| Face Recognition Technology refers to analysis and comparison of the use of visual features of face identification information in computer technology, which has been more than 40 years of history. So far,it has been proposed by a variety of face recognition algorithms.Different with 2D Face Recognition Technology, 3D Face Recognition Technology find match point through two photos match point as a species Sub-point,but the seed point to meet the requirements rarely.This requires the adoption of point cloud matching and propagation of the seeds of more points, the conditions of reconstruction of human face.Based on the image processing and binocular stereovision theory,in this paper we have present a system to generate 3D facial data form two photos of face and implement it with VC++ 6.0 on the platform of Windows. The system first adopts two cameras to shoot the face of the same person form different angles respectively,then finds a few corresponding point matches between two the pictures, which are later propagated to be quasi-dense , integrating the camera's geometry parameters,the 3D facial data is calculated.In this paper, open with 3D face recognition technology and image match-ing,introduce based on Gray-Scale Image Matching Algorithm and the Feature Points based on the Image Matching Algorithm respectively.After Face Image processing, according to ZNCC, we achieve the algorithm. Moreover,parts of the experimental results are presented.The pictures need preprocessing before find matching , because there is a lot of noise during the acquisition of the pictures. Our preprocessing mainly include eliminating the effect of illumination and background. Concerning the illumination,we pick the "best picture" ,namely the picture form which we extract the most accurate color node,transform the grey-scale of the other images in order that the mean and standard deviation are identical to these of the "best picture" .As to the background,set the background to be black so that the mean and standard deviation can reflect the facial grey-scale.The arithmetic also use epipolar geometry to eliminate the bad matches and optimize the matches left.The strategy is as follows: given a threshold T,which is decided by experiment,the distance between a point and its match point's corresponding epipolar line is Dist1,the opposite direction is Dist2 , let Dist = Dist1 + Dist2, if Dist is lager than T, the point match is eliminated, otherwise, optimize it by looking for the "best" point match in their neighbourhood whose Dist is the shortest.The primary point matches are sparse and is far away from the need of face recognition and other applications.So the system later propagate them to be qusi-dense.The improved propagation arithmetic is adopted. The main idea is that: pick the point match whose ZNCC is largest , and look for the potential matches (u, u') in its immediate neighbourhood N(x,x') following some particular "matching rules" ,as figure .Given that the facial texture is not obvious, we introduce image gradient together with ZNCC. Most of the threshold of the original arithmetic is reset by experiment results.Moreover, epipolar geometry restriction is also applied.Finally, this paper presents parts of the experimental results, as well as summarize, pointing out that the existing problems and future direction of development... |
PDF Full Text Request