Showing papers by "Mohamed-Chaker Larabi published in 2003"

Segmentation in the HSI Color Space Dedicated for Medical Imaging.

Abstract: This study is about 3D scanner conception dedicated to human foot modelling. It is composed by digital devices. The reconstruction method used is based on a stereovision technique. In order to obtain a 3D reconstruction of the patient foot, it is absolutely necessary to extract and reproduce accurately its shape. Consequently, a segmentation stage is unavoidable and requires a specific algorithm given that standard algorithms do not provide enough satisfactory results. Moreover, the environment definition (background color, lighting conditions) depends on the envisaged method. The comparison of the RGB components of several foot skin has shown a weak occurrence of the blue component. A colorimetric study was done using a set of backgrounds with different referenced blue colors (Pantone R ©). The study was done in the HSI color space allowing the decorrelation of the RGB components. A set of images were acquired while combining several foot with different types and different blue backgrounds. So, the study of the hue component obtained shows a perfect uniformity with a sufficiently high saturation component which allows a first segmentation.

Using a CBIR scheme based on experts knowledge for a computer-aided classification of ornamental stones

Abstract: This paper aims to present a complete methodology based on a multidisciplinary approach, that combines the extraction of low-level features to describe images in a high-level concept or formalism dedicated to Computer-Aided Categorization of ornamental stones (granite, marble). The problem is resolved thanks to a Content-Based Image Retrieval scheme where each image from the ornamental database is represented by a features vector. This last is composed, on one hand, by a color feature corresponding to a novel characterization of color histogram and on the other hand by a texture feature corresponding to a color-based co-occurrence matrix from where we extract some feature representation. The combination of both color texture descriptors is done thanks to a stage of expert know-how extraction. This know-how is represented by the way of weighting factors and confidence degrees. The fusion of the whole data allows to improve the categorization performances.

3D Acquisition System for the Measurement of the Foot.

Abstract: This study concerns the conception of a 3D scanner dedicated to the human foot for its 3D reconstruction for biomedical applications. The view of this article has been to show the research made since two years. This system must allow to extract metrology of human foot. Indeed, the precision of 1mm has to allow the quality of the manufacture of adapted prostheses to the patient feet. This article is directed towards two axes : on the one hand, the explanation of the encountered problems and objectives defining the specifications and on the other hand, the solutions brought and choices for the acquisition system. The main goal of the system is to be able to measure various pathologies of met foot. Therefore, the solutions brought must make it possible to obtain a completely automatic system. They include the choice of the extraction method of points of the foot surface and the modelling to rebuild surface starting from the cloud of points. It must be also calibrated to supply the metrology of the foot. Moreover, the system is built with several color cameras. These various choices allow to extract the metrology of the foot in the desired resolution.