This paper proposes a way to incorporate a priori information in a 3D stereo reconstruction process from a pair of calibrated face images. In our framework, a 3D mesh modeling the surface is iteratively deformed in order to minimize an energy function in a snake-like process. Differential information about the object shape is used to generate an anisotropic mesh that can both fulfill the compac...

The aim of this paper is to attain a fast and realistic 3D face reconstruction, when only a limited set of images taken from multiple views, is available. Instead of much relying on merely 2D images as suggested by image-based modeling approaches, we investigate the used of several shape-from-shading (SFS) techniques, which have been studied extensively in computer vision researches. This is be...

Title of dissertation: RECOGNIZING HUMAN FACES: PHYSICAL MODELING AND PATTERN CLASSIFICATION Gaurav Aggarwal, Doctor of Philosophy, 2008 Dissertation directed by: Professor Rama Chellappa Dept. of Electrical & Computer Engineering and Dept. of Computer Science Although significant work has been done in the field of face recognition, the performance of the state-of-the-art face recognition algor...

In this paper, we propose an example based realistic face modeling method with viseme control. The viseme describes the particular facial and oral positions and movements that occur alongside the voicing of phonemes. In facial animation such as speech animation and talking head, etc, a face model with open mouth is often used and the model is animated along with the speech sound by synchronizin...

This paper presents a new hierarchical facial model that conforms to the human anatomy for realistic and fast 3D facial expression synthesis. The facial model has a skin/muscle/skull structure. The deformable skin model uses a kind of nonlinear springs to directly simulate the nonlinear visco-elastic behavior of soft tissue, and a new kind of edge repulsion springs is developed to prevent model...

This paper proposes a method of geometric modeling of features extracted from 3D face and presents some of its applications. It describes a new automatic pose and expression invariant feature extraction algorithms to extract features (control points) from eyebrows, nose and lips of 3D facial data. The proposed algorithms are tested on BU-3DFE (Binghamton University 3D Facial Expression) Databas...

Face analysis fields are widely spread out over a large quantity of domains : Human Computer Interaction, security, movies post-production, games... It includes detection, recognition, 3D reconstruction, animation, and emotion analysis. Face animation was the main motivation of this thesis, and we always kept it in mind at anytime. We discuss here, most of the fields. We first talk about face r...

In the past few years several systems for tridimensional face reconstruction based on the analysis of 2D images have been proposed. The main goal of these systems is to provide fast and reliable 3D information to face recognition systems. Nevertheless, nowadays, affordable systems that guarantees an high level of details and fast processing time using commercial devices are far from be realized...

Researchers have been working on human face recognition for decades. Face recognition is hard due to different types of variations in face images, such as pose, illumination and expression, among which pose variation is the hardest one to deal with. To improve face recognition, this thesis presents an integrated approach to performing pose robust video-based face tracking and recognition by usi...