Cette thèse porte sur la modélisation et vérification des signatures en ligne. La première partie a pour thème principal la modélisation biomécanique des mouvements de la main. Un modèle basé sur le critère de Minimum de Secousse (MS) a été choisi parmi plusieurs théories du contrôle moteur. Ensuite, le problème de la segmentation des trajectoires en traits qui correspondent au modèle cinématique choisi a été étudié, ce qui a conduit à la mise au point d'une méthode de segmentation itérative. Le choix du modèle et de la méthode de segmentation sont basé sur le compromis entre la qualité de reconstruction et la compression. Dans la deuxième partie, le modèle polynomial issu du critère de MS est volontairement dégradé. Les zéros non-Réels des polynômes sont jetés et les effets de cette dégradation sont étudiés dans une perspective de vérification biométrique. Cette dégradation est équivalente à la technique connue sous le nom d’Infinity Clipping, initialement appliqué à des signaux de parole. Pour les signatures en ligne, comme pour la parole, la préservation de l'information essentielle a été observée sur des tâches de vérification de signature. En fait, en utilisant seulement la distance de Levenshtein sur la représentation dégradée, un taux d'erreur comparable à ceux des méthodes plus élaborées a été obtenu. En outre, la représentation symbolique issue de l’Infinity Clipping permet d’établir une relation conceptuelle entre le nombre de segments obtenus par la segmentation itératif basée sur le MS et la complexité de Lempel-Ziv. Cette relation est potentiellement utile pour l'analyse des signatures en ligne et pour l’amélioration des systèmes de reconnaissance / This thesis deals with the modelling and verification of online signatures. The first part has as main theme the biomechanical modelling of hand movements associated to the signing gesture. A model based on the Minimum Jerk (MJ) criterion was chosen amongst the several available motor control theories. Next, the problem of signature trajectory segmentation into strokes that better fit the chosen kinematic model is studied, leading to the development of an iterative segmentation method. Both the choice of the model and the segmentation method are strongly based on the tradeoff between reconstruction quality and compression. On the second part, the polynomial model provided by the MJ criterion is intentionally degraded. The non-Real zeroes of the polynomials are discarded and the effects of this degradation are studied from a biometric verification perspective. This degradation is equivalent to the signal processing technique known as Infinity Clipping, originally applied to speech signals. On signatures, as for speech, the preservation of essential information was observed on signature verification tasks. As a matter of fact, using only the Levenshtein distance over the infinitely clipped representation, verification error rates comparable to those of more elaborate methods were obtained. Furthermore, the symbolic representation yielded by the infinity clipping technique allows for a conceptual relationship between the number of polynomial segments obtained through the Minimum Jerk-Based iterative segmentation and the Lempel-Ziv complexity. This relationship is potentially useful for the analysis of online signature signals and the improvement of recognition systems

We present a theory for constructing linear, black box approximations to face recognition algorithms and empirically demonstrate that a surprisingly diverse set of face recognition approaches can be approximated well using a linear model. The construction of the linear model to a face recognition algorithm involves embedding of a training set of face images constrained by the distances between them, as computed by the face recognition algorithm being approximated. We accomplish this embedding by iterative majorization, initialized by classical multi-dimensional scaling (MDS). We empirically demonstrate the adequacy of the linear model using six face recognition algorithms, spanning both template based and feature based approaches on standard face recognition benchmarks such as the Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. The experimental results show that the average Error in Modeling for six algorithms is 6.3% at 0.001 False Acceptance Rate (FAR), for FERET fafb probe set which contains maximum number of subjects among all the probe sets. We demonstrate the usefulness of the linear model for algorithm dependent indexing of face databases and find that it results in more than 20 times reduction in face comparisons for Bayesian Intra/Extra-class person classifier (BAY), Elastic Bunch Graph Matching algorithm (EBGM), and the commercial face recognition algorithms. We also propose a novel paradigm to reconstruct face templates from match scores using the linear model and use the reconstructed templates to explore the security breach in a face recognition system. We evaluate the proposed template reconstruction scheme using three, fundamentally different, face recognition algorithms: Principal Component Analysis (PCA), Bayesian Intra/Extra-class person classifier (BAY), and a feature based commercial algorithm. With an operational point set at 1% False Acceptance Rate (FAR) and 99% True Acceptance Rate (TAR) for 1196 enrollments (FERET gallery), we show that at most 600 attempts (score computations) are required to achieve 73%, 72% and 100% chance of breaking in as a randomly chosen target subject for the commercial, BAY and PCA based face recognition system, respectively. We also show that the proposed reconstruction scheme has 47% more probability of breaking in as a randomly chosen target subject for the commercial system as compared to a hill climbing approach with the same number of attempts.

