 20 machos cada. O consumo de água foi maior quanto maior o tempo de jejum, e maior foi à perda de peso desde a eclosão até o alojamento. Ocorreu também a perda de peso relativo do saco vitelino. O jejum influenciou o peso relativo de todos os órgãos do trato digestivo, exceto esôfago+papo que permaneceram inalterados. Com o aumento do tempo de jejum aumentou o peso relativo do esôfago+papo, proventrículo+moela, intestino delgado+pâncreas, intestino grosso e fígado+vesícula biliar. No entanto, a bromatologia e o desempenho zootécnico não foram influenciados pelo jejum. CAPÍTULO 3: Objetivou-se com esta pesquisa avaliar o efeito da maltodextrina sobre o desempenho zootécnico e biometria dos órgãos digestivos em pintainhos submetidos a quatro períodos de jejum. Foi executado um delineamento experimental inteiramente casualizado composto por três tratamentos (1 controle; 2 4% de açúcar; 3 4% de maltodextrina 20) e quatro tempos de jejum póseclosão (0, 12, 24 e 36 horas) com quatro repetições, contendo no total 1920 aves de ambos os sexos. Os resultados mostraram que tanto a maltodextrina quanto o açúcar estimularam o consumo de água e depois de 24 horas o grupo que não sofreu jejum e foi recepcionado com maltodextrina obteve maior peso de intestino delgado e pâncreas, além de maior comprimento do trato gastrintestinal. O desempenho zootécnico aos 42 dias não foi influenciado pela utilização de aditivo, no entanto, a viabilidade sofreu influencia positiva aos sete dias de vida.
Mestre em Ciências Veterinárias

It has been noticed for a long time that humans can identify others based on their biological movement from a distance. However, it is only recently that computer vision based gait biometrics has received much attention. In this dissertation, we perform a thorough study of gait recognition from a computer vision perspective. We first present a parameterless baseline recognition algorithm, which bases similarity on spatio-temporal correlation that emphasizes gait dynamics as well as gait shapes. Our experiments are performed with three popular gait databases: the USF/NIST HumanID Gait Challenge outdoor database with 122 subjects, the UMD outdoor database with 55 subjects, and the CMU Mobo indoor database with 25 subjects. Despite its simplicity, the baseline algorithm shows strong recognition power. On the other hand, the outcome suggests that changes in surface and time have strong impact on recognition with significant drop in performance. To gain insight into the effects of image segmentation on recognition -- a possible cause for performance degradation, we propose a silhouette reconstruction method based on a Population Hidden Markov Model (pHMM), which models gait over one cycle, coupled with an Eigen-stance model utilizing the Principle Component Analysis (PCA) of the silhouette shapes. Both models are built from a set of manually created silhouettes of 71 subjects. Given a sequence of machine segmented silhouettes, each frame is matched into a stance by pHMM using the Viterbi algorithm, and then is projected into and reconstructed by the Eigen-stance model. We demonstrate that the system dramatically improves the silhouette quality. Nonetheless, it does little help for recognition, indicating that segmentation is not the key factor of the covariate impacts. To improve performance, we look into other aspects. Toward this end, we propose three recognition algorithms: (i) an averaged silhouette based algorithm that deemphasizes gait dynamics, which substantially reduces computation time but achieves similar recognition power with the baseline algorithm; (ii) an algorithm that normalizes gait dynamics using pHMM and then uses Euclidean distance between corresponding selected stances -- this improves recognition over surface and time; and (iii) an algorithm that also performs gait dynamics normalization using pHMM, but instead of Euclidean distances, we consider distances in shape space based on the Linear Discriminant Analysis (LDA) and consider measures that are invariant to morphological deformation of silhouettes. This algorithm statistically improves the recognition over all covariates. Compared with the best reported algorithm to date, it improves the top-rank identification rate (gallery size: 122 subjects) for comparison across hard covariates: briefcase, surface type and time, by 22%, 14%, and 12% respectively. In addition to better gait algorithms, we also study multi-biometrics combination to improve outdoor biometric performance, specifically, fusing with face data. We choose outdoor face recognition, a "known" hard problem in face biometrics, and test four combination schemes: score sum, Bayesian rule, confidence score sum, and rank sum. We find that the recognition power after combination is significantly stronger although individual biometrics are weak, suggesting another effective approach to improve biometric recognition. The fundamental contributions of this work include (i) establishing the "hard" problems for gait recognition involving comparison across time, surface, and briefcase carrying conditions, (ii) revealing that their impacts cannot be explained by silhouette segmentation, (iii) demonstrating that gait shape is more important than gait dynamics in recognition, and (iv) proposing a novel gait algorithm that outperforms other gait algorithms to date.

