The principal objective of an image retrieval system is to obtain images which are as similar as possible to the user´s requirements, from all the images in the reference collection. Such an objective is difficult to reach due principally to the subjectivity of the image similarities. This is due to the fact the images can be interpreted in different ways by different people. With the aim of resolving this problem the content-based image retrieval systems explore the features of color, shape and texture. These are nearly always associated to the regions and use relevance feedback mechanisms to adjust a search to the user s criterions. Various approaches have been used in relevance feedback from those genetic algorithms have become quite popular due to their adaptive abilities. In this work we presented an image retrieval system based on the similarity of local patterns, working with the features of color, shape and texture as well as relevance feedback via a genetic algorithm. The task of this algorithm is infer weights to the features of color, shape, texture and regions which better adjust to the similarity found between images through the user s search criterions, thus producing a final ranking which is in accordance with the criterions expressed in the relevance feedback. The genetic algorithms theory states that the fitness measure applies an essential role upon the performance of these algorithms, once the fitness measure directs the search path for the evaluation of each individuals aptitude. Due to the lack of consensus about the best fitness measure in the ranking evaluation problem we present a performance analysis of ten fitness functions. The fitness functions are classified in two groups: order-based and non-order based. Some of these functions are adapted from textbased information retrieval systems and others are proposed in this work. The experimental results show that the order based fitness functions are more compatible to the user s interests, once they present superior rankings in terms of precision for low recall rates and conduct the quickest genetic algorithm in the search for an optimal heuristic solution. The results obtained are superior to those of the works of Stejic et al., which served as our inspiration. / O principal objetivo de um sistema de recuperação de imagens é obter imagens que são o mais similar possível à requisição do usuário, de todas as imagens de uma coleção de referência. Tal objetivo é difícil de ser alcançado devido principalmente à subjetividade do conceito de similaridade entre imagens, visto que uma mesma imagem poder ser interpretada de diferentes maneiras por diferentes pessoas. Na tentativa de resolver este problema os sistemas de recuperação de imagens por conteúdo exploram as características de cor, forma e textura, quase sempre associadas à regiões e usam de mecanismos de realimentação de relevantes para ajustar uma busca aos critérios do usuário. Várias abordagens têm sido usadas em realimentação de relevância entre as quais os algoritmos genéticos têm se tornado bastante populares devido às suas habilidades adaptativas. Neste trabalho apresentamos um sistema de recuperação de imagens com base na similaridade de padrões locais, empregando as características de cor, forma e textura e com realimentação de relevância via algoritmo genético. A tarefa do algoritmo genético é inferir pesos para as características de cor, forma, textura e regiões que melhor ajustam a medida de similaridade entre imagens aos critérios de busca do usuário, fazendo com que o ranking final esteja de acordo com os critérios expressos na realimentação. Da teoria dos algoritmos genéticos é conhecido que a medida de aptidão exerce um papel essencial na performance destes algoritmos, uma vez que ela direciona o caminho da busca, por avaliar a aptidão dos indivíduos. Devido à falta de consenso acerca da medida de aptidão ideal na avaliação de rankings apresentamos uma análise de performance de dez medidas de aptidão. As funções de aptidão são classificadas em dois grupos: baseadas em ordem e não baseadas em ordem. Algumas destas funções são adaptadas do contexto de sistemas de recuperação de informação e outras são propostas neste trabalho. Os resultados experimentais mostram que as funções de aptidão baseadas em ordem são mais compatíveis aos interesses dos usuários uma vez que elas apresentam rankings superiores em precisão para baixos níveis de revocação e, conduzem mais rapidamente o AG na busca por uma solução heurísticamente ótima. Os resultados obtidos são superiores aos dos trabalhos de Stejic et al. que nos serviram de inspiração. / Mestre em Ciência da Computação

O problema da descontinuidade semântica tem sido um dos principais focos de pesquisa no desenvolvimento de sistemas de recuperação de imagens baseada em conteúdo (CBIR). Neste contexto, as pesquisas mais promissoras focam principalmente na inferência de pesos de características contínuos e na seleção de características. Entretanto, os processos tradicionais de inferência de pesos contínuos são computacionalmente caros e a seleção de características equivale a uma ponderação binária. Visando tratar adequadamente o problema de lacuna semântica, este trabalho propõe dois métodos de transformação de espaço de características métricos baseados na inferência de funções de transformação por meio de algoritmo genético. O método WF infere funções de ponderação para ajustar a função de dissimilaridade e o método TF infere funções para transformação das características. Comparados às abordagens de inferência de pesos contínuos da literatura, ambos os métodos propostos proporcionam uma redução drástica do espaço de busca ao limitar a busca à escolha de um conjunto ordenado de funções de transformação. Análises visuais do espaço transformado e de gráficos de precisão vs. revocação confirmam que TF e WF superam a abordagem tradicional de ponderação de características. Adicionalmente, foi