Submitted by GUILHERME BRANDÃO MARTINS null (guilherme-bm@outlook.com) on 2016-06-09T18:22:45Z No. of bitstreams: 1 Dissertacao_Guilherme_Brandão_Martins.pdf: 11362535 bytes, checksum: c1da2ab3e80ead0846eae49d9a1bc40e (MD5) / Approved for entry into archive by Ana Paula Grisoto (grisotoana@reitoria.unesp.br) on 2016-06-13T17:06:19Z (GMT) No. of bitstreams: 1 martins_gb_me_sjrp.pdf: 11362535 bytes, checksum: c1da2ab3e80ead0846eae49d9a1bc40e (MD5) / Made available in DSpace on 2016-06-13T17:06:19Z (GMT). No. of bitstreams: 1 martins_gb_me_sjrp.pdf: 11362535 bytes, checksum: c1da2ab3e80ead0846eae49d9a1bc40e (MD5) Previous issue date: 2016-05-20 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Com os avanços relacionados às tecnologias de redes computacionais e armazenamento de dados observa-se que, atualmente, uma grande quantidade de conteúdo digital está sendo disponibilizada via internet, em especial por meio de redes sociais. A fim de explorar esse contexto, abordagens relacionadas ao processamento e apredizado de padrões em vídeos têm recebido crescente atenção nos últimos anos. Sistemas de recomendação de filmes, amplamente empregados em lojas virtuais, são umas das principais aplicações no que se refere aos avanços de pesquisa na área de processamento de vídeos. Com o objetivo de acelerar o processo de recomendação e redução de armazenamento, técnicas para classificação e sumarização de vídeos por meio de aprendizado de máquina têm sido utilizadas com o intuito de explorar conteúdo informativo e também redundante. Por meio de técnicas de agrupamento e descrição de dados, é possível identificar quadros-chave de um conjunto de amostras a fim de que, posteriormente, estes sejam usados para sumarização do vídeo. Além disso, por meio de bases de vídeos rotuladas, podemos classificar amostras de modo a organizá-las por gêneros de vídeo. O presente trabalho objetiva utilizar o classificador Floresta de Caminhos Ótimos para sumarização automática e classificação de vídeos por gênero, bem como o estudo de sua viabilidade nestes contextos. Os resultados obtidos mostram que o referido classificador obteve desempenhos bastante promissores e próximos à algumas das técnicas de sumarização automática e classificação de vídeos que, atualmente, representam o estado-da-arte no atual contexto. / Currently, a number of improvements related to computational networks and data storage technologies have allowed a considerable amount of digital content to be provided on the internet, mainly through social networks. In order to exploit this context, video processing and pattern recognition approaches have received a considerable attention in the last years. Movie recommendation systems are widely employed in virtual stores, thus being one of the main applications regarding to research advances in the video processing field. Aiming to boost the content recommendation and storage cutback, different video categorization and video summarization techniques have been applied to handle with more informative and redundant content. By availing clustering and data description techniques, it is possible to identify keyframes from a given sample collection in order to consider them as part of the video summarization process. Furthermore, through labeled video data collections it is possible to classify samples in order to arrange them by video genres. The main goal of this work is to employ the Optimum-Path Forest classifier in both video summarization and video genre classification processes as well as to conduct a viability study of such classifier in the aforementioned contexts. The results have shown this classifier can achieve promising performances, being very close in terms of summary quality and consistent recognition rates to some state-of-the-art video summarization and classification approaches.

