Pattern Analysis for an Automatic and Low-cost 3D Face Acquisition Technique
Résumé
This paper proposes an automatic 3D face modeling and localizing, based on active stereovision. In offline stage, the optical and geometrical parameters of the stereosensor are estimated. In online acquisition stage, alternate complementary patterns are successively projected. The captured right and left images are separately analyzed in order to localize left and right primitives with a sub pixel precision. Also, this analysis provides us an efficient segmentation of facial informative region. Epipolar geometry transforms stereo matching problem into a one-dimensional search problem. Indeed, we employ an adapted and optimized dynamic programming algorithm to pairs of primitives which are already located in each epiline. 3D geometry is retrieved by computing the intersection of optical rays coming from the pair of matched features. A pipeline of geometric modeling techniques is applied to densify obtained 3D point cloud, mesh and texturize 3D final face model. An adequate evaluation strategy is proposed and experimental results are provided.