顔認識における混合顔特徴ディスクリプタ

抄録

This paper presents a face recognition approach using hybrid face features descriptors (HFFD). The HFFD is a face descriptor containing of rich discriminant information that is created by fusing some frequency-based features extracted using both wavelet and DCT analysis of several different poses of 2D face images. The HFFD based face recognition tends to provide better performance than that of the recent 2D-based face recognition method and it also sufficiently to handle large pose variations.