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: Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approaches or human motion analysis, etc. As far as we know, an overall review of this problem domain has yet to be provided. Furthermore, recent advancements based on deep learning have brought novel algorithms for this problem. In this paper, a comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements. Based on one standard pipeline for the solution of computer vision problems, this survey splits the problem into several modules: feature extraction and description, human body models, and modeling
methods. Problem modeling methods are approached based on two means of categorization in this survey. One way to categorize includes top-down and bottom-up methods, and another way includes generative and discriminative methods. Considering the fact that one direct application of human pose estimation is to provide initialization for automatic video surveillance, there are additional sections for motion-related methods in all modules: motion features, motion models, and motion-based methods. Finally, the paper also collects 26 publicly available data sets for validation and provides error measurement methods that are frequently used.

Abstract: In this paper we propose an original sparse vector model for symbol retrieval task. More specically, we apply the K-SVD algorithm for learning a visual dictionary based on symbol descriptors locally computed around interest points. Results on benchmark datasets show that the obtained sparse representation is competitive related to state-of-the-art methods. Moreover, our sparse representation is invariant to rotation and scale transforms and also robust to degraded images and distorted symbols. Thereby, the learned visual dictionary is able to represent instances of unseen classes of symbols.

Abstract: Recent methods for facial landmark location perform well on close-to-frontal faces but have problems in generalising to large head rotations. In order to address this issue we propose a second order linear regression method that is both compact and robust against strong rotations. We provide a closed form solution, making the method fast to train. We test the method’s performance on two challenging datasets. The first has been intensely used by the community. The second has been specially generated from a well known 3D face dataset. It is considerably more challenging, including a high diversity of rotations and more samples than any other existing public dataset. The proposed method is compared against state-of-the-art approaches, including RCPR, CGPRT, LBF, CFSS, and GSDM. Results upon both datasets show that the proposed method offers state-of-the-art performance on near frontal view data, improves state-of-the-art methods on more challenging head rotation problems and keeps a compact model size.

Abstract: In the context of human action recognition using skeleton data, the 3D trajectories of joint points may be considered as multi-dimensional time series. The traditional recognition technique in the literature is based on time series dis(similarity) measures (such as Dynamic Time Warping). For these general dis(similarity) measures, k-nearest neighbor algorithms are a natural choice. However, k-NN classifiers are known to be sensitive to noise and outliers. In this paper, a new class of Support Vector Machine that is applicable to trajectory classification, such as action recognition, is developed by incorporating an efficient time-series distances measure into the kernel function. More specifically, the derivative of Dynamic Time Warping (DTW) distance measure is employed as the SVM kernel. In addition, the pairwise proximity learning strategy is utilized in order to make use of non-positive semi-definite (PSD) kernels in the SVM formulation. The recognition results of the proposed technique on two action recognition datasets demonstrates the ourperformance of our methodology compared to the state-of-the-art methods. Remarkably, we obtained 89 % accuracy on the well-known MSRAction3D dataset using only 3D trajectories of body joints obtained by Kinect

Abstract: Best student paper award.
Pain detection using facial images is of critical importance in many Health applications. Since pain is a spatiotemporal process, recent works on this topic employ facial spatiotemporal features to detect pain. These systems extract such features from the entire area of the face. In this paper, we show that by employing super-pixels we can divide the face into three regions, in a way that only one of these regions (about one third of the face) contributes to the pain estimation and the other two regions can be discarded. The experimental results on the UNBCMcMaster database show that the proposed system using this single region outperforms state-of-the-art systems in detecting no-pain scenarios, while it reaches comparable results in detecting weak and severe pain scenarios.