Improved face recognition by incorporating local color information into the active shape model
Shih‐Hsuan Yang, Zhan Yu-Xiang · 2016
Face recognition is one of the most natural biometrics identification approaches. But the accuracy of face recognition is significantly influenced by poses, facial expressions, and lighting conditions. This paper presents a novel robust facial recognition system by incorporating color information into a modified active shape model (ASM). The selected robust geometric and chromatic information of facial landmark points are derived from ASM. Faces are classified using the k-nearest neighbors algorithm with the chosen distance and color features. Compared with the original ASM and its enhanced version, the proposed method consistently achieves a much higher recognition rate at a comparable processing speed.