http://biblioteca.universia.net/searchAutor.do?q=Tarela,%20A. Resultados 1 - 10 de 34 de Tarela, A.. (0,09 segundos) es http://biblioteca.universia.net/img/logotipo.jpg http://biblioteca.universia.net/ http://biblioteca.universia.net/ficha.do?id=46276530 This article presents a seldom studied 3D reconstruction approach, and focus on its numerous advantages. It is a global approach, in which the algorithm attempts to reconstruct geometric high level features by using only global attributes of the image projections of the feature. Our elementary feature is a 3D planar patch, and geometric moments are the global attributes. The proposed method of reconstruction has the following advantages: ffl the use of the geometric moments of image region d... Jean-Philippe Tarel Inria http://biblioteca.universia.net/ficha.do?id=46909342 We describe a general-purpose method for the accurate and robust interpretation of a data set of p-dimensional points by several deformable prototypes. This method is based on the fusion of two algorithms: a Generalization of the Iterative Closest Point (GICP) to different types of deformations for registration purposes, and a fuzzy clustering algorithm (FCM). Our method always converges monotonically to the nearest local minimum of a mean-square distance metric, and experiments show that the... Jean-Philippe Tarel http://biblioteca.universia.net/ficha.do?id=48359412 VELASCO TARELO, PAULA MARGARITA http://biblioteca.universia.net/ficha.do?id=46139278 In image retrieval systems, a variety of simple similarity measures are used. The choice for one similarity measure or another is generally driven by an experimental comparison on a labeled database. The drawback of such an approach is that, while a large number of possible similarity measures can be tested, we do not know how to extend from the obtained results. However, the choice of a good similarity measure leads to noticeable better results. It is known that this choice is related to the... Jean-Philippe Tarel; Sabri Boughorbel http://biblioteca.universia.net/ficha.do?id=46278066 We present an algorithm that extracts the largest shape within a specific class, starting from a set of image edgels. The algorithm inherits the Best-First Segmentation approach [1]. However, instead of being applicable only to shapes defined within a given class of curves, we have extended our approach to tackle more general - and complex - shapes. For example, we can now process shapes obtained from sets defined over different kinds of curves and related to one another by estimated paramete... Jean-Philippe Tarel; Frédéric Guichard http://biblioteca.universia.net/ficha.do?id=46296741 We present an algorithm that extracts curves from a set of edgels within a specific class in a decreasing order of their "length". The algorithm inherits the perceptual grouping approaches. But, instead of using only local cues, a global constraint is imposed to each extracted subset of edgels, that the underlying curve belongs to a specific class. In order to reduce the complexity of the solution, we work with a linearly parameterized class of curves, function of one image coordina... Frederic Guichard; Jean-Philippe Tarel http://biblioteca.universia.net/ficha.do?id=46455595 We present an ellipse-based camera calibration. Correct measures in the image are required to perform the camera model estimation. We suggest a technique, based upon surface photometry, allowing to compute robustly and accurately the moments of a shape in an image, and use them as inputs for the estimation algorithm. Connections between the specification of a 3D-ellipse, the moments of its image and calibration parameters are described. These equations are partially extended to models includi... Jean-Philippe Tarel; Projet Syntim http://biblioteca.universia.net/ficha.do?id=46535518 In Computer Vision methods such as shape-from-shading, 3D reconstruction by correlation and edge detection, all the pixels of the CCD matrix are assumed equivalent. A radiometric camera calibration step is necessary to verify this hypothesis, which is the subject of this paper. First, the modeling of the sensor, based on its physical properties, is described. A method to estimate the parameters of this model is given and the results of experimentations are described. These experiments valid t... Jean-Philippe Tarel; Projet Syntim http://biblioteca.universia.net/ficha.do?id=46571793 We present a 3D reconstruction approach which is few studied in consideration of its numerous advantages. It is a global approach, where the algorithm attempt to reconstruct geometric high level features by using only global parameters of the image projections of the feature. Our elementary feature is 3D planar patch, and geometric moments are our global parameters. The proposed method of reconstruction has the following adavatages: - using of the geometric moments of image region do not need... Jean-Philippe Tarel; Projet Syntim http://biblioteca.universia.net/ficha.do?id=46839610 In Computer Vision methods such as shape-from-shading, 3D reconstruction by correlation and edge detection, all the pixels of the CCD matrix are assumed equivalent. A radiometric camera calibration step is necessary to verify this hypothesis, which is the subject of this paper. First, the modeling of the sensor, based on its physical properties, is described. A method to estimate the parameters of this model is given and the results of experimentations are described. These experiments valid t... Jean-Philippe Tarel; Domaine De Voluceau