A multiple-baseline stereo for precise human face acquisition

Stereo algorithms can provide useful three-dimensional information for a variety of purposes, including face recognition. For good accuracy, the distance between cameras should be large. However, the large baseline often makes the correspondence problem more difficult. In this paper, we examine the problem of non-Lambertian reflectivity in multi-baseline stereo and propose a refined multiple-baseline stereo technique which estimates the brightness on each camera by using adjacent cameras. In this way, the erroneous stereo correspondences due to brightness changes caused by non-Lambertian reflectance can be reduced without needing to explicitly model the actual reflectance model. Experimental results are presented and significant reductions in correspondences errors are demonstrated in comparison with previous methods. (C) 1997 Elsevier Science B.V.