Abstract: In the recent years commercial eye-tracking hardware has become more common, with the introduction of new models from several brands that have better performance and easier setup procedures. A cause and at the same time a result of this phenomenon is the popularity of eye-tracking research directed at marketing, accessibility and usability, among others.
One problem with these hardware components is scalability, because both the price and the necessary expertise to operate them makes it practically impossible in the large scale. In this work, we analyze the feasibility of a software eye-tracking system based on a single, ordinary webcam. Our aim is to discover the limits of such a system and to see whether it provides acceptable performances.
The significance of this setup is that it is the most common setup found in consumer environments, off-the-shelf electronic devices such as laptops, mobile phones and tablet computers. As no special equipment such as infrared lights, mirrors or zoom lenses are used; setting up and calibrating the system is easier compared to other approaches using these components.
Our work is based on the open source application Opengazer, which provides a good starting point for our contributions. We propose several improvements in order to push the system's performance further and make it feasible as a robust, real-time device. Then we carry out an elaborate experiment involving 18 human subjects and 4 different system setups. Finally, we give an analysis of the results and discuss the effects of setup changes, subject differences and modifications in the software.

Abstract: Eye tracker devices have traditionally been only used inside laboratories, requiring trained professionals and elaborate setup mechanisms. However, in the recent years the scientific work on easier–to–use eye trackers which require no special hardware—other than the omnipresent front facing cameras in computers, tablets, and mobiles—is aiming at making this technology common–place. These types of trackers have several extra challenges that make the problem harder, such as low resolution images provided by a regular webcam, the changing ambient lighting conditions, personal appearance differences, changes in head pose, and so on. Recent research in the field has focused on all these challenges in order to provide better gaze estimation performances in a real world setup.
In this work, we aim at tackling the gaze tracking problem in a single camera setup. We first analyze all the previous work in the field, identifying the strengths and weaknesses of each tried idea. We start our work on the gaze tracker with an appearance–based gaze estimation method, which is the simplest idea that creates a direct mapping between a rectangular image patch extracted around the eye in a camera image, and the gaze point (or gaze direction). Here, we do an extensive analysis of the factors that affect the performance of this tracker in several experimental setups, in order to address these problems in future works. In the second part of our work, we propose a feature–based gaze estimation method, which encodes the eye region image into a compact representation. We argue that this type of representation is better suited to dealing with head pose and lighting condition changes, as it both reduces the dimensionality of the input (i.e. eye image) and breaks the direct connection between image pixel intensities and the gaze estimation. Lastly, we use a face alignment algorithm to have robust face pose estimation, using a 3D model customized to the subject using the tracker. We combine this with a convolutional neural network trained on a large dataset of images to build a face pose invariant gaze tracker.

Abstract: Recent advances in thermal infrared imaging (LWIR) has allowed its use in applications beyond of the military domain. Nowadays, this new family of sensors is included in different technical and scientific applications. They offer features that facilitate tasks, such as detection of pedestrians, hot spots, differences in temperature, among others, which can significantly improve the performance of a system where the persons are expected to play the principal role. For instance, video surveillance applications, monitoring, and pedestrian detection.
During this dissertation the next question is stated: Could a couple of sensors measuring different bands of the electromagnetic spectrum, as the visible and thermal infrared, be used to extract depth information? Although it is a complex question, we shows that a system of these characteristics is possible as well as their advantages, drawbacks, and potential opportunities.
The matching and fusion of data coming from different sensors, as the emissions registered at visible and infrared bands, represents a special challenge, because it has been showed that theses signals are weak correlated. Therefore, many traditional techniques of image processing and computer vision are not helpful, requiring adjustments for their correct performance in every modality.
In this research an experimental study that compares different cost functions and matching approaches is performed, in order to build a multimodal stereovision system. Furthermore, the common problems in infrared/visible stereo, specially in the outdoor scenes are identified. Our framework summarizes the architecture of a generic stereo algorithm, at different levels: computational, functional, and structural, which can be extended toward high-level fusion (semantic) and high-order (prior).The proposed framework is intended to explore novel multimodal stereo matching approaches, going from sparse to dense representations (both disparity and depth maps). Moreover, context information is added in form of priors and assumptions. Finally, this dissertation shows a promissory way toward the integration of multiple sensors for recovering three-dimensional information.

Abstract: Colorectal cancer is the fourth most common cause of cancer death worldwide and its survival rate depends on the stage in which it is detected on hence the necessity for an early colon screening. There are several screening techniques but colonoscopy is still nowadays the gold standard, although it has some drawbacks such as the miss rate. Our contribution, in the field of intelligent systems for colonoscopy, aims at providing a polyp localization and a polyp segmentation system based on a model of appearance for polyps. To develop both methods we define a model of appearance for polyps, which describes a polyp as enclosed by intensity valleys. The novelty of our contribution resides on the fact that we include in our model aspects of the image formation and we also consider the presence of other elements from the endoluminal scene such as specular highlights and blood vessels, which have an impact on the performance of our methods. In order to develop our polyp localization method we accumulate valley information in order to generate energy maps, which are also used to guide the polyp segmentation. Our methods achieve promising results in polyp localization and segmentation. As we want to explore the usability of our methods we present a comparative analysis between physicians fixations obtained via an eye tracking device and our polyp localization method. The results show that our method is indistinguishable to novice physicians although it is far from expert physicians.

Abstract: Despite the “paperless office” ideal that started in the decade of the seventies, businesses still strive against an increasing amount of paper documentation. Companies still receive huge amounts of paper documentation that need to be analyzed and processed, mostly in a manual way. A solution for this task consists in, first, automatically scanning the incoming documents. Then, document images can be analyzed and information can be extracted from the data. Documents can also be automatically dispatched to the appropriate workflows, used to retrieve similar documents in the dataset to transfer information, etc.
Due to the nature of this “digital mailroom”, we need document representation methods to be general, i.e., able to cope with very different types of documents. We need the methods to be sound, i.e., able to cope with unexpected types of documents, noise, etc. And, we need to methods to be scalable, i.e., able to cope with thousands or millions of documents that need to be processed, stored, and consulted. Unfortunately, current techniques of document representation, classification and retrieval are not apt for this digital mailroom framework, since they do not fulfill some or all of these requirements.
Through this thesis we focus on the problem of document representation aimed at classification and retrieval tasks under this digital mailroom framework. We first propose a novel document representation based on runlength histograms, and extend it to cope with more complex documents such as multiple-page documents, or documents that contain more sources of information such as extracted OCR text. Then we focus on the scalability requirements and propose a novel binarization method which we dubbed PCAE, as well as two general asymmetric distances between binary embeddings that can significantly improve the retrieval results at a minimal extra computational cost. Finally, we note the importance of supervised learning when performing large-scale retrieval, and study several approaches that can significantly boost the results at no extra cost at query time.

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: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.