Thesis (MSc)--Stellenbosch University, 2011. / ENGLISH ABSTRACT: An off-line signature verification system attempts to authenticate the identity of an individual by examining his/her handwritten signature, after it has been successfully extracted from, for example, a cheque, a debit or credit card transaction slip, or any other legal document. The questioned signature is typically compared to a model trained from known positive samples, after which the system attempts to label said signature as genuine or fraudulent. Classifier fusion is the process of combining individual classifiers, in order to construct a single classifier that is more accurate, albeit computationally more complex, than its constituent parts. A combined classifier therefore consists of an ensemble of base classifiers that are combined using a specific fusion strategy. In this dissertation a novel off-line signature verification system, using a multi-hypothesis approach and classifier fusion, is proposed. Each base classifier is constructed from a hidden Markov model (HMM) that is trained from features extracted from local regions of the signature (local features), as well as from the signature as a whole (global features). To achieve this, each signature is zoned into a number of overlapping circular retinas, from which said features are extracted by implementing the discrete Radon transform. A global retina, that encompasses the entire signature, is also considered. Since the proposed system attempts to detect high-quality (skilled) forgeries, it is unreasonable to assume that samples of these forgeries will be available for each new writer (client) enrolled into the system. The system is therefore constrained in the sense that only positive training samples, obtained from each writer during enrolment, are available. It is however reasonable to assume that both positive and negative samples are available for a representative subset of so-called guinea-pig writers (for example, bank employees). These signatures constitute a convenient optimisation set that is used to select the most proficient ensemble. A signature, that is claimed to belong to a legitimate client (member of the general public), is therefore rejected or accepted based on the majority vote decision of the base classifiers within the most proficient ensemble. When evaluated on a data set containing high-quality imitations, the inclusion of local features, together with classifier combination, significantly increases system performance. An equal error rate of 8.6% is achieved, which compares favorably to an achieved equal error rate of 12.9% (an improvement of 33.3%) when only global features are considered. Since there is no standard international off-line signature verification data set available, most systems proposed in the literature are evaluated on data sets that differ from the one employed in this dissertation. A direct comparison of results is therefore not possible. However, since the proposed system utilises significantly different features and/or modelling techniques than those employed in the above-mentioned systems, it is very likely that a superior combined system can be obtained by combining the proposed system with any of the aforementioned systems. Furthermore, when evaluated on the same data set, the proposed system is shown to be significantly superior to three other systems recently proposed in the literature. / AFRIKAANSE OPSOMMING: Die doel van ’n statiese handtekening-verifikasiestelsel is om die identiteit van ’n individu te bekragtig deur sy/haar handgeskrewe handtekening te analiseer, nadat dit suksesvol vanaf byvoorbeeld ’n tjek,’n debiet- of kredietkaattransaksiestrokie, of enige ander wettige dokument onttrek is. Die bevraagtekende handtekening word tipies vergelyk met ’n model wat afgerig is met bekende positiewe voorbeelde, waarna die stelsel poog om die handtekening as eg of vervals te klassifiseer. Klassifiseerder-fusie is die proses waardeer individuele klassifiseerders gekombineer word, ten einde ’n enkele klassifiseerder te konstrueer, wat meer akkuraat, maar meer berekeningsintensief as sy samestellende dele is. ’n Gekombineerde klassifiseerder bestaan derhalwe uit ’n ensemble van basis-klassifiseerders, wat gekombineer word met behulp van ’n spesifieke fusie-strategie. In hierdie projek word ’n nuwe statiese handtekening-verifikasiestelsel, wat van ’n multi-hipotese benadering en klassifiseerder-fusie gebruik maak, voorgestel. Elke basis-klassifiseerder word vanuit ’n verskuilde Markov-model (HMM) gekonstrueer, wat afgerig word met kenmerke wat vanuit lokale gebiede in die handtekening (lokale kenmerke), sowel as vanuit die handtekening in geheel (globale kenmerke), onttrek is. Ten einde dit te bewerkstellig, word elke handtekening in ’n aantal oorvleulende sirkulêre retinas gesoneer, waaruit kenmerke onttrek word deur die diskrete Radon-transform te implementeer. ’n Globale retina, wat die hele handtekening in beslag neem, word ook beskou. Aangesien die voorgestelde stelsel poog om hoë-kwaliteit vervalsings op te spoor, is dit onredelik om te verwag dat