Albert Pujol

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.

A SUPERVISED MODIFICATION OF THE HAUSDORFF DISTANCE FOR VISUAL SHAPE CLASSIFICATION

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.

Parotidectomías en tumores benignos: clasificación «Sant Pau» de la extensión de la resección

INTRODUCTION AND GOALS At present different options co-exist for treating a benign tumour of the parotid gland, which has led to some confusion about the extent of resection performed in each case. In an effort to improve this situation, we created a classification system to define the areas removed. We started using this classification in July, 2006, and this article reviews its applicability and usefulness. METHODS We analyzed 44 patients who underwent surgery for clinically benign tumours of the parotid gland in our department between July, 2006, and December, 2008. In all resections, our classification was applied, dividing the parotid gland into five areas: I (lateral superior), II (lateral inferior), III (deep superior), IV (deep inferior), V (accessory). RESULTS The classification was easily applied and has presented no practical problem in the 44 patients operated. When analyzing the areas excised in surgery, the most common surgery was lateral inferior partial parotidectomy (removal of area II) in 47% of the cases. Lateral parotidectomy (removal of areas I and II) was the next most frequent, with 14 cases (33%). The remaining 20% was distributed among the other options. CONCLUSIONS Our classification system appears to be a simple and easy way to define the surgery performed in each case, which simplifies the description of the resection performed, even in unusual resections.

Colour normalisation based on background information

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.

Automatic view based caricaturing

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.

Learning and caricaturing the face space using self-organization and Hebbian learning for face processing

This paper shows a self-organized system designed to obtain compressed representations of instances of a population of visual forms. It is shown how, when applied to face shape information, the system evolves into a prototype of the population and induces automatic warping, or caricaturing, transformations where geometrical differences between forms are increased, improving, as a consequence, recognition performance. In this way, the proposed system provides a unified account for the whole chain of face processing tasks including data compression, detection, and recognition. Experimental data is presented to show the feasibility of our approach in terms of performance and robustness to changes in illumination and face expressions.

Locating people in indoor scenes for real applications

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 subjects 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.

Separating geometry from texture to improve face analysis

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.

Parotidectomies in benign parotid tumours: “Sant Pau” surgical extension classification

Abstract Introduction and goals At present different options co-exist for treating benign tumours of the parotid gland, which has led to some confusion about the extent of resection performed in each case. In an effort to improve this situation, we created a classification system to define the areas removed. We started using this classification in July 2006, and this article reviews its applicability and usefulness. Methods We analysed 44 patients who underwent surgery for clinically benign tumours of the parotid gland in our department between July 2006 and December 2008. Our classification was applied in all resections, dividing the parotid gland into five areas: I (lateral superior), II (lateral inferior), III (deep superior), IV (deep inferior), V (accessory). Results The classification was easily applied and presented no practical problems in the 44 patients operated on. When analysing the areas excised in surgery, the most common surgery was lateral inferior partial parotidectomy (removal of Area II), in 47% of the cases. Lateral parotidectomy (removal of Areas I and II) was the next most frequent, with 14 cases (33%). The remaining 20% was distributed among the other options. Conclusions Our classification system appears to be a simple, easy way to define the surgery performed in each case, which simplifies the description of the resection performed, even in unusual resections.

Improving shape-based face recognition by means of a supervised discriminant Hausdorff distance

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.