Facial Image Authentication System Based on Real-Time 3D Facial Imaging by Using Complex-Valued Eigenfaces Algorithm
Shu Zhan, Toru Kurihara, Shigeru Ando · 2006
In this paper, a facial image recognition system based on 3D real-time facial imaging system is proposed. Based on the vector map and intensity image obtained by three-phase correlation image sensor, the differential geometry theory is employed to find the key points of face image, according to these key points, the 3D facial image in different pose is correction. In this paper, the traditional eigenface algorithm is extended to the complex-valued eigenface based on the 3D imaging system; the complex-valued eigenface algorithm could take advantage more facial information than the normal eigenface technique. The experiments show that the performance for our test is very satisfactory.