voorbeelde van hierdie handtekeninge beskikbaar sal wees vir elke nuwe skrywer (kliënt) wat vir die stelsel registreer. Die stelsel is derhalwe beperk in die sin dat slegs positiewe afrigvoorbeelde, wat bekom is van elke skrywer tydens registrasie, beskikbaar is. Dit is egter redelik om aan te neem dat beide positiewe en negatiewe voorbeelde beskikbaar sal wees vir ’n verteenwoordigende subversameling van sogenaamde proefkonynskrywers, byvoorbeeld bankpersoneel. Hierdie handtekeninge verteenwoordig ’n gereieflike optimeringstel, wat gebruik kan word om die mees bekwame ensemble te selekteer. ’n Handtekening, wat na bewering aan ’n wettige kliënt (lid van die algemene publiek) behoort, word dus verwerp of aanvaar op grond van die meerderheidstem-besluit van die basis-klassifiseerders in die mees bekwame ensemble. Wanneer die voorgestelde stelsel op ’n datastel, wat hoë-kwaliteit vervalsings bevat, ge-evalueer word, verhoog die insluiting van lokale kenmerke en klassifiseerder-fusie die prestasie van die stelsel beduidend. ’n Gelyke foutkoers van 8.6% word behaal, wat gunstig vergelyk met ’n gelyke foutkoers van 12.9% (’n verbetering van 33.3%) wanneer slegs globale kenmerke gebruik word. Aangesien daar geen standard internasionale statiese handtekening-verifikasiestelsel bestaan nie, word die meeste stelsels, wat in die literatuur voorgestel word, op ander datastelle ge-evalueer as die datastel wat in dié projek gebruik word. ’n Direkte vergelyking van resultate is dus nie moontlik nie. Desnieteenstaande, aangesien die voorgestelde stelsel beduidend ander kenmerke en/of modeleringstegnieke as dié wat in bogenoemde stelsels ingespan word gebruik, is dit hoogs waarskynlik dat ’n superieure gekombineerde stelsel verkry kan word deur die voorgestelde stelsel met enige van bogenoemde stelsels te kombineer. Voorts word aangetoon dat, wanneer op dieselfde datastel geevalueerword, die voorgestelde stelstel beduidend beter vaar as drie ander stelsels wat onlangs in die literatuur voorgestel is.

Dans son contexte spécifique, le terme « biométrie » est souvent associé à l'étude des caractéristiques physiques et comportementales des individus afin de parvenir à leur identification ou à leur vérification. Ainsi, le travail développé dans cette thèse nous a conduit à proposer un algorithme d'identification robuste, en considérant les caractéristiques intrinsèques des phalanges de la main. Considérée comme une biométrie cachée, cette nouvelle approche peut s'avérer intéressante, notamment lorsqu'il est question d'assurer un niveau de sécurité élevé, robuste aux différentes attaques qu'un système biométrique doit contrer. La base des techniques proposées requière trois phases, à savoir: (1) la segmentation des phalanges, (2) l'extraction de leurs caractéristiques par la génération d'une empreinte, appelée « Phalange-Code » et (3) l'identification basée sur la méthode du 1-plus proche voisin ou la vérification basée sur une métrique de similarité. Ces algorithmes opèrent sur des niveaux hiérarchiques permettant l'extraction de certains paramètres, invariants à des transformations géométriques telles que l'orientation et la translation. De plus, nous avons considéré des techniques robustes au bruit, pouvant opérer à différentes résolutions d'images. Plus précisément, nous avons élaboré trois approches de reconnaissance biométrique : la première approche utilise l'information spectrale des contours des phalanges de la main comme signature individuelle, alors que la deuxième approche nécessite l'utilisation des caractéristiques géométriques et morphologiques des phalanges (i.e. surface, périmètre, longueur, largeur, capacité). Enfin, la troisième approche requière la génération d'un nouveau rapport de vraisemblance entre les phalanges, utilisant la théorie de probabilités géométriques. En second lieu, la construction d'une base de données avec la plus faible dose de rayonnement a été l'un des grands défis de notre étude. Nous avons donc procédé par la collecte de 403 images radiographiques de la main, acquises en utilisant la machine Apollo EZ X-Ray. Ces images sont issues de 115 adultes volontaires (hommes et femmes), non pathologiques. L'âge moyen étant de 27.2 ans et l'écart-type est de 8.5. La base de données ainsi construite intègre des images de la main droite et gauche, acquises à des positions différentes et en considérant des résolutions différentes et des doses de rayonnement différentes (i.e. réduction jusqu'à 98 % de la dose standard recommandée par les radiologues « 1 µSv »).Nos expériences montrent que les individus peuvent être distingués par les caractéristiques de leurs phalanges, que ce soit celles de la main droite ou celles de la main gauche. Cette distinction est également valable pour le genre des individus (homme/femme). L'étude menée a montré que l'approche utilisant l'information spectrale des contours des phalanges permet une identification par seulement trois phalanges, à un taux EER (Equal Error Rate) inférieur à 0.24 %. Par ailleurs, il a été constaté « de manière surprenante » que la technique fondée sur les rapports de vraisemblance