Hohenheim, Univ., Diss., 2005.
Aus: Congruency of quantitative trait loci detected for agronomic traits in testcrosses of five populations of European maize.2004.Crop Sci. 44:114-124. and QTL correspondence between line per se and testcross performance for agronomic traits in four populations of European maize.Crop Sci. 45:114-122.

Les organismes font face à des compromis entre leur reproduction, leur maintenance et leur survie, dont découlent des stratégies adaptatives énergétiques, comportementales et écologiques.Ce travail de thèse propose de préciser les stratégies de reproduction chez la tortue luth Dermochelys coriacea nidifiant en Guyane. Nous avons étudié les caractéristiques maternelles, les performances de reproduction et les potentiels liens existants entre la migration et la reproduction chez une population d'individus d'identité connue, suivis grâce à un suivi longitudinal original combinant biométrie, physiologie et biologie moléculaire.Premièrement nous montrons que les tortues luth opèrent comme des reproducteurs sur capital, i.e., leur reproduction repose sur les ressources stockées sous forme de réserves corporelles pendant la migration précédant la saison de ponte. D'autre part, nous suggérons que les femelles ajustent la durée de leur migration en fonction des conditions océanographiques rencontrées pendant la migration. Ceci leur permettrait, à l'échelle de la vie, de répondre au compromis entre la reproduction en cours et les reproductions futures. Enfin, notre démarche souligne l'importance de prendre en compte les caractéristiques individuelles dans la compréhension des stratégies de reproduction, et de manière ultime pour l'établissement de modèles réalistes de la dynamique des populations, notamment dans le cas d'espèces emblématiques telles que les tortues marines.

In this study, any change in fingerprint performance, image quality and minutiae count for infants in three different age groups was evaluated (0-6, 7-12, and >12 months). This was done to determine whether there is a difference in performance between infant age groups for a fingerprint recognition system.

The purpose of this research was to determine whether there is a difference in infant fingerprint performance and image quality metrics, between three different age groups (0-6, 7-12, and >12 months old), using the same optical sensor? The data used for this secondary analysis was collected as part of a longitudinal multimodal infant study, using the Digital Persona U.are.U 4500. DET curves, zoo analysis, and image quality metrics were used to evaluate performance and quality factored by infant age group.

This study found that there was a difference in image quality and minutiae count, genuine and impostor match scores, and performance error rates (EER) between the three age groups. Therefore, quality and performance were dependent on age. While there was a difference in performance between age groups, there was generally stability for subjects who overlapped between multiple age groups. Difference in performance was most likely due to the difference in physical characteristics between subjects in each age group, rather than individual instability. The results showed that it could potentially be feasible to use fingerprint recognition for children over the age of 12 months.

碩士
國立臺灣科技大學
資訊工程系
96
In a multimodal biometric system, the effective fusion method is necessary for combining information from various single modality systems. In this paper we examined the performance of sum rule-based score level fusion and Support Vector Machines (SVM)-based score level fusion. Three biometric characteristics were considered in this study: fingerprint, face, and finger vein. We also proposed a new robust normalization scheme which is derived from min-max normalization scheme. Experiments on four different multimodal databases suggest that integrating the proposed scheme in sum rule-based fusion and SVM-based fusion leads to consistently high accuracy. The performance of simple sum rule preceded by our normalization scheme is comparable to another approach which is based on the estimation of matching scores densities. Comparison between experimental results on sum rule-based fusion and SVM-based fusion reveals that SVM-based fusion could attain better performance compared to sum rule-based fusion, provided that the kernel and its parameters have been carefully selected.

