Visual place recognition for persistent robot navigation in changing environments

This thesis demonstrates that robots can learn about how the world changes, and can use this information to recognise where they are, even when the appearance of the environment has changed a great deal. The ability to localise in highly dynamic environments using vision only is a key tool for achieving long-term, autonomous navigation in unstructured outdoor environments. The proposed learning algorithms are designed to be unsupervised, and can be generated by the robot online in response to its observations of the world, without requiring information from a human operator or other external source.

Resolving Ambiguities in Confused Online Tamil Characters with Post Processing Algorithms

This paper addresses the problem of resolving ambiguities in frequently confused online Tamil character pairs by employing script specific algorithms as a post classification step. Robust structural cues and temporal information of the preprocessed character are extensively utilized in the design of these algorithms. The methods are quite robust in automatically extracting the discriminative sub-strokes of confused characters for further analysis. Experimental validation on the IWFHR Database indicates error rates of less than 3 % for the confused characters. Thus, these post processing steps have a good potential to improve the performance of online Tamil handwritten character recognition.

Application of Entropy and Fractal Dimension Analyses to the Pattern Recognition of Contaminated Fish Responses in Aquaculture

The objective of the work was to develop a non-invasive methodology for image acquisition, processing and nonlinear trajectory analysis of the collective fish response to a stochastic event. Object detection and motion estimation were performed by an optical flow algorithm in order to detect moving fish and simultaneously eliminate background, noise and artifacts. The Entropy and the Fractal Dimension (FD) of the trajectory followed by the centroids of the groups of fish were calculated using Shannon and permutation Entropy and the Katz, Higuchi and Katz-Castiglioni's FD algorithms respectively. The methodology was tested on three case groups of European sea bass (Dicentrarchus labrax), two of which were similar (C1 control and C2 tagged fish) and very different from the third (C3, tagged fish submerged in methylmercury contaminated water). The results indicate that Shannon entropy and Katz-Castiglioni were the most sensitive algorithms and proved to be promising tools for the non-invasive identification and quantification of differences in fish responses. In conclusion, we believe that this methodology has the potential to be embedded in online/real time architecture for contaminant monitoring programs in the aquaculture industry.

Autenticacão de Assinaturas Online: Estudo dos Parâmetros do Dynamic Time Warping e da Representação da Assinatura

O reconhecimento de padões é uma área da inteligência computacional que apoia a resolução de problemas utilizando ferramentas computacionais. Dentre esses problemas podem ser citados o reconhecimento de faces, a identificação de impressões digitais e a autenticação de assinaturas. A autenticação de assinaturas de forma automática tem sua relevância pois está ligada ao reconhecimento de indivíduos e suas credenciais em sistemas complexos e a questões financeiras. Neste trabalho é apresentado um estudo dos parâmetros do Dynamic Time Warping, um algoritmo utilizado para alinhar duas assinaturas e medir a similaridade existente entre elas. Variando-se os principais parâmetros desse algoritmo, sobre uma faixa ampla de valores, foram obtidas as médias dos resultados de erros na classificação, e assim, estas médias foram avaliadas. Com base nas primeiras avaliação, foi identificada a necessidade de se calcular um desses parâmetros de forma dinâmica, o gap cost, a fim de ajustá-lo no uso de uma aplicação prática. Uma proposta para a realização deste cálculo é apresentada e também avaliada. É também proposta e avaliada uma maneira alternativa de representação dos atributos da assinatura, de forma a considerar sua curvatura em cada ponto adquirido no processo de aquisição, utilizando os vetores normais como forma de representação. As avaliações realizadas durante as diversas etapas do estudo consideraram o Equal Error Rate (EER) como indicação de qualidade e as técnicas propostas foram comparadas com técnicas já estabelecidas, obtendo uma média percentual de EER de 3,47%.

On-line learning of mutually orthogonal subspaces for face recognition by image sets.