entre les phalanges permet d'atteindre un taux d'identification de 100 % et un taux d'EER de 0.37 %, avec une seule phalange. Hormis l'aspect identification/authentification, notre étude s'est penchée sur l'optimisation de la dose de rayonnement permettant une identification saine des individus. Ainsi, il a été démontré qu'il était possible d'acquérir plus de 12500/an d'images radiographiques de la main, sans pour autant dépasser le seuil administratif de 0.25 mSv / In its specific context, the term "biometrics" is often associated with the study of the physical and behavioral of individual's characteristics to achieve their identification or verification. Thus, the work developed in this thesis has led us to suggest a robust identification algorithm, taking into account the intrinsic characteristics of the hand phalanges. Considered as hidden biometrics, this new approach can be of high interest, particularly when it comes to ensure a high level of security, robust to various attacks that a biometric system must address. The basis of the proposed techniques requires three phases, namely: (1) the segmentation of the phalanges (2) extracting their characteristics by generating an imprint, called "Phalange-Code" and (3) the identification based on the method of 1-nearest neighbor or the verification based on a similarity metric. This algorithm operates on hierarchical levels allowing the extraction of certain parameters invariant to geometric transformations such as image orientation and translation. Furthermore, the considered algorithm is particularly robust to noise, and can function at different resolutions of images. Thus, we developed three approaches to biometric recognition: the first approach produces individual signature from the spectral information of the contours issued from the hand phalanges, whereas the second approach requires the use of geometric and morphological characteristics of the phalanges (i.e. surface, perimeter, length, width, and capacity). Finally, the third approach requires the generation of a new likelihood ratio between the phalanges, using the geometric probability theory. Furthermore, the construction of a database with the lowest radiation dose was one of the great challenges of our study. We therefore proceeded with the collection of 403 x-ray images of the hand, acquired using the Apollo EZ X-Ray machine. These images are from 115 non-pathological volunteering adult (men and women). The average age is 27.2 years and the standard deviation is 8.5. Thus, the constructed database incorporates images of the right and left hands, acquired at different positions and by considering different resolutions and different radiation doses (i.e. reduced till 98% of the standard dose recommended by radiologists "1 µSv").Our experiments show that individuals can be distinguished by the characteristics of their phalanges, whether those of the right hand or the left hand. This distinction also applies to the kind of individuals (male/female). The study has demonstrated that the approach using the spectral information of the phalanges' contours allows identification by only three phalanges, with an EER (Equal Error Rate) lower than 0.24 %. Furthermore, it was found “Surprisingly” that the technique based on the likelihood ratio between phalanges reaches an identification rate of 100% and an EER of 0.37% with a single phalanx. Apart from the identification/authentication aspect, our study focused on the optimization of the radiation dose in order to offer safe identification of individuals. Thus, it has been shown that it was possible to acquire more than 12,500/year radiographic hand images, without exceeding the administrative control of 0.25 mSv

Baigiamajame magistro darbe nagrinėjamas genetinių algoritmų taikymas biometrijoje. Išnagrinėta plačiausiai naudojama biometrinė informacija, aprašytos labiausiai paplitusios biometrinės sistemos, genetiniai algoritmai bei jų pritaikymas biometrinių sistemų optimizavimui. Baigiamajame darbe pasiūlytas naujas rankos atpažinimo metodas. Šiam metodui pritaikyti genetiniai algoritmai. Darbą sudaro 7 dalys: įvadas, biometrija, genetiniai algoritmai, genetinių algoritmų taikymas biometrinėse sistemose, genetinių algoritmų taikymas rankos atpažinimui, išvados ir literatūra. Darbo apimtis – 51 p. teksto be priedų, 30 pav., 4 lent., 32 bibliografiniai šaltiniai. / In the graduation thesis to receive the master‘s degree the application of genetic algorithms in biometrics is analysed. The most widely used biometric information have been examined, the most common biometric systems, genetic algorithms and their customization in biometric systems optimization have been described. A new method is proposed for hand recognition. Genetic algorithms have been customized for this method. Structure: introduction, biometry, genetic algorithms, application of genetic algorithms in biometric systems, application of genetic algorithms for hand recognition, the conclusions and bibliography. Thesis consist of: 51 p. text without appendixes, 30 pictures, 4 tables, 32 bibliographical entries.

