Juan José Villanueva

Symbol recognition by error-tolerant subgraph matching between region adjacency graphs

We propose an error-tolerant subgraph isomorphism algorithm formulated in terms of region adjacency graphs (RAG). A set of edit operations to transform one RAG into another one are defined as regions are represented by polylines and string matching techniques are used to measure their similarity. The algorithm follows a branch and bound approach driven by the RAG edit operations. This formulation allows matching computing under distorted inputs and also reaching a solution in a near polynomial time. The algorithm has been used for recognizing symbols in hand drawn diagrams.

Evaluation of methods for ridge and valley detection

Ridges and valleys are useful geometric features for image analysis. Different characterizations have been proposed to formalize the intuitive notion of ridge/valley. In this paper, we review their principal characterizations and propose a new one. Subsequently, we evaluate these characterizations with respect to a list of desirable properties and their purpose in the context of representative image analysis tasks.

Multilocal creaseness based on the level-set extrinsic curvature

Abstract Creases are a type of ridge/valley structures of an image characterized by local conditions. As creases tend to be at the center of anisotropic grey-level shapes, creaseness can be considered a measure of medialness, and therefore as useful in many image analysis problems. Among the several possibilities, a priori the creaseness based on the level-set extrinsic curvature (LSEC) is especially interesting due to its invariance properties. However, in practice, it produces a discontinuous response with a badly dynamic range. The same problems arise with other related creaseness measures proposed in the literature. In this paper, we argue that these problems are due to the very local definition of the LSEC. Therefore, rather than designing an ad hoc solution, we propose two new multilocal creaseness measures that we will show to be free of discontinuities and to have a meaningful dynamic range of response. Still, these measures are based on the LSEC idea, to preserve its invariance properties. We demonstrate the usefulness of the new creaseness measures in the context of two applications that we are currently developing in the field of 3D medical image analysis, the rigid registration of CT and MR head volumes and the orientation analysis of trabecular bone patterns.

3D curve reconstruction by biplane snakes

Stent implantation for coronary disease treatment is a highly important minimally invasive technique that avoids surgery interventions. In order to assure the success of such an intervention, it is very important to determine the real length of the lesion as exactly as possible. Currently, lesion measures are performed directly from the angiography without considering the system projective parameters or, alternatively, from the 3D reconstruction obtained from a correspondence of points defined by the physicians. In this paper, we present a method for 3D vessel reconstruction from biplane images by means of deformable models. In particular, we study the known shortcoming of point-based 3D vessel reconstruction (no intersection of projective beams) and illustrate that by using snakes the reconstruction error is minimal. We validate out method by a computer-generated phantom, a real phantom and coronary vessels.

Tracking elongated structures using statistical snakes

In this paper we introduce a statistic snake that learns and tracks image features by means of statistic learning techniques. Using probabilistic principal component analysis a feature description is obtained from a training set of object profiles. In our approach a sound statistical model is introduced to define a likelihood estimate of the grey-level local image profiles together with their local orientation. This likelihood estimate allows to define a probabilistic potential field of the snake where the elastic curve deforms to maximise the overall probability of detecting learned image features. To improve the convergence of snake deformation, we enhance the likelihood map by a physics-based model simulating a dipole-dipole interaction. A new extended local coherent interaction is introduced defined in terms of extended structure tensor of the image to give priority to parallel coherence vectors.

Recursive coarse-to-fine localization for fast object detection

Cascading techniques are commonly used to speed-up the scan of an image for object detection. However, cascades of detectors are slow to train due to the high number of detectors and corresponding thresholds to learn. Furthermore, they do not use any prior knowledge about the scene structure to decide where to focus the search. To handle these problems, we propose a new way to scan an image, where we couple a recursive coarse-to-fine refinement together with spatial constraints of the object location. For doing that we split an image into a set of uniformly distributed neighborhood regions, and for each of these we apply a local greedy search over feature resolutions. The neighborhood is defined as a scanning region that only one object can occupy. Therefore the best hypothesis is obtained as the location with maximum score and no thresholds are needed. We present an implementation of our method using a pyramid of HOG features and we evaluate it on two standard databases, VOC2007 and INRIA dataset. Results show that the Recursive Coarse-to-Fine Localization (RCFL) achieves a 12x speed-up compared to standard sliding windows. Compared with a cascade of multiple resolutions approach our method has slightly better performance in speed and Average-Precision. Furthermore, in contrast to cascading approach, the speed-up is independent of image conditions, the number of detected objects and clutter.

Unconstrained multiple-people tracking

This work presents two main contributions to achieve robust multiple-target tracking in uncontrolled scenarios. A novel system which consists on a hierarchical architecture is proposed. Each level is devoted to one of the main tracking functionalities: target detection, low-level tracking, and high-level tasks such as target-appearance representation, or event management. Secondly, tracking performances are enhanced by on-line building and updating multiple appearance models. Successful experimental results are accomplished on sequences with significant illumination changes, grouping, splitting and occlusion events.

aSpaces: Action Spaces for Recognition and Synthesis of Human Actions

Human behavior analysis is an open problem in the computer vision community. The aim of this paper is to model human actions. We present a taxonomy in order to discuss about a knowledge-based classification of human behavior. A novel human action model is presented, called the aSpace, based on a Point Distribution Model (PDM). This representation is compact, accurate and specific. The human body model is represented as a stick figure, and several sequences of humans actions are used to compute the aSpace. In order to test our action representation, two applications are provided: recognition and synthesis of actions.

Topological principal component analysis for face encoding and recognition

Abstract Principal component analysis (PCA)-like methods make use of an estimation of the covariances between sample variables. This estimation does not take into account their topological relationships. This paper proposes how to use these relationships in order to estimate the covariances in a more robust way. The new method topological principal component analysis (TPCA) is tested using both face encoding and recognition experiments showing how the generalization capabilities of PCA are improved.

Trinocular stereo matching with composite disparity space image

In this paper we propose a method that smartly improves occlusion handling in stereo matching using trinocular stereo. The main idea is based on the assumption that any occluded region in a matched stereo pair (middle-left images) in general is not occluded in the opposite matched pair (middle-right images). Then two disparity space images (DSI) are merged in one composite DSI. The proposed integration differs from the known approach that uses a cumulative cost. The experimental results are evaluated on the Middlebury data set, showing high performance of the proposed algorithm especially in the occluded regions. Our method solves the problem on the base of a real matching cost, in such a way a global optimization problem is solved just once, and the resultant solution does not have to be corrected in the occluded regions. In contrast, the traditional methods that use two images approach have to complicate a lot their algorithms by additional add hog or heuristic techniques to reach competitive results in occluded regions.