Building Standardized 3D Face Data Base for Face Recognition Applications.

摘要

During the past 9 months we concentrated our work on three main issues: First, we developed of methods and software for processing three- dimensional face data and started a collaboration with the University of Florida to obtain and process a large set of high quality laser scans of human heads that might be valuable for future research on automated face recognition. Second, we derived a morphable face model from a selected subset of the face data collected so far using a method we developed earlier. Third, we now also performed a series of first experiments on using a three-dimensional morphable face model for pose and illumination invariant face recognition. The results of these experiments demonstrated that the morphable model is a promising approach for compensating pose variations up to 90 deg.