Averaged Segmental Partial Hausdorff Distance for Robust Face Recognition

摘要

Face recognition is a non-contact biometric identification that tries to verify individuals automatically based on their images. Computational time and accuracy rate are important aspects to be considered for Face Recognition systems. Huasdorff distance is a dissimilarity measurement between two point sets which has been increasingly used for face recognition. In this paper, we have proposed a modified criterion based on Hausdorff distance, which conspicuously decreases the excessive computational time while increases the recognition rate of conventional face recognition methods, based on Hausdorff distance.