Saugiais gali būti laikomi tik užšifruoti duomenys, o šifravimas neįmanomas be šifravimo rakto. Vienas iš geriausiai žinomų ir plačiausiai naudojamų šifravimo raktų yra slaptažodis, tačiau pagrindinis jo trūkumas tas, kad jį reikia atsiminti. Šioje situacijoje gali padėti biometrija, kadangi praktiškai kiekvienas žmogus turi unikalias charakteristikas. Tačiau pagrindinė problema yra - kaip iš biometrinių charakteristikų suformuoti šifravimo raktą. Pirštų atspaudai yra gerai žinoma biometrinė charakteristika, naudojama žmonių identifikavimui ir tapatybės patvirtinimui, o USB atmintinėse ar nešiojamuosiuose kompiuteriuose integruoti pirštų atspaudų skaitytuvai jau nieko nebestebina. Kiekvienas piršto atspaudas gali būti aprašytas minutiae taškų matrica iš kurios būtų galima generuoti šifravimo raktą. Tačiau netgi to paties piršto atspaudai nėra identiški ir į tai reikia atsižvelgti. Šiame darbe pateikiamas vienas tiesioginių šifravimo raktų generavimo iš pirštų atspaudų metodas. Iš atspaudo suformuojama minutiae taškų matrica, iš jos suformuojami parametrai ir perduodami raktų generatoriams. Matricų formavimui panaudoti du produktai, realizuoti 8 generatoriai, formuojantys 64 ir 128 bitų ilgio šifravimo raktus. Sistema ištestuota su pasiruošta pirštų atspaudų duomenų baze, pateikti gauti rezultatai. / Only encrypted data can be treated as secure data and encryption is impossible without encryption key. One of the best known and widely used encryption keys is password, but the main its drawback is necessity to remember it. Biometrics may help to avoid this situation, because everyone has unique characteristics. But the main question is how to extract encryption key from biometric data. Fingerprints are well known biometric characteristic, used for people identification or authentication and fingerprint readers integrated into USB flash drives or laptops don’t cause surprise any more. Every fingerprint can be described using minutiae points’ matrix and from this matrix encryption key can be generated. But fingerprints of the same finger aren’t identical, so this must be kept in mind as well. In this research one method of direct encryption key generation from fingerprint is introduced. Minutiae matrix is structured from fingerprint image; parameters are formed and passed to encryption key generators. Two products were used for making matrix and eight generators were produced, generating encryption keys length of 64 and 128 bits. This system was tested with prepared fingerprint set and all the results are given.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

[pt] Esta dissertação teve por objetivo comparar o desempenho de diversos algoritmos que representam o estado da arte em reconhecimento facial a imagens de sequências de vídeo. Três objetivos específicos foram perseguidos: desenvolver um método para determinar quando uma face está em posição frontal com respeito à câmera (detector de face frontal); avaliar a acurácia dos algoritmos de reconhecimento com base nas imagens faciais obtidas com ajuda do detector de face frontal; e, finalmente, identificar o algoritmo com melhor desempenho quando aplicado a tarefas de verificação e identificação. A comparação dos métodos de reconhecimento foi realizada adotando a seguinte metodologia: primeiro, foi criado um detector de face frontal que permitiu o captura das imagens faciais frontais; segundo, os algoritmos foram treinados e testados com a ajuda do facereclib, uma biblioteca desenvolvida pelo Grupo de Biometria no Instituto de Pesquisa IDIAP; terceiro, baseando-se nas curvas ROC e CMC como métricas, compararam-se os algoritmos de reconhecimento; e por ultimo, as análises dos resultados foram realizadas e as conclusões estão relatadas neste trabalho. Experimentos realizados sobre os bancos de vídeo: MOBIO, ChokePOINT, VidTIMIT, HONDA, e quatro fragmentos de diversos filmes, indicam que o Inter Session Variability Modeling e Gaussian Mixture Model são os algoritmos que fornecem a melhor acurácia quando são usados em tarefas tanto de verificação quanto de identificação, o que os indica como técnicas de reconhecimento viáveis para o vídeo monitoramento automático em vídeo. / [en] This dissertation aimed to compare the performance of state-of-the-arte face recognition algorithms in facial images captured from multiple video sequences. Three specific objectives were pursued: to develop a method for determining when a face is in frontal position with respect to the camera (frontal face detector); to evaluate the accuracy for recognition algorithms based on the facial images obtained with the help of the frontal face detector; and