verificado que TF supera significativamente WF em termos de precisão dos resultados de consultas por similaridade por permitir transformação não lineares no espaço de característica, conforme constatado por análise visual. / The semantic gap problem has been a major focus of research in the development of content-based image retrieval (CBIR) systems. In this context, the most promising research focus primarily on the inference of continuous feature weights and feature selection. However, the traditional processes of continuous feature weighting are computationally expensive and feature selection is equivalent to a binary weighting. Aiming at alleviating the semantic gap problem, this master dissertation proposes two methods for the transformation of metric feature spaces based on the inference of transformation functions using Genetic Algorithms. The WF method infers weighting functions and the TF method infers transformation functions for the features. Compared to the existing methods, both proposed methods provide a drastic searching space reduction by limiting the search to the choice of an ordered set of transformation functions. Visual analysis of the transformed space and precision. vs. recall graphics confirm that both TF and WF outperform the traditional feature eighting methods. Additionally, we found that TF method significantly outperforms WF regarding the query similarity accuracy by performing non linear feature space transformation, as found in the visual analysis.

Europeana, a freely accessible digital library with an idea to make Europe's cultural and scientific heritage available to the public was founded by the European Commission in 2008. The goal was to deliver a semantically enriched digital content with multilingual access to it. Even though they managed to increase the content of data they slowly faced the problem of retrieving information in an unstructured form. So to complement the Europeana portal services, ASSETS (Advanced Search Service and Enhanced Technological Solutions) was introduced with services that sought to improve the usability and accessibility of Europeana. My contribution is to study different text-based information retrieval models, their relevance feedback techniques and to implement one simple model. The thesis explains a detailed overview of the information retrieval process along with the implementation of the chosen strategy for relevance feedback that generates automatic query expansion. Finally, the thesis concludes with the analysis made using relevance feedback, discussion on the model implemented and then an assessment on future use of this model both as a continuation of my work and using this model in ASSETS.

Les activités basées sur l'exploitation de données vidéo se sont développées de manière fulgurante ces dernières années : nous assisté à une démocratisation de certaines de ces activités (vidéo-surveillance) mais également à une diversification importante des applications opérationnelles (suivi de ressources naturelles, reconnaissance etc). Cependant, le volume de données vidéo généré est aujourd'hui astronomique et l'efficacité de ces activités est limitée par le coût et la durée nécessaire à l'interprétation humaine des données vidéo. L'analyse automatique de flux vidéos est donc devenue une problématique cruciale pour de nombreuses applications. L'approche semi-automatique développée dans le cadre de cette thèse se concentre plus spécifiquement sur l'analyse de vidéos aériennes, et permet d'assister l'analyste image dans sa tâche en suggérant des zones d'intérêt potentiel par détection de changements. Pour cela, nous effectuons une modélisation tridimensionnelle des apparences observées dans les vidéos de référence. Cette modélisation permet ensuite d'effectuer une détection en ligne des changements significatifs dans une nouvelle vidéo, en identifiant les déviations d'apparence par rapport aux modèles de référence. Des techniques spécifiques ont également été proposées pour effectuer l'estimation des paramètres d'acquisition ainsi que l'atténuation des effets de l'illumination. De plus, nous avons développé plusieurs techniques de consolidation permettant d'exploiter la connaissance a priori relative aux changements à détecter. L'intérêt et les bonnes performances de notre approche a été minutieusement démontré à l'aide de données réelles et synthétiques. / Business activities based on the use of video data have developed at a dazzling speed these last few years: not only has the market of some of these activities widely expanded (video-surveillance) but the operational applications have also greatly diversified (natural resources monitoring, intelligence etc). However, nowadays, the volume of generated data has become overwhelming and the efficiency of these activities is now limited by the cost and the time required by the human interpretation of this video data. Automatic analysis of video streams has hence become a critical problem for numerous applications. The semi-autmoatic approach developed in this thesis focuses more specifically on the automatic analysis of aerial videos and enables assisting the image analyst in his task by suggesting areas of potential interest identified using change detection. For that purpose, our approach proceeds to a tridimensional modeling of the appearances observed in the reference videos. Such a modeling then enables the online detection of significant changes in a new video, by identifying appearance deviations with respect to the reference models. Specific techniques have also been developed to estimate the acquisition parameters and to attenuate illumination effects. Moreover, we developed several consolidation techniques making use of a priori knowledge related to targeted changes, in order to improve detection accuracy. The interest and good performance of our change detection approach has been carefully demonstrated using both real and synthetical data.