We address the problem of face recognition by matching image sets. Each set of face images is represented by a subspace (or linear manifold) and recognition is carried out by subspace-to-subspace matching. In this paper, 1) a new discriminative method that maximises orthogonality between subspaces is proposed. The method improves the discrimination power of the subspace angle based face recognition method by maximizing the angles between different classes. 2) We propose a method for on-line updating the discriminative subspaces as a mechanism for continuously improving recognition accuracy. 3) A further enhancement called locally orthogonal subspace method is presented to maximise the orthogonality between competing classes. Experiments using 700 face image sets have shown that the proposed method outperforms relevant prior art and effectively boosts its accuracy by online learning. It is shown that the method for online learning delivers the same solution as the batch computation at far lower computational cost and the locally orthogonal method exhibits improved accuracy. We also demonstrate the merit of the proposed face recognition method on portal scenarios of multiple biometric grand challenge.

Online multiple classifier boosting for object tracking

This paper presents a new online multi-classifier boosting algorithm for learning object appearance models. In many cases the appearance model is multi-modal, which we capture by training and updating multiple strong classifiers. The proposed algorithm jointly learns the classifiers and a soft partitioning of the input space, defining an area of expertise for each classifier. We show how this formulation improves the specificity of the strong classifiers, allowing simultaneous location and pose estimation in a tracking task. The proposed online scheme iteratively adapts the classifiers during tracking. Experiments show that the algorithm successfully learns multi-modal appearance models during a short initial training phase, subsequently updating them for tracking an object under rapid appearance changes. © 2010 IEEE.

Recognition of Planar Segments in Point Cloud Based on Wavelet Transform

© 2005-2012 IEEE.Within industrial automation systems, three-dimensional (3-D) vision provides very useful feedback information in autonomous operation of various manufacturing equipment (e.g., industrial robots, material handling devices, assembly systems, and machine tools). The hardware performance in contemporary 3-D scanning devices is suitable for online utilization. However, the bottleneck is the lack of real-time algorithms for recognition of geometric primitives (e.g., planes and natural quadrics) from a scanned point cloud. One of the most important and the most frequent geometric primitive in various engineering tasks is plane. In this paper, we propose a new fast one-pass algorithm for recognition (segmentation and fitting) of planar segments from a point cloud. To effectively segment planar regions, we exploit the orthonormality of certain wavelets to polynomial function, as well as their sensitivity to abrupt changes. After segmentation of planar regions, we estimate the parameters of corresponding planes using standard fitting procedures. For point cloud structuring, a z-buffer algorithm with mesh triangles representation in barycentric coordinates is employed. The proposed recognition method is tested and experimentally validated in several real-world case studies.

Towards Real-time Speech Emotion Recognition for Affective E-Learning

The original article is available as an open access file on the Springer website in the following link: http://link.springer.com/article/10.1007/s10639-015-9388-2

Preconception counselling for women with diabetes: An online resource

Pre-pregnancy care impacts positively on pregnancy outcome, yet the majority of women continue to receive suboptimal support in this area owing to a lack of awareness about the importance of pregnancy planning. An innovative preconception counselling resource has been developed in Northern Ireland (originally as a DVD and later in an online format), in collaboration with end users to raise awareness of planning for pregnancy. This educational resource is now embedded in routine care in the region as a preconception counselling tool, being adopted by all diabetes care teams and many GP practices. It also recently received national recognition, winning the “Best improvement programme for pregnancy and maternity” category at the 2013 Quality in Care Diabetes awards. This article presents the background to the resource’s development, as well as experiences from its production and roll-out.

3D Morphable Model Construction for Robust Ear and Face Recognition

Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the face within a recognition system could improve accuracy and robustness, particularly for non-frontal views. The paper describes work that investigates this hypothesis using an approach based on the construction of a 3D morphable model of the head and ear. One issue with creating a model that includes the ear is that existing training datasets contain noise and partial occlusion. Rather than exclude these regions manually, a classifier has been developed which automates this process. When combined with a robust registration algorithm the resulting system enables full head morphable models to be constructed efficiently using less constrained datasets. The algorithm has been evaluated using registration consistency, model coverage and minimalism metrics, which together demonstrate the accuracy of the approach. To make it easier to build on this work, the source code has been made available online.