finally, to identify the algorithm with better performance when applied to verification and identification tasks in video surveillance systems. The comparison of the recognition methods was performed adopting the following approach: first, a frontal face detector, which allowed the capture of facial images was created; second, the algorithms were trained and tested with the help of facereclib, a library developed by the Biometrics Group at the IDIAP Research Institute; third, ROC and CMC curves were used as metrics to compare the recognition algorithms; and finally, the results were analyzed and the conclusions were reported in this manuscript. Experiments conducted on the video datasets: MOBIO, ChokePOINT, VidTIMIT, HONDA, and four fragments of several films, indicate that the Inter-Session Variability Modelling and Gaussian Mixture Model algorithms provide the best accuracy on classification when the algorithms are used in verification and identification tasks, which indicates them as a good automatic recognition techniques for video surveillance applications.

A combinação de fontes biométricas não redundantes da multibiometria supera a precisão de cada fonte individual (monobiometria). Além do mais, dois problemas em biometria, ruído e ataques de usurpadores, podem ser minimizados pelo uso de múltiplos sensores e biometria multimodal. Entretanto, se as similaridades estão em todos traços biométricos, como em gêmeos monozigotos (MZ), o processamento de múltiplas fontes não melhora a performance. Para distinguir extrema similitude, influências epigenéticas e ambientais são mais importantes do que o DNA herdado. Esta tese examina a plasticidade fenotípica na assimetria humana como uma ferramenta para melhorar a multibiometria. A técnica de Processamento Bilateral (PB) é introduzida para analisar discordâncias em lados esquerdo e direito dos traços biométricos. PB foi testado com imagens de espectro visível e infravermelho usando Correlação Cruzada, Wavelets e Redes Neurais Artificiais. Os traços selecionados foram dentes, orelhas, íris, impressões digitais, narinas e bochechas. PB acústico também foi implementado para avaliação da assimetria vibracional durante sons vocálicos e comparado a um sistema reconhecedor de locutores com parametrização via MFCC (Mel Frequency Cepstral Coefficients) e classificado por Quantização Vetorial. Para o PB de imagens e acústico foram coletadas 20 amostras por traço biométrico durante um ano de nove irmãos masculinos adultos. Com propósito de teste, as biometrias esquerdas foram impostoras às biometrias direitas do mesmo indivíduo e vice-versa, o que levou a 18 entidades serem identificadas por traço biométrico. Resultados alcançaram identificação total em todas biometrias tratadas com PB, comparado a um máximo de 44% de identificação correta sem PB. Esta tese conclui que peculiaridades bilaterais melhoram a performance multibiométrica e podem complementar qualquer abordagem de reconhecimento. / Combination of non-redundant biometric sources in multibiometrics overcomes individual source accuracy (monobiometrics). Moreover, two problems in biometrics, noise and impostor attacks, can be minimized by the use of multi-sensor, multi-modal biometrics. However, if similarities are in all traits, as in monozygotic twins (MZ), multiple source processing does not improve performance. To distinguish extreme similitude, epigenetic and environmental influences are more important than DNA inherited. This thesis examines phenotypic plasticity in human asymmetry as a tool to ameliorate multibiometrics. Bilateral Processing (BP) technique is introduced to analyze discordances in left and right trait sides. BP was tested in visible and infrared spectrum images using Cross-Correlation, Wavelets and Artificial Neural Networks. Selected traits were teeth, ears, irises, fingerprints, nostrils and cheeks. Acoustic BP was also implemented for vibration asymmetry evaluation during voiced sounds and compared to a speaker recognition system parameterized via MFCC (Mel Frequency Cepstral Coefficients) and classified by Vector Quantization. Image and acoustic BP gathered 20 samples per biometric trait during one year from nine adult male brothers. For test purposes, left biometrics was impostor to right biometrics from the same individual and vice-versa, which led to 18 entities to be identified per trait. Results achieved total identification in all biometrics treated with BP, compared to maximum 44% of correct identification without BP. This study concludes that bilateral peculiarities improve multibiometric performance and can complement any recognition approach.

