Abstract: Understanding the content of the images is one of the greatest challenges of computer vision. Recognition of objects appearing in images, identifying and interpreting their actions are the main purposes of Image Understanding. This thesis seeks to identify what is present in a picture by categorizing and locating all the objects in the scene.
Images are composed by pixels, and one possibility consists of assigning to each pixel an object category, which is commonly known as semantic segmentation. By incorporating information as a contextual cue, we are able to resolve the ambiguity within categories at the pixel-level. We propose three levels of scale in order to resolve such ambiguity.
Another possibility to represent the objects is the object detection task. In this case, the aim is to recognize and localize the whole object by accurately placing a bounding box around it. We present two new approaches. The first one is focused on improving the object representation of deformable part models with the concept of factorized appearances. The second approach addresses the issue of reducing the computational cost for multi-class recognition. The results given have been validated on several commonly used datasets, reaching international recognition and state-of-the-art within the field

Abstract: Feature matching is a fundamental problem in Computer Vision, having multiple applications such as tracking, image classification and retrieval, shape recognition and stereo fusion. In numerous domains, it is useful to represent the local structure of the matching features to increase the matching accuracy or to make the correspondence invariant to certain transformations (affine, homography, etc. . . ). However, encoding this knowledge requires complicating the model by establishing high-order relationships between the model elements, and therefore increasing the complexity of the optimization problem.
The importance of many-to-many matching is sometimes dismissed in the literature. Most methods are restricted to perform one-to-one matching, and are usually validated on synthetic, or non-realistic datasets. In a real challenging environment, with scale, pose and illumination variations of the object of interest, as well as the presence of occlusions, clutter, and noisy observations, many-to-many matching is necessary to achieve satisfactory results. As a consequence, finding the most likely many-to-many correspondence often involves a challenging combinatorial optimization process.
In this work, we design and demonstrate matching algorithms that compute many-to-many correspondences, applied to several challenging problems. Our goal is to make use of high-order representations to improve the expressive power of the matching, at the same time that we make feasible the process of inference or optimization of such models. We effectively use graphical models as our preferred representation because they provide an elegant probabilistic framework to tackle structured prediction problems.
We introduce a matching-based tracking algorithm which performs matching between frames of a video sequence in order to solve the difficult problem of headlight tracking at night-time. We also generalise this algorithm to solve the problem of data association applied to various tracking scenarios. We demonstrate the effectiveness of such approach in real video sequences and we show that our tracking algorithm can be used to improve the accuracy of a headlight classification system.
In the second part of this work, we move from single (point) matching to dense (region) matching and we introduce a new hierarchical image representation. We make use of such model to develop a high-order many-to-many matching between pairs of images. We show that the use of high-order models in comparison to simpler models improves not only the accuracy of the results, but also the convergence speed of the inference algorithm.
Finally, we keep exploiting the idea of region matching to design a fully unsupervised image co-segmentation algorithm that is able to perform competitively with state-of-the-art supervised methods. Our method also overcomes the typical drawbacks of some of the past works, such as avoiding the necessity of variate appearances on the image backgrounds. The region matching in this case is applied to effectively exploit inter-image information. We also extend this work to perform co-segmentation of videos, being the first time that such problem is addressed, as a way to perform video object segmentation