A construção da identidade em ambientes digitais: estudo de caso sobre a construção da identidade online no Sapo Campus e em ambientes informais

O reconhecimento da dimensão criativa, participativa e social da rede trouxe profundas alterações à forma como se percebem e compreendem as questões relacionadas com a identidade, a educação, a prática e o conhecimento. Num cenário caraterizado pela conectividade e pela facilidade de acesso a pessoas e conteúdos, a rede oferece aos indivíduos um espaço onde podem interagir, trabalhar na sua aprendizagem, trocar experiências e construir uma identidade e reputação acessíveis a toda a comunidade. Quando se torna praticamente impossível permanecer fora do mundo digital e, consequentemente, da produção de uma identidade online (Costa e Torres, 2011; Warburton, 2009), a presença construída pelo indivíduo na rede surge como um currículo vitae ativo e dinâmico, revelador não apenas das competências adquiridas e certificadas em contextos de aprendizagem formais como daquelas desenvolvidas pela interação com os pares, pela partilha e pela comunicação. Partindo da análise da utilização de uma plataforma suportada institucionalmente (i.e. SAPO Campus), o presente trabalho de investigação tem como principal objetivo a análise e caraterização da construção da identidade online de um grupo de alunos do Mestrado em Comunicação Multimédia da Universidade de Aveiro num espaço providenciado pela instituição de ensino que frequentam. Com recurso a inquéritos por questionário, entrevistas em profundidade (realizadas aos participantes no estudo e a profissionais da área da comunicação e gestão de carreiras) e observação direta (análise quantitativa e qualitativa dos conteúdos publicados pelos participantes no SAPO Campus e em duas redes informais), procurou-se ainda caraterizar e analisar a identidade construída em espaços formais e informais, e aferir a importância – para alunos, instituição e mercado – da identidade online enquanto espaço de manifestação e divulgação de competências. Ainda que circunscrita ao contexto específico do Mestrado em Comunicação Multimédia e mais especificamente aos alunos cuja identidade online foi objeto de estudo, análise dos dados permite avançar que, de facto, os alunos estão conscientes da sua própria identidade online bem como da relevância de construir uma identidade e reputação sólidas e autênticas, que reflitam as suas competências e capacidades enquanto aprendentes e profissionais. Assim, poder-se-á avançar que no SAPO Campus os alunos estão a construir uma identidade online mais formal e cuidada, editando e selecionando os conteúdos de acordo com o contexto. Neste espaço, a maioria das publicações está diretamente relacionada com os trabalhos de investigação dos participantes, que recorrem à sua partilha nas redes informais para aumentar a visibilidade e exposição dos conteúdos publicados. Os participantes no estudo revelaram ainda valorizar o sentimento de segurança providenciado pelas tecnologias institucionais, bem como a possibilidade de construir uma identidade numa plataforma associada à sua instituição de ensino. Do estudo efetuado resultou ainda uma proposta de um modelo para a análise da identidade online, que poderá ser utilizado na análise da presença dos indivíduos em ambientes online formais e informais. Apresentando a identidade online como uma realidade assente na representação digital, na gestão da privacidade e na reputação construída na rede, o modelo foi aplicado aos dados recolhidos pelo estudo, conduzindo ao desenho de duas grandes formas de estar na rede: identidade orientada pelo contexto, e identidade orientada pelo utilizador. Quando as caraterísticas dos mundos digitais alteram a forma de produção da identidade e num cenário onde a contextualização de dados e informação assume uma importância crescente, este estudo de caso poderá contribuir para o conhecimento dos processos de construção da identidade em espaços formais e informais, da forma como os indivíduos gerem e constroem a sua identidade online, e ainda sobre a importância e o impacto da construção de uma identidade online consciente e credível para a reputação dos indivíduos e das Instituições de Ensino Superior.