A fase mais difícil e que exige mais recursos em um programa de melhoramento de milho é a avaliação experimental dos híbridos, pois geralmente um elevado número de híbridos necessita ser avaliado em diversos ambientes. Deste modo, tanto o número de híbridos como o de ambientes são limitados pelos recursos disponíveis, o que poderia levar a uma redução do número de ambientes, e, portanto, conjuntos de híbridos comumente são avaliados em diferentes ambientes levando a comparações desbalanceadas entre os híbridos. A metodologia estatística conhecida como REM/BLUP tem sido amplamente utilizada no melhoramento animal, mas nos programas de melhoramento vegetal a sua utilização tem sido restrita a culturas perenes, onde experimentos desbalanceados são comuns. Há pouca informação na literatura sobre a confiabilidade do método REML/BLUP utilizando dados experimentais para a predição de valores genotípicos sob experimentos desbalanceados para programas de melhoramento de culturas anuais. Assim, o objetivo desta pesquisa foi avaliar se o método REML/BLUP poderia ser útil para predizer os valores genotípicos de híbridos simples de milho sob situações de desbalanceamento. Um conjunto de 256 híbridos simples foi avaliado em delineamento látice 16 x 16 com duas repetições por ambiente em 13 ambientes e as características analisadas foram produção de grãos, altura da planta e acamamento de plantas. Uma vez que a avaliação constou de 26 observações para cada híbrido simples, suas médias gerais ajustadas computadas pelo método dos quadrados mínimos foram consideradas como seus valores genotípicos, para fins de comparações com as predições dos valores genotípicos pelo método REML/BLUP. As predições dos híbridos simples foram computadas pelo método REML/BLUP considerando conjuntos desbalanceados de híbridos dentro de ambientes e perdas completas dos dados de ambientes. Os dados foram submetidos a um desbalanceamento aleatório e cada situação foi simulada 1.000 vezes utilizando o método bootstrap. Foram computados coeficientes de correlação entre os valores genotípicos preditos e as médias gerais ajustadas, e seus valores foram elevados ao quadrado para obter os valores de R2; assim 1.000 valores de R2 foram obtidos para cada situação considerada. Além disso, foi praticada seleção utilizando os valores genotípicos preditos e as médias gerais ajustadas dos híbridos simples e as percentagens de coincidência foram computadas. Independentemente do caráter analisado, os valores de R2 e o percentual de coincidência dos híbridos simples selecionados mostrou que o REML/BLUP prediz com alta acurácia os valores genotípicos dos híbridos simples com até 20% das perdas de híbridos dentro de ambientes ou com redução de até 23% dos ambientes. Nota-se que o caráter produção de grãos apresentou interação genótipos x ambientes significativa e complexa, e mesmo assim o método REML/BLUP fez a predição dos valores genotípicos com alta acurácia. Deste modo, o método REML/BLUP poderia ser considerado como uma valiosa ferramenta no melhoramento genético de milho para predizer os valores genotípicos dos híbridos sob dados desbalanceados. Entretanto, os resultados também apontaram que há um limite para a sua acurácia, o qual corresponde a cerca de 20% dos dados desbalanceados. / The more difficult phase and that demands more funding in a maize breeding program is the experimental evaluation of the hybrids, because usually a high number of hybrids needs to be evaluated in several environments. Then, both the number of environments and hybrids are limited by the resources available, which could lead to a reduction in the number of environments, and therefore, sets of hybrids are commonly tested in different environments leading to unbalanced comparisons among the hybrids. The statistical methodology known as REM/BLUP has been widely used in animal breeding, but in plant breeding programs its use has been restricted to perennial crops where unbalanced experiments are very common. There is limited information about the reliability of