Abstract: Publication date: 2012/3/8

Abstract: We present a Bag-of-Visual-and-Depth-Words (BoVDW) model for gesture recognition, an extension of the Bag-of-Visual-Words (BoVW) model, that benefits from the multimodal fusion of visual and depth features. State-of-the-art RGB and depth features, including a new proposed depth descriptor, are analysed and combined in a late fusion fashion. The method is integrated in a continuous gesture recognition pipeline, where Dynamic Time Warping (DTW) algorithm is used to perform prior segmentation of gestures. Results of the method in public data sets, within our gesture recognition pipeline, show better performance in comparison to a standard BoVW model.

Abstract: Different studies have shown that languages from industrialized cultures
share a set of 11 basic colour terms: red, green, blue, yellow, pink, purple, brown, orange, black, white, and grey (Berlin & Kay, 1969, Basic Color Terms, University of California Press)( Kay & Regier, 2003, PNAS, 100, 9085-9089). Some of these studies have also reported the best representatives or focal values of each colour (Boynton and Olson, 1990, Vision Res. 30,1311–1317), (Sturges and Whitfield, 1995, CRA, 20:6, 364–376). Some further studies have provided us with fuzzy datasets for color naming by asking human observers to rate colours in terms of membership values (Benavente -et al-, 2006, CRA. 31:1, 48–56,). Recently, a computational model based on these human ratings has been developed (Benavente -et al-, 2008, JOSA-A, 25:10, 2582-2593). This computational model follows a fuzzy approach to assign a colour name to a particular RGB value. For example, a pixel with a value (255,0,0) will be named 'red' with membership 1, while a cyan pixel with a RGB value of (0, 200, 200) will be considered to be 0.5 green and 0.5 blue. In this work, we show how this colour naming paradigm can be applied to different computer vision tasks. In particular, we report results in colour constancy (Vazquez-Corral -et al-, 2012, IEEE TIP, in press) showing that the classical constraints on either illumination or surface reflectance can be substituted by
the statistical properties encoded in the colour names. [Supported by projects TIN2010-21771-C02-1, CSD2007-00018].

Abstract: In this paper, we propose a new approach to extract text regions from graphical documents. In our method, we first empirically construct two sequences of learned dictionaries for the text and graphical parts respectively. Then, we compute the sparse representations of all different sizes and non-overlapped document patches in these learned dictionaries. Based on these representations, each patch can be classified into the text or graphic category by comparing its reconstruction errors. Same-sized patches in one category are then merged together to define the corresponding text or graphic layers which are combined to createfinal text/graphic layer. Finally, in a post-processing step, text regions are further filtered out by using some learned thresholds.

Abstract: In this thesis we tackle the problem of automatic characterization of human coronary vessel in Intravascular Ultrasound (IVUS) image modality. The basis for the whole characterization process is machine learning applied to multi-class problems. In all the presented approaches, the Error-Correcting Output Codes (ECOC) framework is used as central element for the design of multi-class classifiers.
Two main topics are tackled in this thesis. First, the automatic detection of the vessel borders is presented. For this purpose, a novel context-aware classifier for multi-class classification of the vessel morphology is presented, namely ECOC-DRF. Based on ECOC-DRF, the lumen border and the media-adventitia border in IVUS are robustly detected by means of a novel holistic approach, achieving an error comparable with inter-observer variability and with state of the art methods.
The two vessel borders define the atheroma area of the vessel. In this area, tissue characterization is required. For this purpose, we present a framework for automatic plaque characterization by processing both texture in IVUS images and spectral information in raw Radio Frequency data. Furthermore, a novel method for fusing in-vivo and in-vitro IVUS data for plaque characterization is presented, namely pSFFS. The method demonstrates to effectively fuse data generating a classifier that improves the tissue characterization in both in-vitro and in-vivo datasets.
A novel method for automatic video summarization in IVUS sequences is also presented. The method aims to detect the key frames of the sequence, i.e., the frames representative of morphological changes. This novel method represents the basis for video summarization in IVUS as well as the markers for the partition of the vessel into morphological and clinically interesting events.
Finally, multi-class learning based on ECOC is applied to lung tissue characterization in Computed Tomography. The novel proposed approach, based on supervised and unsupervised learning, achieves accurate tissue classification on a large and heterogeneous dataset.

Abstract: Today, robust learners trained in a real supervised machine learning application should count with a rich collection of positive and negative examples. Although in many applications, it is not difficult to obtain huge amount of data, labeling those data can be a very expensive process, especially when dealing with data of high variability and complexity. A good example of such cases are data from medical imaging applications where annotating anomalies like tumors, polyps, atherosclerotic plaque or informative frames in wireless endoscopy need highly trained experts. Building a representative set of training data from medical videos (e.g. Wireless Capsule Endoscopy) means that thousands of frames to be labeled by an expert. It is quite normal that data in new videos come different and thus are not represented by the training set. In this paper, we review the main approaches on active learning and illustrate how active learning can help to reduce expert effort in constructing the training sets. We show that applying active learning criteria, the number of human interventions can be significantly reduced. The proposed system allows the annotation of informative/non-informative frames of Wireless Capsule Endoscopy video containing more than 30000 frames each one with less than 100 expert ”clicks”.