自從美國911恐怖攻擊事件後，生物辨識技術受到世界各國重視，使得生物辨識應用大鳴大放，涵蓋範圍非常廣泛，從國家的入出境管理、國民身分證，到公司或住家的門禁管理、安全監控，乃至於個人身分確認，如電腦開機登錄、隨身碟資料加密。然而生物辨識應用，會涉及個人生物特徵之蒐集與相關個人資料之運用，一方面為生活上帶來便利，另一面也無聲無息為個人隱私帶來衝擊與威脅。本文從生物辨識技術之研究，藉由分析指紋辨識、臉型辨識及DNA辨識之應用所引發的隱私權問題，以及相關法令規範之探討，最後從法制面、政策面與執行面上提供建議，希望藉由完備的法令規範，評估各種應用可能引發之隱私爭議，建立完善的管理制度與監督機制，將生物辨識應用之隱私侵害與疑慮降到最低，得以享受生物辨識應用所帶來的安全性與方便性。

Face verification is a challenging pattern recognition problem. The face is a biometric that, we as humans, know can be recognised. However, the face is highly deformable and its appearance alters significantly when the pose, illumination or expression changes. These changes in appearance are most notable for texture images, or two-dimensional (2D) data. But the underlying structure of the face, or three dimensional (3D) data, is not changed by pose or illumination variations. Over the past five years methods have been investigated to combine 2D and 3D face data to improve the accuracy and robustness of face verification. Much of this research has examined the fusion of a 2D verification system and a 3D verification system, known as multi-modal classifier score fusion. These verification systems usually compare two feature vectors (two image representations), a and b, using distance or angular-based similarity measures. However, this does not provide the most complete description of the features being compared as the distances describe at best the covariance of the data, or the second order statistics (for instance Mahalanobis based measures). A more complete description would be obtained by describing the distribution of the feature vectors. However, feature distribution modelling is rarely applied to face verification because a large number of observations is required to train the models. This amount of data is usually unavailable and so this research examines two methods for overcoming this data limitation: 1. the use of holistic difference vectors of the face, and 2. by dividing the 3D face into Free-Parts. The permutations of the holistic difference vectors is formed so that more observations are obtained from a set of holistic features. On the other hand, by dividing the face into parts and considering each part separately many observations are obtained from each face image; this approach is referred to as the Free-Parts approach. The extra observations from both these techniques are used to perform holistic feature distribution modelling and Free-Parts feature distribution modelling respectively. It is shown that the feature distribution modelling of these features leads to an improved 3D face verification system and an effective 2D face verification system. Using these two feature distribution techniques classifier score fusion is then examined. This thesis also examines methods for performing classifier fusion score fusion. Classifier score fusion attempts to combine complementary information from multiple classifiers. This complementary information can be obtained in two ways: by using different algorithms (multi-algorithm fusion) to represent the same face data for instance the 2D face data or by capturing the face data with different sensors (multimodal fusion) for instance capturing 2D and 3D face data. Multi-algorithm fusion is approached as combining verification systems that use holistic features and local features (Free-Parts) and multi-modal fusion examines the combination of 2D and 3D face data using all of the investigated techniques. The results of the fusion experiments show that multi-modal fusion leads to a consistent improvement in performance. This is attributed to the fact that the data being fused is collected by two different sensors, a camera and a laser scanner. In deriving the multi-algorithm and multi-modal algorithms a consistent framework for fusion was developed. The consistent fusion framework, developed from the multi-algorithm and multimodal experiments, is used to combine multiple algorithms across multiple modalities. This fusion method, referred to as hybrid fusion, is shown to provide improved performance over either fusion system on its own. The experiments show that the final hybrid face verification system reduces the False Rejection Rate from 8:59% for the best 2D verification system and 4:48% for the best 3D verification system to 0:59% for the hybrid verification system; at a False Acceptance Rate of 0:1%.