Abstract: Pattern recognition is the task that aims at distinguishing objects among different classes. When such a task wants to be solved in an automatic way a crucial step is how to formally represent such patterns to the computer. Based on the different representational formalisms, we may distinguish between statistical and structural pattern recognition. The former describes objects as a set of measurements arranged in the form of what is called a feature vector. The latter assumes that relations between parts of the underlying objects need to be explicitly represented and thus it uses relational structures such as graphs for encoding their inherent information. Vector spaces are a very flexible mathematical structure that has allowed to come up with several efficient ways for the analysis of patterns under the form of feature vectors. Nevertheless, such a representation cannot explicitly cope with binary relations between parts of the objects and it is restricted to measure the exact same number of features for each pattern under study regardless of their complexity. Graph-based representations present the contrary situation. They can easily adapt to the inherent complexity of the patterns but introduce a problem of high computational complexity, hindering the design of efficient tools to process and analyse patterns.
Solving this paradox is the main goal of this thesis. The ideal situation for solving pattern recognition problems would be to represent the patterns using relational structures such as graphs, and to be able to use the wealthy repository of data processing tools from the statistical pattern recognition domain. An elegant solution to this problem is to transform the graph domain into a vector domain where any processing algorithm can be applied. In other words, by mapping each graph to a point in a vector space we automatically get access to the rich set of algorithms from the statistical domain to be applied in the graph domain. Such methodology is called graph embedding.
In this thesis we propose to associate feature vectors to graphs in a simple and very efficient way by just putting attention on the labelling information that graphs store. In particular, we count frequencies of node labels and of edges between labels. Although their locality, these features are able to robustly represent structurally global properties of graphs, when considered together in the form of a vector. We initially deal with the case of discrete attributed graphs, where features are easy to compute. The continuous case is tackled as a natural generalization of the discrete one, where rather than counting node and edge labelling instances, we count statistics of some representatives of them. We encounter how the proposed vectorial representations of graphs suffer from high dimensionality and correlation among components and we face these problems by feature selection algorithms. We also explore how the diversity of different embedding representations can be exploited in order to boost the performance of base classifiers in a multiple classifier systems framework. An extensive experimental evaluation finally shows how the methodology we propose can be efficiently computed and compete with other graph matching and embedding methodologies.

Abstract: The release of challenging datasets with a vast number of images, requires the development of efficient image representations and algorithms which are able to manipulate these large-scale datasets efficiently. Nowadays the Bag-of-Words (BoW) is the most successful approach in the context of object and scene classification tasks. However, its main drawback is the absence of the important spatial information. Spatial pyramids (SP) have been successfully applied to incorporate spatial information into BoW-based image representation. Observing the remarkable performance of spatial pyramids, their growing number of applications to a broad range of vision problems, and finally its geometry inclusion, a question can be asked what are the limits of spatial pyramids. Within the SP framework, the optimal way for obtaining an image spatial representation, which is able to cope with it’s most foremost shortcomings, concretely, it’s high dimensionality and the rigidity of the resulting image representation, still remains an active research domain. In summary, the main concern of this thesis is to search for the limits of spatial pyramids and try to figure out solutions for them.

Abstract: he objective of this work is to show the importance of a good line segmentation to obtain better results in the segmentation of words of historical documents. We have used the approach developed by Manmatha and Rothfeder [1] to segment words in old handwritten documents. In their work the lines of the documents are extracted using projections. In this work, we have developed an approach to segment lines more efficiently. The new line segmentation algorithm tackles with skewed, touching and noisy lines, so it is significantly improves word segmentation. Experiments using Spanish documents from the Marriages Database of the Barcelona Cathedral show that this approach reduces the error rate by more than 20%

Abstract: Colour constancy is a perceptual mechanism that seeks to keep the colour of objects relatively stable under an illumination shift. Experiments haveshown that its effects depend on the number of colours present in the scene. We
studied categorical colour changes under different adaptation states, in particular, whether the colour categories seen under a chromatically neutral illuminant are the same after a shift in the chromaticity of the illumination. To do this, we developed the chromatic setting paradigm (2011 Journal of Vision11 349), which is as an extension of achromatic setting to colour categories. The paradigm exploits the ability of subjects to reliably reproduce the most representative examples of each category, adjusting multiple test patches embedded in a coloured Mondrian. Our experiments were run on a CRT monitor (inside a dark room) under various simulated illuminants and restricting the number of colours of the Mondrian background to three, thus weakening the adaptation effect. Our results show a change in the colour categories present before (under neutral illumination) and after adaptation (under coloured illuminants) with a tendency for adapted colours to be less saturated than before adaptation. This behaviour was predicted by a simple
affine matrix model, adjusted to the chromatic setting results.

Abstract: Human-machine interaction is a hot topic nowadays in the communities of computer vision and robotics. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. This is mostly due to the difficulty of simultaneously handling variations in illumination, pose, and occlusions. In this paper, we propose a novel approach for robust pose-invariant face recognition for human-robot interaction based on the real-time fitting of a 3D deformable model to input images taken from video sequences. More concrete, our approach generates a rectified face image irrespective with the actual head-pose orientation. Experimental results performed on Honda video database, using several manifold learning techniques, show a distinct advantage of the proposed method over the standard 2D appearance-based snapshot approach.