Abstract: In this paper we present an industrial application for the automatic screening of incoming multi-page documents in a banking workflow aimed at determining whether these documents are properly signed or not. The proposed method is divided in three main steps. First individual pages are classified in order to identify the pages that should contain a signature. In a second step, we segment within those key pages the location where the signatures should appear. The last step checks whether the signatures are present or not. Our method is tested in a real large-scale environment and we report the results when checking two different types of real multi-page contracts, having in total more than 14,500 pages.

Abstract: Wireless Capsule Endoscopy (WCE) provides a new perspective of the small intestine, since it enables, for the first time, visualization of the entire organ. However, the long visual video analysis time, due to the large number of data in a single WCE study, was an important factor impeding the widespread use of the capsule as a tool for intestinal abnormalities detection. Therefore, the introduction of WCE triggered a new field for the application of computational methods, and in particular, of computer vision. In this paper, we follow the computational approach and come up with a new perspective on the small intestine motility problem. Our approach consists of three steps: first, we review a tool for the visualization of the motility information contained in WCE video; second, we propose algorithms for the characterization of two motility building-blocks: contraction detector and lumen size estimation; finally, we introduce an approach to detect segments of stable motility behavior. Our claims are supported by an evaluation performed with 10 WCE videos, suggesting that our methods ably capture the intestinal motility information.

Abstract: Breast cancer disease has recently been classified into four subtypes regarding the molecular properties of the affected tumor region. For each patient, an accurate diagnosis of the specific type is vital to decide the most appropriate therapy in order to enhance life prospects. Nowadays, advanced therapeutic diagnosis research is focused on gene selection methods, which are not robust enough. Hence, we hypothesize that computer vision algorithms can offer benefits to address the problem of discriminating among them through X-Ray images. In this paper, we propose a novel approach driven by texture feature descriptors and machine learning techniques. First, we segment the tumour part through an active contour technique and then, we perform a complete fractal analysis to collect qualitative information of the region of interest in the feature extraction stage. Finally, several supervised and unsupervised classifiers are used to perform multiclass classification of the aforementioned data. The experimental results presented in this paper support that it is possible to establish a relation between each tumor subtype and the extracted features of the patterns revealed on mammograms.

Abstract: Autonomous driving is a key factor for future mobility. Properly perceiving the environment of the vehicles is essential for a safe driving, which requires computing accurate geometric and semantic information in real-time. In this paper, we challenge state-of-the-art computer vision algorithms for building a perception system for autonomous driving. An inherent drawback in the computation of visual semantics is the trade-off between accuracy and computational cost. We propose to circumvent this problem by following an offline-online strategy. During the offline stage dense 3D semantic maps are created. In the online stage the current driving area is recognized in the maps via a re-localization process, which allows to retrieve the pre-computed accurate semantics and 3D geometry in realtime. Then, detecting the dynamic obstacles we obtain a rich understanding of the current scene. We evaluate quantitatively our proposal in the KITTI dataset and discuss the related open challenges for the computer vision community.

Abstract: Graph-based representations are experiencing a growing usage in visual recognition and retrieval due to their representational power in front of classical appearance-based representations in terms of feature vectors. Retrieving a query graph from a large dataset of graphs has the drawback of the high computational complexity required to compare the query and the target graphs. The most important property for a large-scale retrieval is the search time complexity to be sub-linear in the number of database examples. In this paper we propose a fast indexation formalism for graph retrieval. A binary embedding is defined as hashing keys for graph nodes. Given a database of labeled graphs, graph nodes are complemented with vectors of attributes representing their local context. Hence, each attribute counts the length of a walk of order k originated in a vertex with label l. Each attribute vector is converted to a binary code applying a binary-valued hash function. Therefore, graph retrieval is formulated in terms of finding target graphs in the database whose nodes have a small Hamming distance from the query nodes, easily computed with bitwise logical operators. As an application example, we validate the performance of the proposed methods in a handwritten word spotting scenario in images of historical documents.

Abstract: Document analysis is an active field of research, which can attain a complete understanding of the semantics of a given document. One example of the document understanding process is enabling a computer to identify the key elements of a comic book story and arrange them according to a predefined domain knowledge. In this study, we propose a knowledge-driven system that can interact with bottom-up and top-down information to progressively understand the content of a document. We model the comic book’s and the image processing domains knowledge for information consistency analysis. In addition, different image processing methods are improved or developed to extract panels, balloons, tails, texts, comic characters and their semantic relations in an unsupervised way.

Abstract: The first requisite of a robot to succeed in social interactions is accurate human localisation, i.e. subject detection and tracking. Later, it is estimated whether an interaction partner seeks attention, for example by interpreting the position and orientation of the body. In computer vision, these cues usually are obtained in colour images, whose qualities are degraded in ill illuminated social scenes. In these scenarios depth sensors offer a richer representation. Therefore, it is important to combine colour and depth information. The
second aspect that plays a fundamental role in the acceptance of social robots is their real-time-ability. Processing colour and depth images is computationally demanding. To overcome this we propose a parallelisation strategy of face detection and tracking based on two different architectures: message passing and shared memory. Our results demonstrate high accuracy in
low computational time, processing nine times more number of frames in a parallel implementation. This provides a real-time social robot interaction.

Abstract: Human multi-limb segmentation in RGB images has attracted a lot of interest in the research community because of the huge amount of possible applications in fields like Human-Computer Interaction, Surveillance, eHealth, or Gaming. Nevertheless, human multi-limb segmentation is a very hard task because of the changes in appearance produced by different points of view, clothing, lighting conditions, occlusions, and number of articulations of the human body. Furthermore, this huge pose variability makes the availability of large annotated datasets difficult. In this paper, we introduce the HuPBA8k+ dataset. The dataset contains more than 8000 labeled frames at pixel precision, including more than 120000 manually labeled samples of 14 different limbs. For completeness, the dataset is also labeled at frame-level with action annotations drawn from an 11 action dictionary which includes both single person actions and person-person interactive actions. Furthermore, we also propose a two-stage approach for the segmentation of human limbs. In a first stage, human limbs are trained using cascades of classifiers to be split in a tree-structure way, which is included in an Error-Correcting Output Codes (ECOC) framework to define a body-like probability map. This map is used to obtain a binary mask of the subject by means of GMM color modelling and GraphCuts theory. In a second stage, we embed a similar tree-structure in an ECOC framework to build a more accurate set of limb-like probability maps within the segmented user mask, that are fed to a multi-label GraphCut procedure to obtain final multi-limb segmentation. The methodology is tested on the novel HuPBA8k+ dataset, showing performance improvements in comparison to state-of-the-art approaches. In addition, a baseline of standard action recognition methods for the 11 actions categories of the novel dataset is also provided.