Orientador: Aparecido Nilceu Elias / Banca: Agma Juci Machado Traina / Banca: Wilson Massashiro Yonezawa / Resumo: Nos últimos anos tem sido observado um crescimento exponencial na oferta de cursos a distância realizados pela Internet, decorrente de suas vantagens e características (menores custos de distribuição e atualização de conteúdo, gerenciamento de grandes turmas, aprendizado assíncrono e geograficamente independente, etc.), bem como de sua regulamentação e apoio governamental. Entretanto, a falta de mecanismos eficazes para assegurar a autenticação dos alunos neste tipo de ambiente é apontada como uma séria deficiência, tanto no acesso ao sistema quanto durante a participação do usuário nas atividades do curso. Atualmente, a autenticação baseada em senhas continua predominante. Porém, estudos têm sido conduzidos sobre possíveis aplicações da Biometria para autenticação em ambientes Web. Com a popularização e conseqüente barateamento de hardware habilitado para coleta biométrica (como webcams, microfone e leitores de impressão digital embutidos), a Biometria passa a ser considerada uma forma segura e viável de autenticação remota de indivíduos em aplicações Web. Baseado nisso, este trabalho propõe uma arquitetura distribuída para um ambiente de e-Learning, explorando as propriedades de um sistema Web para a autenticação biométrica tanto no acesso ao sistema quanto de forma contínua, durante a realização do curso. Para análise desta arquitetura, é avaliada a performance de técnicas de reconhecimento de faces a partir de vídeo capturadas on-line por uma webcam em um ambiente de Internet, simulando a interação natural de um indivíduo em um sistema de e- Learning. Para este fim, foi criada uma base de dados de vídeos própria, contando com 43 indivíduos navegando e interagindo com páginas Web. Os resultados obtidos mostram que os métodos analisados, consolidados na literatura, podem ser aplicados com sucesso nesse tipo de aplicação... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: In the last years it has been observed an exponential growth in the offering of Internet-enabled distance courses, due to its advantages and features (decreased distribution and content updates costs, management of large groups of students, asynchronous and geographically independent learning) as well as its regulation and governmental support. However, the lack of effective mechanisms that assure user authentication in this sort of environment has been pointed out as a serious deficiency, both in the system logon and during user attendance in the course assignments. Currently, password based authentication still prevails. Nevertheless, studies have been carried out about possible biometric applications for Web authentication. With the popularization and resultant decreasing costs of biometric enabled devices, such as webcams, microphones and embedded fingerprint sensors, Biometrics is reconsidered as a secure and viable form of remote authentication of individuals for Web applications. Based on that, this work presents a distributed architecture for an e-Learning environment, by exploring the properties of a Web system for biometric authentication both in the system logon and in continuous monitoring, during the course attendance. For the analysis of this architecture, the performance of techniques for face recognition from video, captured on-line by a webcam in an Internet environment, is evaluated, simulating the natural interaction of an individual in an e-Learning system. For that, a private database was created, with 43 individuals browsing and interacting with Web pages. The results show that the methods analyzed, though consolidated in the literature, can be successfully applied in this kind of application, with recognition rates up to 97% in ideal conditions, with low execution times and with short amount of information transmitted between client and server, with templates sizes of about 30KB. / Mestre

