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.

This paper presents an efficient real-time method for detecting moving objects in unconstrained environments, using a background subtraction technique. A new background model that combines spatial and temporal information based on similarity measure in angles and intensity between two color vectors is introduced. The comparison is done in RGB color space. A new feature based on chromaticity and intensity pattern is extracted in order to improve the accuracy in the ambiguity region where there is a strong similarity between background and foreground and to cope with cast shadows. The effectiveness of the proposed method is demonstrated in the experimental results and comparison with others approaches is also shown.

Face detection and tracking, through image sequences, are primary steps in many applications such as video surveillance, human computer interface, and expression analysis. Many currently existing techniques donpsilat perform well due to pose variations, appearance changes, illumination changes, complex backgrounds, and inaccurate initialization. The last short coming, which is the difficulty to initialize motion regions, is a problem facing any tracker. In this paper, we present an automatic and robust face detection and tracking system for color image sequences. Face detection is done using skin color segmentation and connected components analysis. Later, facial features are detected by active shape models and a face mesh is initialized. Finally, the tracking is done by active appearance models. Experimental detection and tracking results on a pose varying face video are given.

This paper introduces a supervised discriminant Hausdorff distance that fits into the framework for automatic face analysis and recognition proposed in [A. Pujol et al.,2002]. Our proposal relies solely on face shape variation contrarily to most of the successful model-based approaches, and results show comparable performance to them. The whole framework is based in a new set of Hausdorff measures and defines face-shape based similarity measures and supervised criteria to add discriminant capabilities to the Hausdorff distance. The paper presents experimental results supporting the proposed methodologies.

Hausdorff distance is a deformation tolerant measure between two sets of points. The main advantage of this measure is that it does not need an explicit correspondence between the points of the two sets. This paper presents the application to automatic face recognition of a novel supervised Hausdorff-based measure. This measure is designed to minimize the distance between sets of the same class (subject) and at the same time maximize the distance of sets between different classes.

This article studies the effect of preprocessing a classical PCA decomposition using a modified self organizing map (SOM) in order to find shape clusters to improve the texture analysis by means of a pool of PCAs. In most successful view-based recognition systems, shape and texture are jointly used to model statistically a linear or piece-wise linear subspace that optimally explains the face space for a specific database. Our work is aimed at separating the influence that variance in face shape stamps on the set of eigenfaces in the classical PCA decomposition. A set of experiments show the reliability of this new system.

This paper presents a face recognition system based on the use of image ridges and valleys as face shape descriptors and a supervised Hausdorff based measure as similarity criteria. The proposed measure is designed to decrease the distance measured between images of the same subject. This measure is approximated using eigendecomposition in order to obtain a computationally efficient recognition method.

This paper proposes an improvement on a well-known colour normalisation by the introduction of some knowledge on background. Comprehensive normalisation gives an invariant representation of the image colour. This invariant representation can be considered a canonical representation whenever image content is preserved and changes are only due to illuminant conditions. One of the steps of the normalisation is based on the grey-world normalisation that removes colour changes on each channel. Because a diagonal model is assumed, the independence of chromatic variations is also achieved if the channel normalisation is applied only with background mean in spite of image mean. This will allow one to remove illuminant effects meanwhile no influence from the foreground is introduced on the normalised coordinates. It will provide an almost canonical colour space without an explicit estimation of the scene illuminant.

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.

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.

Retinal images are routinely used in ophthalmology to study the optical nerve head and the retina. To assess objectively the evolution of an illness, images taken at different times must be registered. Most methods so far have been designed specifically for a single image modality, like temporal series or stereo pairs of angiographies, fluorescein angiographies or scanning laser ophthalmoscope (SLO) images, which makes them prone to fail when conditions vary. In contrast, the method we propose has shown to be accurate and reliable on all the former modalities. It has been adapted from the 3D registration of CT and MR image to 2D. Relevant features (also known as landmarks) are extracted by means of a robust creaseness operator, and resulting images are iteratively transformed until a maximum in their correlation is achieved. Our method has succeeded in more than 100 pairs tried so far, in all cases including also the scaling as a parameter to be optimized.

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.

We address the object recognition problem in a probabilistic framework to detect and describe object appearance through image features organized by means of active contour models. We consider the formulation of saliency in terms of visual similarity embedded in the probabilistic principal component analysis framework. A likelihood of object structure detection is obtained using the relation between the visual field and the internal object representation. Deformable models are employed introducing a computational methodology for a perceptual organisation of image features as an abstract understanding of the integration between structure and constraints of the visual information-processing problem. A specific application of the integrated approach for vessels segmentation in angiography is considered and the results are encouraging.

A real person description application needs, as a first step, a robust process of people location. To locate people it is required to find out the subject's position and extent. This paper presents a robust architecture for solving this problem in static images. The work presented combines in a probabilistic manner, information from background, skin and shape models. This method has been tested in a large set of images for a real application.

This paper describes a new method for the automatic view based generation of caricatures using image operators and lending itself to parallel implementation. This work is motivated by the need for a realistic and automatic caricaturing process for both human studies related to understanding why caricatures are recognized better than real images, and automatic face recognition. The proposed method determines how the valleys of an image should be distorted in order to obtain a caricature. The propagation of this sparse transformation to the full image provides a dense and smooth deformation field that, when it is properly applied, yields a realistic face caricature. The new caricaturing method does not require manual annotation and yields more realistic images due to the dense and smooth deformation field. A new shape and texture descriptor for representing faces based on the new caricatured image is also proposed for face recognition.

We introduce a new deformable model, called eigensnake, for segmentation of elongated structures in a probabilistic framework. Instead of snake attraction by specific image features extracted independently of the snake, our eigensnake learns an optimal object description and searches for such image feature in the target image. This is achieved applying principal component analysis on image responses of a bank of Gaussian derivative filters. Therefore, attraction by eigensnakes is defined in terms of classification of image features. The potential energy for the snake is defined in terms of likelihood in the feature space and incorporated into a new energy minimising scheme. Hence, the snake deforms to minimise the mahalanobis distance in the feature space. A real application of segmenting and tracking coronary vessels in angiography is considered and the results are very encouraging.

Real applications on people tracking are usually based on image heuristics. Real approaches do not use to apply recent prediction-estimation theoretical frameworks. These require the definition of complex dynamical and shape object models before the tracking process. We present a probablistic framework that takes profit of these theories adapting them to real applications. The key idea of this work is to estimate the shape model and dynamical objects parameters using only image data. The flexibility of our algorithm makes it suitable to be used on different real applications. Some experiments have been done in order to test our method in outdoor scenes people tracking.

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.

In this paper we describe a model-based system for the assessment of skeletal maturity on hand radiographs by the TW2 method. The problem consists in classifiying a set of bones appearing in an image, in one of several stages described in an atlas. A first approach consisting in pre-processing, segmentation and classification independent phases is also presented. However, it is only well suited for well contrasted, low noise images, without superimposed bones, were the edge detection by zero crossing of second directional derivatives is able to extract all bone contours, maybe with little gaps, and few false edges on the background. Hence, the use of all available knowledge about the problem domain is needed to build a rather general system. We have designed a rule-based system for narrow down the rank of possible stages for each bone, and guide the analysis process. It calls procedures written in conventional languages for matching stage models against the image, and getting features needed in the classification process.