As apostas desportivas online associadas à combinação de resultados

The present dissertation is aimed at finding out whether the existing criminal protection of the sports ethics value is sufficient, regarding the dangers arising from the global online sports betting market and its characteristics. In the first chapter, the main issue will be introduced: the association between online sports bets and competition manipulations from a criminal point of view. In the second chapter, online sports bets will be defined, the characteristics of the referred global market explained and the danger said features bear to the manipulation of sports competitions exposed – also analysing the participants in this phenomenon. In chapter 3, it will be shown that the protection of sports ethics is a matter of public interest and that this interest is carried out by the sports federations as well. In the fourth chapter, the focus will be the criminal protection of sports ethics: its necessity based on the penal dignity of this system of sport associated values; the need to re-evaluate the existing protection due to the recognition of the existence of the online sports betting market; the existing criminal norms regarding the manipulation of sports competitions. Finally, in chapter 5, the intent will be to propose solutions to the identified problems concerning the sufficiency of the existing criminal legislation.

Online Dispute Resolution: Some Implications for the Emergence of Law in Cyberspace

"L’auteur Ethan Katsh analyse les problématiques posées par les relations de la communauté virtuelle de l’Internet et son processus en ligne de résolution des conflits. Il explique comment le cyberespace constitue un environnement intégral et indépendant qui développe ses propres règles normatives. L’évolution des normes au sein du cyberespace semble être une conséquence des interactions entre les acteurs, sans intervention législative fondamentale de la part des états. L’auteur trace l’évolution, depuis le début des années 1990, du processus en ligne de résolution des différends, principalement dans le domaine du commerce électronique. L’accroissement rapide des relations commerciales électroniques a entraîné une hausse des litiges dans ce domaine. Dans le cadre de tels litiges, les moyens en ligne de résolution des conflits offrent aux justiciables plus de facilité, de flexibilité et d’accessibilité que les moyens alternatifs traditionnels de résolution des conflits. C’est donc dans ce contexte qu’a été développé le système ""Squaretrade"" qui a pour objectif d’aider la résolution de conflits entre les utilisateurs de ""E-Bay"". Ce système présente l’avantage important d’encadrer et d’uniformiser le processus de résolution en définissant les termes généraux et spécifiques du conflit. L’auteur soutient que la principale fonction d’un tel système est d’organiser et d’administrer efficacement les communications entre les parties. Ainsi, cette fonction préserve le ""paradigme de la quatrième personne"", nécessaire aux processus alternatifs traditionnels de résolution de conflits. Par ailleurs, cette fonction, en tant que partie intégrante du programme informatique, constitue pour les justiciables une alternative intéressante aux règles législatives. Pour l’auteur, l’analyse de ce phénomène soulève des questions importantes concernant la création de normes et leur acceptation par les citoyens. L’auteur analyse par la suite le concept général de la formation des normes dans le contexte d’un environnement non régularisé. Il soutient que les normes émergeantes doivent toujours viser à développer une forme de légitimité auprès des justiciables. Dans le cadre du processus en ligne de résolution des conflits, cette légitimité doit être acquise autant auprès des parties au litige qu’auprès de la population en général. Toutefois, les attentes des parties au litige sont souvent très différentes de celles du public. L’auteur illustre ainsi comment certains processus en ligne de résolution de conflit ne réussissent pas à obtenir une telle légitimité, alors que d’autres s’établissent en tant qu’institutions reconnues. Dans ce contexte, les institutions en ligne de résolution de conflits devront développer leur propre valeur normative. Ainsi, les moyens en ligne de résolution des conflits remettent en question le processus traditionnel de formation des normes et peuvent être considérés comme des éléments d’un nouvel environnement normatif."

HWR for Indian Languages: A Comprehensive Survey

Few major Research works are going in the field of Handwriting Word Recognition (HWR) of Indian languages. This paper surveys the major works of offline/online handwritten word recognition. Techniques involved in word recognition are also discussed. Major works carried out in Bangla, Urdu, Tamil and Hindi are mentioned in this paper. Advancement towards HWR in other Indian languages are also discussed. Application of offline HWR is also discussed