Submitted by Henrique Garcia de Lima (hgdlima@gmail.com) on 2014-07-01T02:56:41Z No. of bitstreams: 1 2014-06-30_FGV_Dissertação - Henrique Lima_versão Biblioteca Digital.pdf: 6573543 bytes, checksum: 10d52e68445c89c829a62146889b904f (MD5) / Approved for entry into archive by ÁUREA CORRÊA DA FONSECA CORRÊA DA FONSECA (aurea.fonseca@fgv.br) on 2014-07-07T13:34:56Z (GMT) No. of bitstreams: 1 2014-06-30_FGV_Dissertação - Henrique Lima_versão Biblioteca Digital.pdf: 6573543 bytes, checksum: 10d52e68445c89c829a62146889b904f (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2014-07-14T13:58:09Z (GMT) No. of bitstreams: 1 2014-06-30_FGV_Dissertação - Henrique Lima_versão Biblioteca Digital.pdf: 6573543 bytes, checksum: 10d52e68445c89c829a62146889b904f (MD5) / Made available in DSpace on 2014-07-14T13:58:29Z (GMT). No. of bitstreams: 1 2014-06-30_FGV_Dissertação - Henrique Lima_versão Biblioteca Digital.pdf: 6573543 bytes, checksum: 10d52e68445c89c829a62146889b904f (MD5) Previous issue date: 2014-04-30 / Este trabalho teve como objetivo analisar o uso da biometria no serviço público como forma de redução das oportunidades de fraudes e melhoria da gestão de pessoas na administração pública. Para isso, foi feita uma comparação semiestruturada da experiência internacional e um estudo de caso aprofundado do projeto Identidade Funcional, desenvolvido pelo governo do Estado do Rio de Janeiro. As lições mais importantes, derivadas destas experiências, estão refletidas em um modelo de projeto para formação de uma base biométrica capaz de garantir a integridade do cadastro de pagamento dos salários e benefícios de previdência da administração pública. O modelo tomou por referência a prefeitura de Duque de Caxias, porém foi estruturado de modo a ser viável em municípios do mesmo porte. / This study aims to analyze the use of biometrics in the public service as a way of reducing opportunities for fraud and improving the management of public affairs. The current study uses a semi-structured comparison of international experiences and an in-depth case study of Functional Identity design undertaken by the state government of Rio de Janeiro. The most important lessons derived from these cases were then used to develop a project template for registering biometric data to ensure the integrity of salary and pension benefit within the public administration. The template took as a reference the municipality of Duque de Caxias, but was structured to be viable in cities of a similar size.

Combiner les sources d'information pour créer un système de reconnaissance biométrique multimodal permet d'atténuer les limitations de chaque caractéristique utilisée, et donne l'opportunité d'améliorer significativement les performances. Le travail présenté dans ce manuscrit a été réalisé dans le but de proposer un système de reconnaissance performant, qui réponde à des contraintes d'utilisation grand-public, et qui puisse être implanté sur un système matériel de faible coût. La solution choisie explore les possibilités apportées par la multimodalité, et en particulier par la fusion du visage et de la paume. La chaîne algorithmique propose un traitement basé sur les filtres de Gabor, ainsi qu’une fusion des scores. Une base multimodale réelle de 130 sujets acquise sans contact a été conçue et réalisée pour tester les algorithmes. De très bonnes performances ont été obtenues, et ont été confirmées sur une base virtuelle constituée de deux bases publiques (les bases AR et PolyU). L'étude approfondie de l'architecture des DSP, et les différentes implémentations qui ont été réalisées sur un composant de type TMS320c64x, démontrent qu'il est possible d'implanter le système sur un unique DSP avec des temps de traitement très courts. De plus, un travail de développement conjoint d'algorithmes et d'architectures pour l'implantation FPGA a démontré qu'il était possible de réduire significativement ces temps de traitement. / Including multiple sources of information in personal identity recognition reduces the limitations of each used characteristic and gives the opportunity to greatly improve performance. This thesis presents the design work done in order to build an efficient generalpublic recognition system, which can be implemented on a low-cost hardware platform. The chosen solution explores the possibilities offered by multimodality and in particular by the fusion of face and palmprint. The algorithmic chain consists in a processing based on Gabor filters and score fusion. A real database of 130 subjects has been designed and built for the study. High performance has been obtained and confirmed on a virtual database, which consists of two common public biometric databases (AR and PolyU). Thanks to a comprehensive study on the architecture of the DSP components and some implementations carried out on a DSP belonging to the TMS320c64x family, it has been proved that it is possible to implement the system on a single DSP with short processing times. Moreover, an algorithms and architectures development work for FPGA implementation has demonstrated that these times can be significantly reduced.