the REM/BLUP method using experimental data for the genotypic values prediction under unbalanced experiments for annual crops breeding programs. Thus, the objective of this research was to assess whether the REM/BLUP method could be useful to predict the genotypic values of maize single-crosses under unbalanced situations. A set of 256 single-crosses was evaluated in a 16 x 16 lattice design with two replications per environment in 13 environments, and the traits analyzed were grain yield, plant lodging and plant height. As the evaluation consisted of 26 observations for each single-cross, their adjusted overall means computed by the least squares method were considered as their genotypic values for the sake of comparisons with the genotypic predictions by REM/BLUP method. The predictions of the single-crosses were computed considering unbalanced sets of hybrids within environments and unbalanced sets of environments. The data were submitted to a random unbalance and each situation was simulated 1,000 times using the bootstrap method. Coefficients of correlation were then computed between the predicted genotypic values and the adjusted overall means, and their values were squared to obtain the R2 values; thus 1,000 R2 values were obtained for each considered situation. Also, selection were performed using the predict values and the adjusted overall means of the single-crosses, and the percentage of coincidence were computed. Regardless of the trait analyzed, the R2 values and the percentage of coincidence of the selected single-crosses showed that the REM/BLUP predict with high accuracy the genotypic values of the single-crosses up to 20% of losses of hybrids within environments and up to 23% of environments reduction. It should be noted that grain yield showed a significant cross-over interaction, and even so the REM/BLUP predicted the genotypic values of the hybrids with high accuracy. Thus, the REM/BLUP method can be considered as a valuable tool in maize breeding programs to predict the genotypic values of the hybrids under unbalanced data. However, the results also pointed out that there is a limit for its accuracy, which is around 20% of unbalanced data.

A biometria é o processo de reconhecimento dos seres vivos baseado em suas características fisiológicas ou comportamentais. Existem atualmente diversos métodos biométricos e a assinatura em papel é uma das técnicas de mensuração comportamental mais antigas. Por meio do processamento de sinais de áudio, é possível realizar o reconhecimento de padrões dos ruídos emitidos pela caneta ao assinar. Com o objetivo de aumentar o grau de sucesso ao validar a assinatura realizada por uma pessoa, este trabalho propõe uma técnica baseada em um algoritmo que combina Máquinas de Vetores de Suporte (SVMs), treinadas com o uso de um procedimento de aprendizado semi-supervisionado, alimentadas por um conjunto de parâmetros obtidos com o uso da Transformada Wavelet Discreta do sinal de áudio do ruído emitido pela caneta ao assinar sobre uma superfície rígida. Os testes realizados com uma base de dados de assinaturas reais, testando diversos filtros wavelet, demonstram a eficácia da técnica proposta. / Biometrics is the process of recognition of human beings based on their physiological or behavioral characteristics. There are, currently, several methods and biometric signatures on papers is one of the oldest techniques for measuring behavioral characteristics. By digital processing the audio signals, it is possible to recognize noise emitted by pens when signing. To increase the degree of success, this work propõe a technique based on an algorithm that combines two Support Vector Machines (SVMs), trained using a semi-supervised learning procedure, fed by a set of parameters obtained using the Discrete Wavelet Transform of the audio signals produced by the noise emitted by the pen when signing on a hard surface. Tests conducted with a database of signatures, trying many wavelet filters, demonstrate the real effectiveness of the proposed approach.

