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: Evaluation of driving performance is of utmost importance in order to reduce road accident rate. Since driving ability includes visual-spatial and operational attention, among others, head pose estimation of the driver is a crucial indicator of driving performance. This paper proposes a new automatic method for coarse and fine head's yaw angle estimation of the driver. We rely on a set of geometric features computed from just three representative facial keypoints, namely the center of the eyes and the nose tip. With these geometric features, our method combines two manifold embedding methods and a linear regression one. In addition, the method has a confidence mechanism to decide if the classification of a sample is not reliable. The approach has been tested using the CMU-PIE dataset and our own driver dataset. Despite the very few facial keypoints required, the results are comparable to the state-of-the-art techniques. The low computational cost of the method and its robustness makes feasible to integrate it in massive consume devices as a real time application.

Abstract: During face-to-face human interaction, nonverbal communication plays a fundamental role. A relevant aspect that takes part during social interactions is represented by mirroring, in which a person tends to mimic the non-verbal behavior (head and body gestures, vocal prosody, etc.) of the counterpart. In this paper, we introduce a computer vision-based system to detect mirroring in dyadic social interactions with the use of a wearable platform. In our context, mirroring is inferred as simultaneous head noddings displayed by the interlocutors. Our approach consists of the following steps: (1) facial features extraction; (2) facial features stabilization; (3) head nodding recognition; and (4) mirroring detection. Our system achieves a mirroring detection accuracy of 72% on a custom mirroring dataset.

Abstract: In paper based elections, manual tallies at polling station level produce myriads of documents. These documents share a common form-like structure and a reduced vocabulary worldwide. On the other hand, each tally sheet is filled by a different writer and on different countries, different scripts are used. We present a complete document analysis system for electoral tally sheet processing combining state of the art techniques with a new handwriting recognition subprocess based on unsupervised feature discovery with Variational Autoencoders and sequence classification with BLSTM neural networks. The whole system is designed to be script independent and allows a fast and reliable results consolidation process with reduced operational cost.

Abstract: Automated video and image analysis can be a very efficient tool to analyze
animal behavior based on sociality, especially in hard access environments
for researchers. The understanding of this social behavior can play a key role in the sustainable design of capture policies of many species. This paper proposes the use of computer vision algorithms to identify and track a specific specie, the Norway lobster, Nephrops norvegicus, a burrowing decapod with relevant commercial value which is captured by trawling. These animals can only be captured when are engaged in seabed excursions, which are strongly related with their social behavior.
This emergent behavior is modulated by the day-night cycle, but their social
interactions remain unknown to the scientific community. The paper introduces an identification scheme made of four distinguishable black and white tags (geometric shapes). The project has recorded 15-day experiments in laboratory pools, under monochromatic blue light (472 nm.) and darkness conditions (recorded using Infra Red light). Using this massive image set, we propose a comparative of state-ofthe-art computer vision algorithms to distinguish and track the different animals’ movements. We evaluate the robustness to the high noise presence in the infrared video signals and free out-of-plane rotations due to animal movement. The experiments show promising accuracies under a cross-validation protocol, being adaptable to the automation and analysis of large scale data. In a second contribution, we created an extensive dataset of shapes (46027 different shapes) from four daily experimental video recordings, which will be available to the community.