Made available in DSpace on 2015-03-26T13:42:34Z (GMT). No. of bitstreams: 1 texto completo.pdf: 1068660 bytes, checksum: 930f9c25a88fb00b35dbf177ec6987f8 (MD5) Previous issue date: 2014-07-25 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The search for alternative sources of energy, due to the environmental damage caused by greenhouse gases and the depletion of oil easy to extract, resulted in a new phase of growth of the national sugarcane agribusiness. Apart from sugar cane juice to produce sugar and ethanol, the industrialization process obtains the biomass, a lignocellulosic material with high energy content, which can be converted into biofuels. It is essential the characterization of germplasm banks, which consist in great genetic variability and can be used as potential parents in breeding programs. Recognized this importance, the present work aimed to study the genetic diversity of a germplasm bank of cane sugar for selection of potential parents for bioenergy production. Ninety genotypes sown in simple installments and without repetitions were characterized for their chemical and technological constitutions. The descriptive analysis enabled the determination of variability among accessions. The relationships between the variables were estimated from analyzes of simple and partial correlations and the path analysis with the dry matter (MS) as the main variable. To study the genetic divergence, multivariate analyzes were performed. From the Euclidean distance matrix standardized mean, techniques clustering were applied by Tocher optimization method and the hierarchical agglomerative method based on the average linkage between groups (UPGMA). We proceeded with the principal component analysis in order to complement the analysis of clustering. The simultaneous selection of characters, from the index proposed by Mulamba and Mock (1978), allowed the classification of genotypes for different purposes. It was possible to observe amplitude variation high among accessions for all the variables, excepted cellulose. Despite the low correlations for most variables, it was possible to obtain correlated response to selection of the desired characters, highlighting the variable total soluble solids (BRIX), a feature that is easy to measure and can be regarded as the main feature for be used for indirect selection of correlated characters. Path analysis is not the most appropriate to verify the direct and indirect relationships between the variables studied on the main variable (dry matter), because it showed low value of coefficient of determination (R2= 0.29) and high residual effect of the variable (0.84). The clustering methods gathered 90 genotypes, similarly, for eight distinct groups. The principal components , was not satisfactory, since 8 components were needed to explain 83.3% of the variation, however was good to identify the most important for genetic diversity variable was the total sugars (AT) and contributed the least was the dry matter (MS). With the simultaneous selection of characters were ranked ten most promising access for the sugarcane juice quality and the use of bagasse for the production of bioelectricity and/or cellulosic ethanol. From the selected genotypes and the similarity between them, it was possible to indicate potential crosses between parents with high-quality production of sugar and ethanol, as well as an interesting plant biomass for bioenergy production, highlighting 18 crosses between genotypes for bioelectricity, 14 for cellulosic ethanol and 6 for both purposes. / A busca por fontes alternativas de energia, devido aos prejuízos ambientais ocasionados pelos gases de efeito estufa e ao esgotamento das reservas de petróleo de fácil extração, resultou numa nova fase de crescimento da agroindústria canavieira nacional. Além do caldo da cana para produção de açúcar e etanol, do processo de industrialização obtém- se a biomassa, um material lignocelulósico, com elevado conteúdo energético, que pode ser convertido em biocombustíveis. É indispensável à caracterização de genótipos de bancos de germoplasmas, que constituem excelente variabilidade genética e podem ser utilizados como genitores potenciais nos programas de melhoramento. Reconhecida esta importância, o presente trabalho teve como objetivo o estudo da diversidade genética de um banco de germoplasma de cana-de-açúcar visando à seleção de genitores potenciais para produção de bioenergia. Noventa genótipos semeados em parcelas simples e sem repetições, foram caracterizados quanto suas constituições químicas e tecnológicas. A estatística descritiva possibilitou a verificação da existência de variabilidade entre os