M.Phil. (Electrical And Electronic Engineering)
The enormous increase in technology advancement and the need to secure information e ectively has led to the development and implementation of iris image acquisition technologies for automated iris recognition systems. The iris biometric is gaining popularity and is becoming a reliable and a robust modality for future biometric security. Its wide application can be extended to biometric security areas such as national ID cards, banking systems such as ATM, e-commerce, biometric passports but not applicable in forensic investigations. Iris recognition has gained valuable attention in biometric research due to the uniqueness of its textures and its high recognition rates when employed on high biometric security areas. Identity veri cation for individuals becomes a challenging task when it has to be automated with a high accuracy and robustness against spoo ng attacks and repudiation. Current recognition systems are highly a ected by noise as a result of segmentation failure, and this noise factors increase the biometric error rates such as; the FAR and the FRR. This dissertation reports an investigation of score level fusion methods which can be used to enhance iris matching performance. The fusion methods implemented in this project includes, simple sum rule, weighted sum rule fusion, minimum score and an adaptive weighted sum rule. The proposed approach uses an adaptive fusion which maps feature quality scores with the matcher. The fused scores were generated from four various iris matchers namely; the NHD matcher, the WED matcher, the WHD matcher and the POC matcher. To ensure homogeneity of matching scores before fusion, raw scores were normalized using the tanh-estimators method, because it is e cient and robust against outliers. The results were tested against two publicly available databases; namely, CASIA and UBIRIS using two statistical and biometric system measurements namely the AUC and the EER. The results of these two measures gives the AUC = 99:36% for CASIA left images, the AUC = 99:18% for CASIA right images, the AUC = 99:59% for UBIRIS database and the Equal Error Rate (EER) of 0.041 for CASIA left images, the EER = 0:087 for CASIA right images and with the EER = 0:038 for UBIRIS images.

Psychologists have used biometric data since the early 1900s to analyze the emotional responses of such subjects as students, patients with autism, and adults suffering from stress. Biometric data, the recording of physiological responses such as galvanic skin response, heart rate, and eye blinking frequency, shows peaks in emotional response to stimuli in a human’s environment. Galvanic skin response (GSR) is the most potent form of biometric data used for the study of emotional arousal. GSR, if studied in tandem with stimuli, can help researchers identify events in a subject’s environment that trigger emotion. GSR has been used to analyze responses to performance arts, but these studies are typically performed in controlled environments using video-taped performances and not under live performance conditions. Furthermore, this research is more often conducted using dance and not theatre, and often the material studied is less than ½ hour in length. This study combines techniques from several prominent studies of GSR for performing arts response research and applies them to the analysis of a 1 and ½ hour theatrical performance. GSR data is collected from six audience members during live performances of this theatrical work and the subjects are interviewed based on their galvanic skin response recorded during the play. The results of the analysis and interviews are reported to the director and design team of the play in order to inform them of the emotional impact of their work. Such information holds the potential to inform the creative team’s future play-making processes.
text

In recent times, there has been an increase in national security awareness with a focus on improving current practices relating to the identification and verification of individuals and the reduction of identity fraud. One tool that has been found to assist in these areas is biometrics. This thesis examines some biometric technologies that may be potentially suitable for surveillance and access control applications, and shows why facial recognition technology has been the focus of this study. Despite the testing reported in the literature discussing attempts to solve the problems with facial recognition operational performance, facial recognition has not been widely implemented in security applications to date. The reported testing regimes vary in terms of the date of testing, methodology used for the study, evaluation type, test size and the extent to which possible variations of each variable were examined. To summarise what is known about the effect each variable has on performance, a baseline model of variables together with a ranking scheme is defined and utilised to create a starting point for the research. The research described in this thesis focuses on how to improve the operational performance of two dimensional facial recognition systems by building upon the baseline model of variables and by better understanding how the variables affect facial recognition performance. To improve on the baseline model, systems engineering techniques are used to identify the functional components of a generic facial recognition system, the relationships between them, and the variables that affect those relationships. This identifies other variables that may affect performance. In order to determine which variables affect performance, and how, a series of technical, scenario and operational experiments are conducted to test a selection of the variables. It is shown that this results in a greater understanding of how facial recognition systems react to different variables in operational environments. A revised model of ranked variables is produced that can then be used by current and prospective stakeholders of biometric systems, system designers, integrators and testers to ensure that the majority of the variables are considered when designing, installing, commissioning, or testing facial recognition systems. The findings of this research can also be used to critically analyse existing facial recognition system implementations in order to identify areas where performance increases are possible. This is confirmed in part throughout the two year testing phase of this research where data collected from initial experiments were used as a starting point to improve the performance of later operational experiments. Finally, this thesis identifies that the revised model of variables is sufficiently generic to be used as a starting point for analysing a system using any biometric technology. This is supported by using iris recognition technology as a test case. It is anticipated that with an increased knowledge of how some systems are affected by certain variables, and by better controlling those variables, an increase in performance is possible for access control and surveillance security applications that utilise biometric technologies.
thesis (PhDElectronicSystemsEngineering)--University of South Australia, 2005.