Quand des humains cherchent des informations au sein de bases de connaissancesou de collections de documents, ils utilisent un système de recherche d’information(SRI) faisant office d’interface. Les utilisateurs doivent alors transmettre au SRI unereprésentation de leur besoin d’information afin que celui-ci puisse chercher des documentscontenant des informations pertinentes. De nos jours, la représentation du besoind’information est constituée d’un petit ensemble de mots-clés plus souvent connu sousla dénomination de « requête ». Or, quelques mots peuvent ne pas être suffisants pourreprésenter précisément et efficacement l’état cognitif complet d’un humain par rapportà son besoin d’information initial. Sans une certaine forme de contexte thématiquecomplémentaire, le SRI peut ne pas renvoyer certains documents pertinents exprimantdes concepts n’étant pas explicitement évoqués dans la requête.Dans cette thèse, nous explorons et proposons différentes méthodes statistiques, automatiqueset non supervisées pour la représentation du contexte thématique de larequête. Plus spécifiquement, nous cherchons à identifier les différents concepts implicitesd’une requête formulée par un utilisateur sans qu’aucune action de sa part nesoit nécessaire. Nous expérimentons pour cela l’utilisation et la combinaison de différentessources d’information générales représentant les grands types d’informationauxquels nous sommes confrontés quotidiennement sur internet. Nous tirons égalementparti d’algorithmes de modélisation thématique probabiliste (tels que l’allocationde Dirichlet latente) dans le cadre d’un retour de pertinence simulé. Nous proposonspar ailleurs une méthode permettant d’estimer conjointement le nombre de conceptsimplicites d’une requête ainsi que l’ensemble de documents pseudo-pertinent le plusapproprié afin de modéliser ces concepts. Nous évaluons nos approches en utilisantquatre collections de test TREC de grande taille. En annexes, nous proposons égalementune approche de contextualisation de messages courts exploitant des méthodesde recherche d’information et de résumé automatique / When searching for information within knowledge bases or document collections,humans use an information retrieval system (IRS). So that it can retrieve documentscontaining relevant information, users have to provide the IRS with a representationof their information need. Nowadays, this representation of the information need iscomposed of a small set of keywords often referred to as the « query ». A few wordsmay however not be sufficient to accurately and effectively represent the complete cognitivestate of a human with respect to her initial information need. A query may notcontain sufficient information if the user is searching for some topic in which she is notconfident at all. Hence, without some kind of context, the IRS could simply miss somenuances or details that the user did not – or could not – provide in query.In this thesis, we explore and propose various statistic, automatic and unsupervisedmethods for representing the topical context of the query. More specifically, we aim toidentify the latent concepts of a query without involving the user in the process norrequiring explicit feedback. We experiment using and combining several general informationsources representing the main types of information we deal with on a dailybasis while browsing theWeb.We also leverage probabilistic topic models (such as LatentDirichlet Allocation) in a pseudo-relevance feedback setting. Besides, we proposea method allowing to jointly estimate the number of latent concepts of a query andthe set of pseudo-relevant feedback documents which is the most suitable to modelthese concepts. We evaluate our approaches using four main large TREC test collections.In the appendix of this thesis, we also propose an approach for contextualizingshort messages which leverages both information retrieval and automatic summarizationtechniques