genótipos avaliados. As relações entre os caracteres foram estimadas a partir das análises de correlações simples e parciais e pela análise de trilha que teve como variável principal a matéria seca (MS). Para o estudo da diversidade genética foram realizadas análises multivariadas. A partir da matriz de distância euclidiana média padronizada foi aplicado técnicas de agrupamento pelo método de otimização de Tocher e pelo método aglomerativo hierárquico com base na ligação média entre grupos (UPGMA). Procedeu- se com a análise por componentes principais a fim de complementar as análises de agrupamentos. A seleção simultânea de caracteres, com o índice proposto por Mulamba e Mock (1978), possibilitou selecionar genótipos para diferentes finalidades. Foi possível observar alta amplitude de variação entre os genótipos para os caracteres avaliados, excetuado a celulose. Apesar das baixas correlações encontradas para maior parte das variáveis, foi possível obter resposta correlacionada entre os caracteres desejados para seleção, destacando-se a variável sólidos solúveis totais (BRIX), que é uma característica de fácil medição e pode ser considerada a principal característica para ser utilizada na seleção indireta de caracteres correlacionados. A análise de trilha não é a mais indicada para verificar as relações diretas e indiretas entre os caracteres estudados sobre a variável principal matéria seca (MS), pois apresentou baixo valor de coeficiente de determinação (R2 = 0,29) e alto efeito da variável residual (0,84). Os métodos de agrupamento reuniram os 90 genótipos, de forma similar, em oito grupos distintos. A técnica de componentes principais não foi satisfatória, pois foram necessários 8 componentes para explicar 83,3 % da variação, porém foi eficiente para identificar que a variável mais importante para a diversidade genética foi os açúcares totais (AT) e a que menos contribuiu foi a matéria seca (MS). Com a seleção simultânea de caracteres classificou-se os dez genótipos mais promissores para qualidade do caldo e para aproveitamento do bagaço para produção de bioeletricidade e /ou etanol celulósico. A partir dos genótipos selecionados e da similaridade entre eles, foi possível indicar cruzamentos entre genitores potenciais, com alta qualidade para produção de açúcar e etanol, bem como uma biomassa vegetal interessante para produção de bioenergia, destacando-se 18 cruzamentos para produção de bioeletricidade, 14 para etanol celulósico e 6 para ambas as finalidades.

Made available in DSpace on 2014-06-11T19:29:40Z (GMT). No. of bitstreams: 0 Previous issue date: 2009-07-27Bitstream added on 2014-06-13T20:59:56Z : No. of bitstreams: 1 penteado_be_me_sjrp.pdf: 1032009 bytes, checksum: 4cf143854132e42249128674b69ba77b (MD5) / Nos últimos anos tem sido observado um crescimento exponencial na oferta de cursos a distância realizados pela Internet, decorrente de suas vantagens e características (menores custos de distribuição e atualização de conteúdo, gerenciamento de grandes turmas, aprendizado assíncrono e geograficamente independente, etc.), bem como de sua regulamentação e apoio governamental. Entretanto, a falta de mecanismos eficazes para assegurar a autenticação dos alunos neste tipo de ambiente é apontada como uma séria deficiência, tanto no acesso ao sistema quanto durante a participação do usuário nas atividades do curso. Atualmente, a autenticação baseada em senhas continua predominante. Porém, estudos têm sido conduzidos sobre possíveis aplicações da Biometria para autenticação em ambientes Web. Com a popularização e conseqüente barateamento de hardware habilitado para coleta biométrica (como webcams, microfone e leitores de impressão digital embutidos), a Biometria passa a ser considerada uma forma segura e viável de autenticação remota de indivíduos em aplicações Web. Baseado nisso, este trabalho propõe uma arquitetura distribuída para um ambiente de e-Learning, explorando as propriedades de um sistema Web para a autenticação biométrica tanto no acesso ao sistema quanto de forma contínua, durante a realização do curso. Para análise desta arquitetura, é avaliada a performance de técnicas de reconhecimento de faces a partir de vídeo capturadas on-line por uma webcam em um ambiente de Internet, simulando a interação natural de um indivíduo em um sistema de e- Learning. Para este fim, foi criada uma base de dados de vídeos própria, contando com 43 indivíduos navegando e interagindo com páginas Web. Os resultados obtidos mostram que os métodos analisados, consolidados na literatura, podem ser aplicados com sucesso nesse tipo de aplicação... / In the last years it has been observed an exponential growth in the