The objective of this thesis was to compare biometrical and slaughtering indicators of common carp crossbreeds using two different breeds of Amur mirror carp in performance testing. We applied top-crossing for the test establishment, using the Hungarian mirror carp (M2) on the maternal position. Males of Hungarian mirror carp (for the production of purebreed), Northern mirror carp (M72) and two breeds of Amur mirror carp (ALP ? bred in Pohořelice, ALV ? bred in Vodňany) were crossed on this breed and hybrids of scaly phenotype between Ropsha (ROP) and Tata carp (TAT) were used as a control group. The performance testing started in ponds (in the total of five localities) in the semi ? intensive way of management by releasing yolk sac fry (K0) and its subsequent rearing to the market size (K3). The performance test was completed in ponds after the third year of testing and the tested groups of fish were evaluated for biometrical and slaughtering indicators. In the overall evaluation of the edible parts of the body (processed body and fillets) by the ANCOVA method was not found a statistical difference among the mirror tested groups of fish. The only exception was the proportion of fillets without skin, which was significantly higher in the hybrid M2 x ALP than in breed M2, therefore I would not recommend this breed (M2) to commercial breeding. When comparing my results with other publications, the hybrid M2 x M72 could be used for commercial breeding together with the two hybrids of Amur mirror carp, who not only achieve high yield of edible parts of the body, but also the earlier tests confirmed higher growth, better survival and resistance to the KHV virus.

Dissertação de mestrado em Informatics Engineering
The gaming industry has undergone some changes with the investments and professionalization of the sector, changing the way of playing video games from traditional leisure to be like a sportsman job. There are currently organized multiplayer video games competitions with professional players, know as Electronic Sports (Esports). These professional video games players can be compared to athletes once they’re part of a team and with training, their performance can be improved as well as, given certain factors, conditioned. The emergence of team coaches was naturally introduced, and he’s responsible for optimizing team performance. Due to this fact, arises the need to develop tools with the aim of improving the performance of these professional players as well as increasing the duration of their careers by taking care of their physical and mental health. It was proposed for this study the development of a Performance Optimization and Reporting Platform for Esports to help the coaches and players, continuously and automatically collecting their behavioral states and reporting the obtained results in order to guide the training to improve individual and team performance. This platform was tested in a real environment, with professional teams as a case study, where it was possible to analyze the impact of mental fatigue and behavioral biometric performance on devices interaction in players’ game results.
A indústria de jogos de video eletrónicos sofreu algumas alterações com investimentos e profissionalização do setor, mudando o modo de tradicional lazer a jogar para um trabalho similar a um atleta. Atualmente, há competições organizadas, de jogos eletrónicos multijogador, com jogadores profissionais, conhecidas como Esports. Esses jogadores profissionais podem ser comparados com atletas, uma vez que fazem parte de uma equipa e o seu desempenho pode ser melhorado com treino e condicionado através de determinados fatores. O surgimento de treinadores de equipa foi naturalmente introduzido sendo ele responsável por otimizar o desempenho da equipa. Devido a estes factos, surge a necessidade de desenvolver ferramentas com o objetivo de melhorar o desempenho desses profissionais, bem como aumentar a duração de suas carreiras, cuidando de sua saúde física e mental. Foi proposto para este estudo o desenvolvimento de uma Plataforma de otimização de desempenhos e relatórios para Esports para auxiliar os treinadores e jogadores, recolhendo de forma contínua e automática os seus estados comportamentais e reportando os resultados obtidos, com a finalidade de orientar o treino para melhorar o desempenho individual e de equipa. A plataforma foi testada em ambiente real, com equipas profissionais como caso de estudo, onde foi possível analisar o impacto da fadiga mental e do desempenho biométrico comportamental na interação em dispositivos nos resultados dos jogos dos jogadores.