Abstract: Latest advances in digitization techniques have fostered the interest in creating digital copies of collections of documents. Digitized documents permit an easy maintenance, loss-less storage, and efficient ways for transmission and to perform information retrieval processes. This situation has opened a new market niche to develop systems able to automatically extract and analyze information contained in these collections, specially in the ambit of the business activity.
Due to the great variety of types of documents this is not a trivial task. For instance, the automatic extraction of numerical data from invoices differs substantially from a task of text recognition in historical documents. However, in order to extract the information of interest, is always necessary to identify the area of the document where it is located. In the area of Document Analysis we refer to this process as layout analysis, which aims at identifying and categorizing the different entities that compose the document, such as text regions, pictures, text lines, or tables, among others. To perform this task it is usually necessary to incorporate a prior knowledge about the task into the analysis process, which can be modeled by defining a set of contextual relations between the different entities of the document. The use of context has proven to be useful to reinforce the recognition process and improve the results on many computer vision tasks. It presents two fundamental questions: What kind of contextual information is appropriate for a given task, and how to incorporate this information into the models.
In this thesis we study several ways to incorporate contextual information to the task of document layout analysis, and to the particular case of handwritten text line segmentation. We focus on the study of Probabilistic Graphical Models and other mechanisms for this purpose, and propose several solutions to these problems. First, we present a method for layout analysis based on Conditional Random Fields. With this model we encode local contextual relations between variables, such as pair-wise constraints. Besides, we encode a set of structural relations between different classes of regions at feature level. Second, we present a method based on 2D-Probabilistic Context-free Grammars to encode structural and hierarchical relations. We perform a comparative study between Probabilistic Graphical Models and this syntactic approach. Third, we propose a method for structured documents based on Bayesian Networks to represent the document structure, and an algorithm based in the Expectation-Maximization to find the best configuration of the page. We perform a thorough evaluation of the proposed methods on two particular collections of documents: a historical collection composed of ancient structured documents, and a collection of contemporary documents. In addition, we present a general method for the task of handwritten text line segmentation. We define a probabilistic framework where we combine the EM algorithm with variational approaches for computing inference and parameter learning on a Markov Random Field. We evaluate our method on several collections of documents, including a general dataset of annotated administrative documents. Results demonstrate the applicability of our method to real problems, and the contribution of the use of contextual information to this kind of problems.

Abstract: Photorealistic virtual environments are crucial for developing and testing automated driving systems in a safe way during trials. As commercially available simulators are expensive and bulky, this paper presents a low-cost, extendable, and easy-to-use (LEE) virtual environment with the aim to highlight its utility for level 3 driving automation. In particular, an experiment is performed using the presented simulator to explore the influence of different variables regarding control transfer of the car after the system was driving autonomously in a highway scenario. The results show that the speed of the car at the time when the system needs to transfer the control to the human driver is critical.

Abstract: Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved.

Abstract: Motion perception is an amazing innate ability of the creatures on the planet. This adroitness entails a functional advantage that enables species to compete better in the wild. The motion perception ability is usually employed at different levels, allowing from the simplest interaction with the ’physis’ up to the most transcendental survival tasks. Among the five classical perception system , vision is the most widely used in the motion perception field. Millions years of evolution have led to a highly specialized visual system in humans, which is characterized by a tremendous accuracy as well as an extraordinary robustness. Although humans and an immense diversity of species can distinguish moving object with a seeming simplicity, it has proven to be a difficult and non trivial problem from a computational perspective. In the field of Computer Vision, the detection of moving objects is a challenging and fundamental research area. This can be referred to as the ’origin’ of vast and numerous vision-based research sub-areas. Nevertheless, from the bottom to the top of this hierarchical analysis, the foundations still relies on when and where motion has occurred in an image. Pixels corresponding to moving objects in image sequences can be identified by measuring changes in their values. However, a pixel’s value (representing a combination of color and brightness) could also vary due to other factors such as: variation in scene illumination, camera noise and nonlinear sensor responses among others. The challenge lies in detecting if the changes in pixels’ value are caused by a genuine object movement or not. An additional challenging aspect in motion detection is represented by moving cast shadows. The paradox arises because a moving object and its cast shadow share similar motion patterns. However, a moving cast shadow is not a moving object. In fact, a shadow represents a photometric illumination effect caused by the relative position of the object with respect to the light sources. Shadow detection methods are mainly divided in two domains depending on the application field. One normally consists of static images where shadows are casted by static objects, whereas the second one is referred to image sequences where shadows are casted by moving objects. For the first case, shadows can provide additional geometric and semantic cues about shape and position of its casting object as well as the localization of the light source. Although the previous information can be extracted from static images as well as video sequences, the main focus in the second area is usually change detection, scene matching or surveillance. In this context, a shadow can severely affect with the analysis and interpretation of the scene. The work done in the thesis is focused on the second case, thus it addresses the problem of detection and removal of moving cast shadows in video sequences in order to enhance the detection of moving object.

