抄録
H-035
The Research of 3D Face Recognition Based on Local Feature Matching
◎Daoqing Sheng・Guoyue Chen・Kazuki Saruta・Yuki Terata（Akita Prefectural University）
K-L transformation is employed to adjust coordinate system and coarsely align 3D point cloud. Based on B-splines approximation, 3D facial surface reconstruction is implemented. Through analyzing the curvature features of the fitted surface, local rigid facial patches are extracted. According to the extracted local patches, features vectors are constructed to execute final recognition.The experimental results demonstrate high performance of the presented method and also show that it is effective for 3D face recognition.