Faouzi Ghorbel

A robust invariant bipolar representation for R 3 surfaces: applied to the face description

In this paper, we intend to introduce a novel invariant curved surface representation under the 3D motion group. It is constructed from the superposition of the two geodesic potentials generated from a given couple of surface points. By sampling this continuous representation, invariant points are extracted from a large neighborhood around these reference points. Different numerical methods are implemented in order to find an efficient approximation in the mean of the shape distance. The inference of small distortions of points positions applied to the reference points is analyzed. We apply the proposed representation to real 3D images. The experimentations are performed on the 3D facial database Bosphorus.

A Novel Geometrical Approach for a Rapid Estimation of the HARDI Signal in Diffusion MRI

In this paper, we address the problem of the diffusion signal reconstruction from a limited number of samples. The HARDI (High Angular Resolution Diffusion Imaging) technique was proposed as an alternative to resolve the problems of crossing fibers in the case of Diffusion Tensor Imaging (DTI). However, it requires a long scanning time for the acquisition of the Diffusion Weighted (DW) images. This fact makes hard the clinical applications. We propose here a novel geometrical approach to accurately estimate the HARDI signal from a few number of DW images. The missing diffusion data are obtained according to their neighborhood from a reduced set of diffusion directions on the sphere of the q-space. The experimentations are performed on both synthetic data and many digital phantoms simulating crossing fibers on the brain tissues. The obtained results show the accuracy of the reconstruction of the Fiber Orientation Distribution (FOD) function from the estimated diffusion signal.

Incremental 3D reconstruction using affine invariance in stereo image

The need for mapping small objects in such areas as museum collections may be met by using laser scanning techniques which are likely the best and the most reliable. However, the costs associated with these techniques prohibit their use apart from that such objects are too fragile for repeated handling. Therefore, the alternative is the use of passive methods like stereovision. In this paper we presents a contribution to the problem of 3D surface reconstruction under affine projections in stereo image. Method starts by using the affine invariance to caracterize shape on the objects contours. Such approximation is interesting if we consider small objects regards to the distance from sensors. Additionally, a methodology to estimate the affine transformation that best aligns the matched contours is also presented: a scale factor a, a shift value lo and an affinity matrix A are computed to establish a local matching of points that preserves the circular order of points. In order to validate the proposed matching methodology, some results on stereovision context are exposed with scene containing small archeological 3D objects.

A Novel and Accurate Local 3D Representation for Face Recognition

In this paper, we intend to introduce a novel curved 3D face representation. It is constructed on some static parts of the face which correspond to the nose and the eyes. Each part is described by the level curves of the superposition of several geodesic potentials generated from many reference points. We propose to describe the eye region by a bipolar representation based on the superposition of two geodesic potentials generated from two reference points and the nose by a three-polar one (three reference points). We use the BU-3DFE database of 3D faces to test the accuracy of the proposed approach. The obtained results in the sense of the Hausdorff shape distance prove the performance of the novel representation for 3D faces identification. The obtained scores are comparable to the state of the art methods in the most of cases.

Accurate 3D Shape Correspondence by a Local Description Darcyan Principal Curvature Fields

In this paper, we propose a novel approach for finding correspondence between three-dimensional shapes undergoing non-rigid transformations. Our proposal is based on the computation of the mean of curvature fields values on a local parametrization constructed around interest points on the surface. This local parametrization corresponds to the Darcyan coordinates system. Thereafter, correspondence is found by measuring the \(L_{2}\) distance between obtained descriptors. We conduct the experimentation on the full objects of the Tosca database which contains a set of 3D objects with non-rigid deformations. The obtained results show the performance of the proposed approach.

A New Multi-resolution Affine Invariant Planar Contour Descriptor

In this paper, a novel affine invariant shape descriptor for planar contours is proposed. It is based on a multi-resolution representation of the contour. For each contour resolution, a shape signature is defined from the contour points and the initial contour centroid and points. Finally, Fourier descriptors are computed for each signature. The proposed descriptor is invariant to affine transformations. Experiments carried on the MPEG-7 coutour database and the Multiview Curve Dataset (MCD) show that our proposed descriptor outperforms other contour shape descriptors proposed in the literature.

A Novel Canonical Form for the Registration of Non Rigid 3D Shapes

In this paper, we address the problem of non rigid 3D shapes registration. We propose to construct a canonical form for the 3D objects corresponding to the same shape with different non rigid inelastic deformations. It consists on replacing the geodesic distances computed from three reference points of the original surface by the Euclidean ones calculated from three points of the novel canonical form. Therefore, the problem of non rigid registration is transformed to a rigid matching between canonical forms. The effectiveness of such method for the recognition and the retrieval processes is evaluated by the experimentation on the TOSCA database objects in the mean of the Hausdorff Shape distance.

Stability Evaluation of Combined Neural Networks

In the industrial field, the artificial neural network classifiers are currently used and they are generally integrated of technologic systems which need efficient classifier. However, the lack of control over its mathematical formulation explains the instability of its classification results. In order to improve the prediction accuracy, most of researchers refer to the classifiers combination approach. This paper tries to illustrate the capability of an example of combined neural networks to improve the stability criterion of the single neural classifier. The stability comparison is performed by the error rate probability densities function estimated by a new variant of the kernel-diffeomorphism semi-bounded Plug-in algorithm.

Combining contour matching and visual hull information for 3D reconstruction of archeological objects

Museums are interested in the digitizing of their collections not only for the sake of preserving the cultural heritage, but also to make the information content accessible to the wider public in a manner that is attractive. Computer vision techniques are widely used to create virtual museum exhibitions both in a museum environment through informative kiosks or on the World Wide Web. Such 3D exhibition makes the digital content viewed through the internet from anywhere in the world, without moving objects or visiting really the sites. In this paper, 3D reconstruction of archaeological objects is done using the ”shape from silhouette” approach with an affine contours matching method for the refinement of the obtained models. Starting from a silhouettes sequence, the algorithm constructs a coarse visual hull of the object. Then, using affine-invariant contour matching we proceed iteratively to refine the initial mesh and to obtain a more accurate 3D model.

Affine movement estimation for object modeling under circular motion

Profile of a 3D object provides rich information about its geometry, and can be used for shape recovery under known camera motion. Model reconstruction has found application in many fields, including medical, entertainment and archeological application. For the last one, 3D digital models can be used for study and restoration of cultural heritage artifact.This paper describes a system which generates a 3D model from a sequence of images under circular motion in the context of archeology.Starting from the silhouettes contours, the algorithm recovers camera motion and constructs the objects visual hull. The technique here described is based on stereo matching of external contours using complete and stable set of affine invariants descriptors. Hence, our system is able to reconstruct the 3D geometry using contour matching and sensors parameters that are previously computed on a calibration step. The algorithm has been implemented in practical way model acquisition system experiments including sensors and turntable and some prototype of real archeological objects.