Abstract: It is very common to find different versions of the same music work in archives of Opera Theaters. These differences correspond to modifications and annotations from the musicians. From the musicologist point of view, these variations are very interesting and deserve study. This paper explores the alignment of music scores as a tool for automatically detecting the passages that contain such differences. Given the difficulties in the recognition of handwritten music scores, our goal is to align the music scores and at the same time, avoid the recognition of music elements as much as possible. After removing the staff lines, braces and ties, the bar lines are detected. Then, the bar units are described as a whole using the Blurred Shape Model. The bar units alignment is performed by using Dynamic Time Warping. The analysis of the alignment path is used to detect the variations in the music scores. The method has been evaluated on a subset of the CVC-MUSCIMA dataset, showing encouraging results.

Abstract: Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss-rate and inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing Decision Support Systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. We provide new baselines on this dataset by training standard fully convolutional networks (FCN) for semantic segmentation and significantly outperforming, without any further post-processing, prior results in endoluminal scene segmentation.

Abstract: This thesis addresses the problem of automatic scene text understanding in unconstrained conditions. In particular, we tackle the tasks of multi-language and arbitrary-oriented text detection, tracking, and script identification in natural scenes.
For this we have developed a set of generic methods that build on top of the basic observation that text has always certain key visual and structural characteristics that are independent of the language or script in which it is written. Text instances in any
language or script are always formed as groups of similar atomic parts, being them either individual characters, small stroke parts, or even whole words in the case of cursive text. This holistic (sumof-parts) and recursive perspective has lead us to explore different variants of the “segmentation and grouping” paradigm of computer vision.
Scene text detection methodologies are usually based in classification of individual regions or patches, using a priory knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organization through which
text emerges as a perceptually significant group of atomic objects.
In this thesis, we argue that the text detection problem must be posed as the detection of meaningful groups of regions. We address the problem of text detection in natural scenes from a hierarchical perspective, making explicit use of the recursive nature of text, aiming directly to the detection of region groupings corresponding to text within a hierarchy produced by an agglomerative similarity clustering process over individual regions. We propose an optimal way to construct such an hierarchy introducing a feature space designed to produce text group hypothese with high recall and a novel stopping rule combining a discriminative classifier and a probabilistic measure of group meaningfulness based in perceptual organization. Within this generic framework, we design a text-specific object proposals algorithm that, contrary to existing generic object proposals methods, aims directly to the detection of text regions groupings. For this, we abandon the rigid definition of “what is text” of traditional specialized text detectors, and move towards more fuzzy perspective of grouping-based object proposals methods.
Then, we present a hybrid algorithm for detection and tracking of scene text where the notion of region groupings plays also a central role. By leveraging the structural arrangement of text group components between consecutive frames we can improve
the overall tracking performance of the system.
Finally, since our generic detection framework is inherently designed for multi-language environments, we focus on the problem of script identification in order to build a multi-language end-toend reading system. Facing this problem with state of the art CNN classifiers is not straightforward, as they fail to address a key
characteristic of scene text instances: their extremely variable aspect ratio. Instead of resizing input images to a fixed size as in the typical use of holistic CNN classifiers, we propose a patch-based classification framework in order to preserve discriminative parts of the image that are characteristic of its class. We describe a novel method based on the use of ensembles of conjoined networks to jointly learn discriminative stroke-parts representations and their relative importance in a patch-based classification scheme.

Abstract: Award for the best interactive session
Defining color spaces that provide a good encoding of spatio-chromatic properties of color surfaces is an open problem in color science [8, 22]. Related to this, in computer vision the fusion of color with local image features has been studied and evaluated [16]. In human vision research, the cells which are selective to specific color hues along the visual pathway are also a focus of attention [7, 14]. In line with these research aims, in this paper we study how color is encoded in a deep Convolutional Neural Network (CNN) that has been trained on more than one million natural images for object recognition. These convolutional nets achieve impressive performance in computer vision, and rival the representations in human brain. In this paper we explore how color is represented in a CNN architecture that can give some intuition about efficient spatio-chromatic representations. In convolutional layers the activation of a neuron is related to a spatial filter, that combines spatio-chromatic representations. We use an inverted version of it to explore the properties. Using a series of unsupervised methods we classify different type of neurons depending on the color axes they define and we propose an index of color-selectivity of a neuron. We estimate the main color axes that emerge from this trained net and we prove that colorselectivity of neurons decreases from early to deeper layers.