Ces dernières années, avec l’apparition des sites tels que Youtube, Dailymotion ou encore Blip TV, le nombre de vidéos disponibles sur Internet aconsidérablement augmenté. Le volume des collections et leur absence de structure limite l’accès par le contenu à ces données. Le résumé automatique est un moyen de produire des synthèses qui extraient l’essentiel des contenus et les présentent de façon aussi concise que possible. Dans ce travail, nous nous intéressons aux méthodes de résumé vidéo par extraction, basées sur l’analyse du canal audio. Nous traitons les différents verrous scientifiques liés à cet objectif : l’extraction des contenus, la structuration des documents, la définition et l’estimation des fonctions d’intérêts et des algorithmes de composition des résumés. Sur chacun de ces aspects, nous faisons des propositions concrètes qui sont évaluées. Sur l’extraction des contenus, nous présentons une méthode rapide de détection de termes. La principale originalité de cette méthode est qu’elle repose sur la construction d’un détecteur en fonction des termes cherchés. Nous montrons que cette stratégie d’auto-organisation du détecteur améliore la robustesse du système, qui dépasse sensiblement celle de l’approche classique basée sur la transcription automatique de la parole.Nous présentons ensuite une méthode de filtrage qui repose sur les modèles à mixtures de Gaussiennes et l’analyse factorielle telle qu’elle a été utilisée récemment en identification du locuteur. L’originalité de notre contribution tient à l’utilisation des décompositions par analyse factorielle pour l’estimation supervisée de filtres opérants dans le domaine cepstral.Nous abordons ensuite les questions de structuration de collections de vidéos. Nous montrons que l’utilisation de différents niveaux de représentation et de différentes sources d’informations permet de caractériser le style éditorial d’une vidéo en se basant principalement sur l’analyse de la source audio, alors que la plupart des travaux précédents suggéraient que l’essentiel de l’information relative au genre était contenue dans l’image. Une autre contribution concerne l’identification du type de discours ; nous proposons des modèles bas niveaux pour la détection de la parole spontanée qui améliorent sensiblement l’état de l’art sur ce type d’approches.Le troisième axe de ce travail concerne le résumé lui-même. Dans le cadre du résumé automatique vidéo, nous essayons, dans un premier temps, de définir ce qu’est une vue synthétique. S’agit-il de ce qui le caractérise globalement ou de ce qu’un utilisateur en retiendra (par exemple un moment émouvant, drôle....) ? Cette question est discutée et nous faisons des propositions concrètes pour la définition de fonctions d’intérêts correspondants à 3 différents critères : la saillance, l’expressivité et la significativité. Nous proposons ensuite un algorithme de recherche du résumé d’intérêt maximal qui dérive de celui introduit dans des travaux précédents, basé sur la programmation linéaire en nombres entiers. / These last years, with the advent of sites such as Youtube, Dailymotion or Blip TV, the number of videos available on the Internet has increased considerably. The size and their lack of structure of these collections limit access to the contents. Sum- marization is one way to produce snippets that extract the essential content and present it as concisely as possible.In this work, we focus on extraction methods for video summary, based on au- dio analysis. We treat various scientific problems related to this objective : content extraction, document structuring, definition and estimation of objective function and algorithm extraction.On each of these aspects, we make concrete proposals that are evaluated.On content extraction, we present a fast spoken-term detection. The main no- velty of this approach is that it relies on the construction of a detector based on search terms. We show that this strategy of self-organization of the detector im- proves system robustness, which significantly exceeds the classical approach based on automatic speech recogntion.We then present an acoustic filtering method for automatic speech recognition based on Gaussian mixture models and factor analysis as it was used recently in speaker identification. The originality of our contribution is the use of decomposi- tion by factor analysis for estimating supervised filters in the cepstral domain.We then discuss the issues of structuring video collections. We show that the use of different levels of representation and different sources of information in or- der to characterize the editorial style of a video is principaly based on audio analy- sis, whereas most previous works suggested that the bulk of information on gender was contained in the image. Another contribution concerns the type of discourse identification ; we propose low-level models for detecting spontaneous speech that significantly improve the state of the art for this kind of approaches.The third focus of this work concerns the summary itself. As part of video summarization, we first try, to define what a synthetic view is. Is that what cha- racterizes the whole document, or what a user would remember (by example an emotional or funny moment) ? This issue is discussed and we make some concrete proposals for the definition of objective functions corresponding to three different criteria : salience, expressiveness and significance. We then propose an algorithm for finding the sum of the maximum interest that derives from the one introduced in previous works, based on integer linear programming.