Muitos fatores podem influenciar o desenvolvimento placentário e fetal na égua, dentre eles destaca-se a idade, a paridade e o porte materno. A produção de hormônios esteroides pela unidade feto-placentária também pode ser influenciada pela paridade e raça, porém não existem relatos prévios que relacionem os efeitos da idade da égua sobre a produção desses hormônios na gestação. Este trabalho conta com três objetivos principais: o primeiro investigou a influência do número de partos e da idade materna sobre a eficiência placentária e a biometria do potro ao nascimento, utilizando a análise estereológica da placenta a termo. O segundo determinou a influencia da biometria parental na macro e microscopia placentária e consequências para o desenvolvimento fetal e para o crescimento, comportamento e funções fisiológicas pós-natais. Por último foi avaliada a influência da idade e paridade materna, e da raça do potro sob a produção de estrógenos, progesterona e cortisol plasmáticos em éguas prenhes. Quarenta fêmeas gestantes foram categorizadas de acordo com a idade (Id1: 4 a 8 anos; Id2: 8 a 12 anos; Id3: ≥ 13 anos), a pluriparidade (Par1: nulíparas, Par 2: 1 a 3 partos; Par3: ≥ 4partos) e a raça do produto (MP: Mangalarga Paulista; BH: Brasileiro de Hipismo). As coletas de plasma foram realizadas semanalmente a partir do quinto mês de gestação até o termo, e a quantificação dos hormônios foi realizada pela técnica de Espectrometria de Massas. Os partos foram acompanhados a campo e dados do escore Apgar, comportamento e amostras sanguíneas para análise bioquímica dos potros foram coletados nas primeiras doze horas de vida. As membranas corioalantóides foram recolhidas após o delivramento, pesadas e fotografadas em escala. Foram coletados fragmentos correspondentes às regiões do corpo do útero, corno uterino gestante e corno uterino contralateral para análise estereológica. Parâmetros de crescimento dos neonatos foram comparados do nascimento até os dois anos de idade, assim como foram coletados dados da altura, peso e perímetro torácico materno e paterno. Não foram observadas diferenças significativas na quantificação de esteróides quando considerados os fatores número de partos e raça do produto para a categorização das fêmeas. As concentrações de estrógenos foram estatisticamente superiores no grupo Id2 em relação ao Id3, em alguns meses do período gestacional avaliado. Foi observado que a idade e a paridade materna influenciam o desenvolvimento dos microcotilédones e a densidade total de superfície dos vilos, bem como a vascularização e a composição tecidual das diferentes regiões da placenta, contribuindo de fato para uma maior área de contato materno-fetal e transferência de gases e nutrientes entre mãe e feto, culminando com o nascimento de potros mais altos, mais pesados e com maior circunferência torácica. O porte paterno, e principalmente o materno, influenciou o desenvolvimento das vilosidades fetais e a área de superfície de contato materno-fetal, com efeito positivo no desenvolvimento e no crescimento fetal, resultando no nascimento de potros com melhores respostas adaptativas e metabólicas. Também destaca-se que o período de vida intrauterino foi determinante para a taxa de crescimento pós-natal até os 24 meses de vida. / Many factors may influence placental and fetal development in the mare, like age, parity and maternal size. The production of steroid hormones by fetal-placental unit can also be influenced by parity and breed, but there are no previous reports relating the effects of the mares age on the production of these hormones during pregnancy. This paper has three main objectives: the first investigated the influence of maternal age and parity on placental efficiency and size of the foal at birth, using stereological analysis of the term placenta. The second determined the influence of parental size on macro and microscopy of the placenta and consequences for fetal development and growth, behavior and postnatal physiological functions. Finally, the influence of maternal age and parity was evaluated, and the breed´s foal in the production of plasmatic oestrogens, progesterone and cortisol in pregnant mares. Forty pregnant females were categorized according to age (Id1: 4-8 years; Id2: 8-12 years; Id3: ≥ 13 years), parity (Par1: nulliparous, Par2: 1 to 3 births; Par3: ≥ 4 births) and foal´s breed (MP: Mangalarga Paulista; BH: Brazilian Sporthorse). Plasma samples were collected weekly from the fifth month of pregnancy to term, and quantification of hormones was performed by Mass Spectrometry. Deliveries were accompanied and Apgar score, behavior and blood samples for biochemical analysis of the foals were collected within the first twelve hours of life. The chorioallantoic membranes were collected after delivery, weighed and photographed to scale. Tissue sections were collected from regions: uterine body, pregnant uterine horn and contralateral uterine horn to be analyzed stereologically. Neonate´s growth parameters were compared from birth up to two years old, as well as data on maternal and paternal height, weight, and thoracic perimeter were collected. No significant differences were observed in the quantification of steroids when considering maternal parity and foal´s breed for the mares groups. The concentrations of oestrogens were significantly higher in Id2 group when compared with Id3, in some months of the gestational period evaluated. It was observed that maternal age and parity influence the development of the microcotyledons and total villi surface density, as well as the vascularization and tissue composition of different regions of the placenta, contributing in fact to a larger area of fetomaternal contact and transfer of gases and nutrients between mother and fetus, culminating with foals that were taller, heavier and with larger thoracic circumference at birth. The paternal, and mainly maternal size, influenced the development of fetal villi and the area of fetomaternal contact surface with a positive effect on the development and fetal growth, resulting in the birth of foals with better metabolic and adaptive responses. It also highlights that the period of intrauterine life was decisive for the postnatal growth rate up to 24 months of life.