Multi-pose Face Recognition Using Head Pose Estimation and PCA Approach

In this paper, a novel multi-pose face image recognizing method is presented. In this algorithm, the face with multi-pose can be recognized by comparing it with the eigenface which is generated from 3D face model database, view point of the 3D face model is estimated from the face image, the estimation algorithm utilize the facial geometrical feature to estimate head pose parameter which can be applied to the view point of 3D face model. Through the method, the 3D face model can keep the same pose with the real captured face. Finally, a PCA based algorithm is employed to extract the eigenface from the generated exemplar database and input face image. The cosine distance matching method will be used to compare the similarity of face between input one and the generated database. The one which has the maximum similarity can be judged as the positive one of identifying face. In the experiment, we evaluated the efficiency pose estimation algorithm and the recognition approach. We can see the error of the estimation algorithm is near to ±0.05o for frontal face and ±3.9o for near profile face. And the correct recognition rate is close to 96% for frontal face and 72% for near profile face.

[1]  Suk-Hwan Lee,et al.  Automatic Camera Pose Determination from a Single Face Image , 2007 .

[2]  Li Wei,et al.  Improved Multi-pose 2D Face Recognition Using 3D Face Model with Camera Pose Estimation Approach and nD-PCA Recognition Algorithm , 2008, 2008 Third International Conference on Convergence and Hybrid Information Technology.

[3]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[4]  Patrick J. Flynn,et al.  Face Recognition Using 2D and 3D Facial Data , 2003 .

[5]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[6]  J FlynnPatrick,et al.  An Evaluation of Multimodal 2D+3D Face Biometrics , 2005 .

[7]  P. Jonathon Phillips,et al.  Face recognition vendor test 2002 , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[8]  Ioannis Pitas,et al.  Rule-based face detection in frontal views , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Li Wei,et al.  Human Head Mouse System Based on Facial Gesture Recognition , 2007 .

[10]  Patrick J. Flynn,et al.  An evaluation of multimodal 2D+3D face biometrics , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Gordon Erlebacher,et al.  A novel technique for face recognition using range imaging , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[12]  Thomas Vetter,et al.  Face Recognition Based on Fitting a 3D Morphable Model , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Xiaogang Wang,et al.  An improved Bayesian face recognition algorithm in PCA subspace , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[15]  T. Aoki,et al.  3D face recognition using passive stereo vision , 2005, IEEE International Conference on Image Processing 2005.

[16]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[17]  Ki-Ryong Kwon,et al.  Automatic Face Analysis System Based on Face Recognition and Facial Physiognomy , 2006, ICHIT.

[18]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression Database , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  P J. Phillips,et al.  Face Recognition Vendor Test 2000: Evaluation Report , 2001 .

[20]  M. Bernas,et al.  Determination of the camera position in virtual studio , 2003, