Abstract: The comprehension of animal behavior, especially human behavior, is one of the most ancient and studied problems since the beginning of civilization. The big list of factors that interact to determine a person action require the collaboration of different disciplines, such as psichology, biology, or sociology. In the last years the analysis of human behavior has received great attention also from the computer vision community, given the latest advances in the acquisition of human motion data from image sequences.
Despite the increasing availability of that data, there still exists a gap towards obtaining a conceptual representation of the obtained observations. Human behavior analysis is based on a qualitative interpretation of the results, and therefore the assignment of concepts to quantitative data is linked to a certain ambiguity.
This Thesis tackles the problem of obtaining a proper representation of human behavior in the contexts of computer vision and animation. On the one hand, a good behavior model should permit the recognition and explanation the observed activity in image sequences. On the other hand, such a model must allow the generation of new synthetic instances, which model the behavior of virtual agents.
First, we propose methods to automatically learn the models from observations. Given a set of quantitative results output by a vision system, a normal behavior model is learnt. This results provides a tool to determine the normality or abnormality of future observations. However, machine learning methods are unable to provide a richer description of the observations. We confront this problem by means of a new method that incorporates prior knowledge about the enviornment and about the expected behaviors. This framework, formed by the reasoning engine FMTL and the modeling tool SGT allows the generation of conceptual descriptions of activity in new image sequences. Finally, we demonstrate the suitability of the proposed framework to simulate behavior of virtual agents, which are introduced into real image sequences and interact with observed real agents, thereby easing the generation of augmented reality sequences.
The set of approaches presented in this Thesis has a growing set of potential applications. The analysis and description of behavior in image sequences has its principal application in the domain of smart video--surveillance, in order to detect suspicious or dangerous behaviors. Other applications include automatic sport commentaries, elderly monitoring, road traffic analysis, and the development of semantic video search engines. Alternatively, behavioral virtual agents allow to simulate accurate real situations, such as fires or crowds. Moreover, the inclusion of virtual agents into real image sequences has been widely deployed in the games and cinema industries.

Abstract: Ever since computers were invented, we have wondered whether they might perform some of the human quotidian tasks. One of the most studied and still nowadays less understood problem is the capacity to learn from our experiences and how we generalize the knowledge that we acquire. One of that unaware tasks for the persons and that more interest is awakening in different scientific areas since the beginning, is the one that is known as pattern recognition. The creation of models that represent the world that surrounds us, help us for recognizing objects in our environment, to predict situations, to identify behaviors... All this information allows us to adapt ourselves and to interact with our environment. The capacity of adaptation of individuals to their environment has been related to the amount of patterns that are capable of identifying.
This thesis faces the pattern recognition problem from a Computer Vision point of view, taking one of the most paradigmatic and extended approaches to object detection as starting point. After studying this approach, two weak points are identified: The first makes reference to the description of the objects, and the second is a limitation of the learning algorithm, which hampers the utilization of best descriptors.
In order to address the learning limitations, we introduce evolutionary computation techniques to the classical object detection approach.
After testing the classical evolutionary approaches, such as genetic algorithms, we develop a new learning algorithm based on Probabilistic Darwin Machines, which better adapts to the learning problem. Once the learning limitation is avoided, we introduce a new feature set, which maintains the benefits of the classical feature set, adding the ability to describe non localities. This combination of evolutionary learning algorithm and features is tested on different public data sets, outperforming the results obtained by the classical approach.

Abstract: Usually, pattern recognition systems consist of two main parts. On the one hand, the data acquisition and, on the other hand, the classification of this data on a certain category. In order to recognize which category a certain query element belongs to, a set of pattern models must be provided beforehand. An off-line learning stage is needed to train the classifier and to offer a robust classification of the patterns. Within the pattern recognition field, we are interested in the recognition of graphics and, in particular, on the analysis of documents rich in graphical information. In this context, one of the main concerns is to see if the proposed systems remain scalable with respect to the data volume so as it can handle growing amounts of symbol models. In order to avoid to work with a database of reference symbols, symbol spotting and on-the-fly symbol recognition methods have been introduced in the past years.
Generally speaking, the symbol spotting problem can be defined as the identification of a set of regions of interest from a document image which are likely to contain an instance of a certain queriedn symbol without explicitly applying the whole pattern recognition scheme. Our application framework consists on indexing a collection of graphic-rich document images. This collection is
queried by example with a single instance of the symbol to look for and, by means of symbol spotting methods we retrieve the regions of interest where the symbol is likely to appear within the documents. This kind of applications are known as focused retrieval methods.
In order that the focused retrieval application can handle large collections of documents there is a need to provide an efficient access to the large volume of information that might be stored. We use indexing strategies in order to efficiently retrieve by similarity the locations where a certain part of the symbol appears. In that scenario, graphical patterns should be used as indices for accessing and navigating the collection of documents.
These indexing mechanism allow the user to search for similar elements using graphical information rather than textual queries.
Along this thesis we present a spotting architecture and different methods aiming to build a complete focused retrieval application dealing with a graphic-rich document collections. In addition, a protocol to evaluate the performance of symbol
spotting systems in terms of recognition abilities, location accuracy and scalability is proposed.

Abstract: Handwritten word-spotting (HWS) is the pattern analysis task that consists in finding keywords in handwritten document images. So far, HWS has been applied mostly to historical documents in order to build search engines for such image collections. This thesis addresses the problem of word-spotting for detecting important keywords in business documents. This is a first step towards the process of automatic routing of correspondence based on content.
However, the application of traditional HWS techniques fails for this type of documents. As opposed to historical documents, real business documents present a very high variability in terms of writing styles, spontaneous writing, crossed-out words, spelling mistakes, etc. The main goal of this thesis is the development of pattern recognition techniques that lead to a high-performance HWS system for this challenging type of data.
We develop a statistical framework in which word models are expressed in terms of hidden Markov models and the a priori information is encoded in a universal vocabulary of Gaussian codewords. This systems leads to a very robust performance in word-spotting task. We also find that by constraining the word models to the universal vocabulary, the a priori information of the problem of interest can be exploited for developing new contributions. These include a novel writer adaptation method, a system for searching handwritten words by generating typed text images, and a novel model-based similarity between feature vector sequences.

Abstract: Cardiovascular Diseases, specially those affecting the Left Ventricle (LV), are the leading cause of death in developed countries with approximately a 30% of all global deaths. In order to address this public health concern, physicians focus on diagnosis and therapy planning. On one hand, early and accurate detection of Regional Wall Motion Abnormalities (RWMA) significantly contributes to a quick diagnosis and prevents the patient to reach more severe stages. On the other hand, a thouroughly knowledge of the normal gross anatomy of the LV, as well as, the distribution of its muscular fibers is crucial for designing specific interventions and therapies (such as pacemaker implanction). Statistical models obtained from the analysis of different imaging modalities allow the computation of the normal ranges of variation within a given population. Normality models are a valuable tool for the definition of objective criterions quantifying the degree of (anomalous) deviation of the LV function and anatomy for a given subject. The creation of statistical models involve addressing three main issues: extraction of data from images, definition of a common domain for comparison of data across patients and designing appropriate statistical analysis schemes. In this PhD thesis we present generic image processing tools for the creation of statistical models of the LV anatomy and function. On one hand, we use differential geometry concepts to define a computational framework (the Normalized Parametric Domain, NPD) suitable for the comparison and fusion of several clinical scores obtained over the LV. On the other hand, we present a variational approach (the Harmonic Phase Flow, HPF) for the estimation of myocardial motion that provides dense and continuous vector fields without overestimating motion at injured areas. These tools are used for the creation of statistical models. Regarding anatomy, we obtain an atlas jointly modelling, both, LV gross anatomy and fiber architecture. Regarding function, we compute normality patterns of scores characterizing the (global and local) LV function and explore, for the first time, the configuration of local scores better suited for RWMA detection.

Abstract: Video alignment consists of integrating multiple video sequences recorded independently into a single video sequence. This means to register both in time (synchronize
frames) and space (image registration) so that the two videos sequences can be fused
or compared pixel–wise. In spite of being relatively unknown, many applications today may benefit from the availability of robust and efficient video alignment methods.
For instance, video surveillance requires to integrate video sequences that are recorded
of the same scene at different times in order to detect changes. The problem of aligning videos has been addressed before, but in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, most works rely
on restrictive assumptions which reduce its difficulty such as linear time correspondence or the knowledge of the complete trajectories of corresponding scene points on the images; to some extent, these assumptions limit the practical applicability of the solutions developed until now. In this thesis, we focus on the challenging problem of aligning sequences recorded at different times from independent moving cameras following similar but not coincident trajectories. More precisely, this thesis covers four studies that advance the state-of-the-art in video alignment. First, we focus on analyzing and developing a probabilistic framework for video alignment, that is, a principled way to integrate multiple observations and prior information. In this way, two different approaches are presented to exploit the combination of several purely visual features (image–intensities, visual words and dense motion field descriptor), and
global positioning system (GPS) information. Second, we focus on reformulating the
problem into a single alignment framework since previous works on video alignment
adopt a divide–and–conquer strategy, i.e., first solve the synchronization, and then
register corresponding frames. This also generalizes the ’classic’ case of fixed geometric transform and linear time mapping. Third, we focus on exploiting directly the
time domain of the video sequences in order to avoid exhaustive cross–frame search.
This provides relevant information used for learning the temporal mapping between
pairs of video sequences. Finally, we focus on adapting these methods to the on–line
setting for road detection and vehicle geolocation. The qualitative and quantitative
results presented in this thesis on a variety of real–world pairs of video sequences show that the proposed method is: robust to varying imaging conditions, different image
content (e.g., incoming and outgoing vehicles), variations on camera velocity, and
different scenarios (indoor and outdoor) going beyond the state–of–the–art. Moreover, the on–line video alignment has been successfully applied for road detection and
vehicle geolocation achieving promising results.

Abstract: Put succinctly, the bag-of-words based image representation is the most successful approach for object and scene recognition. Within the bag-of-words framework the optimal fusion of multiple cues, such as shape, texture and color, still remains an active research domain. There exist two main approaches to combine color and shape information within the bag-of-words framework. The first approach called, early fusion, fuses color and shape at the feature level as a result of which a joint colorshape vocabulary is produced. The second approach, called late fusion, concatenates histogram representation of both color and shape, obtained independently. In the first part of this thesis, we analyze the theoretical implications of both early and late feature fusion. We demonstrate that both these approaches are suboptimal for a subset of object categories. Consequently, we propose a novel method for recognizing object categories when using multiple cues by separately processing the shape and color cues and combining them by modulating the shape features by category specific color attention. Color is used to compute bottom-up and top-down attention maps. Subsequently, the color attention maps are used to modulate the weights of the shape features. Shape features are given more weight in regions with higher attention and vice versa. The approach is tested on several benchmark object recognition data sets and the results clearly demonstrate the effectiveness of our proposed method. In the second part of the thesis, we investigate the problem of obtaining compact spatial pyramid representations for object and scene recognition. Spatial pyramids have been successfully applied to incorporate spatial information into bag-of-words based image representation. However, a major drawback of spatial pyramids is that it leads to high dimensional image representations. We present a novel framework for obtaining compact pyramid representation. The approach reduces the size of a high dimensional pyramid representation upto an order of magnitude without any significant reduction in accuracy. Moreover, we also investigate the optimal combination of multiple features such as color and shape within the context of our compact pyramid representation. Finally, we describe a novel technique to build discriminative visual words from multiple cues learned independently from training images. To this end, we use an information theoretic vocabulary compression technique to find discriminative combinations of visual cues and the resulting visual vocabulary is compact, has the cue binding property, and supports individual weighting of cues in the final image representation. The approach is tested on standard object recognition data sets. The results obtained clearly demonstrate the effectiveness of our approach.