offering of Internet-enabled distance courses, due to its advantages and features (decreased distribution and content updates costs, management of large groups of students, asynchronous and geographically independent learning) as well as its regulation and governmental support. However, the lack of effective mechanisms that assure user authentication in this sort of environment has been pointed out as a serious deficiency, both in the system logon and during user attendance in the course assignments. Currently, password based authentication still prevails. Nevertheless, studies have been carried out about possible biometric applications for Web authentication. With the popularization and resultant decreasing costs of biometric enabled devices, such as webcams, microphones and embedded fingerprint sensors, Biometrics is reconsidered as a secure and viable form of remote authentication of individuals for Web applications. Based on that, this work presents a distributed architecture for an e-Learning environment, by exploring the properties of a Web system for biometric authentication both in the system logon and in continuous monitoring, during the course attendance. For the analysis of this architecture, the performance of techniques for face recognition from video, captured on-line by a webcam in an Internet environment, is evaluated, simulating the natural interaction of an individual in an e-Learning system. For that, a private database was created, with 43 individuals browsing and interacting with Web pages. The results show that the methods analyzed, though consolidated in the literature, can be successfully applied in this kind of application, with recognition rates up to 97% in ideal conditions, with low execution times and with short amount of information transmitted between client and server, with templates sizes of about 30KB.

Algumas atividades antrópicas podem provocar alterações nos recursos naturais, seja ela no rio, no solo ou no mar. Os efeitos destas alterações podem ser observados na biota, na qualidade das águas, na disponibilidade de nutrientes, interferindo em todos os elementos que compõem o ecossistema, influenciando-o em maior ou menor grau. O presente estudo procurou determinar o efeito dos poluentes sulfato de zinco, cloreto de amônia, dodecilsulfato de sódio e benzeno, numa espécie bioindicadora marinha, el larvas de mexilhão (Perna perna), além de acrescentar dados sobre a biologia e analisar quimicamente a presença de hidrocarbonetos nos tecidos dos animais adultos e das larvas. Para tanto foram utilizados testes de toxicidade, estudos sobre a bioenergética (consumo de oxigênio e excreção de amônia), enzimas biomarcadoras e excreção de fósforo e nitrogênio. Com relação à biologia, foram encontrados indivíduos sexualmente maduros a partir de 26,1 e 27 mm de comprimento para fêmeas e machos, respectivamente, e há diferença, ainda que esta não seja estatisticamente significativa, entre ovócitos e larvas submetidos a ação de poluentes. A análise de hidrocarbonetos indicou que existe uma contribuição biogênica e petrogênica no litoral norte do Estado de São Paulo. Para as demais análises verificou-se que, quando comparados aos grupos controles, as larvas foram sensíveis e responderam aos diferentes poluentes, geralmente com inibição da atividade. / Some antropic activities may be the cause fo alterations in natural resources, being it river, soil or sea. These alteration effects may be observed in the biota, water quality, nutrients disponibility, interfering with all elements that are part of a ecosystem, with greater or lesser influence degree. The present study was directed to determine the effect of pollutants, such as zinc sulphate, ammonia chlorate, sodium dodecilsulphate and benzene, acting over larvae of a marine bioindicator, the mussel (Perna perna), besides adding data on biology and chemically analysing hidrocarbon presence in larvae and adult animal tissues. In order to obtain these results, toxicity tests were used and bioenergetic (oxygen consumption and ammonia excretion), biomarkers, phosphorus and nitrogen excretion, were studied. As for biology, individuals sexually mature were found starting with 26,1 and 27 mm length females and males, respectively, and there is difference between larvae and ovocites, although statistically not significant, submitted to pollutants action. The hydrocarbon analysis indicates a biogenic and petrogenic contribution to north coast of São Paulo State. For the other analyses the observed results, when compared to control groups, showed that larvae are sensitive, and responded to different pollutants, generally with activity inhibition.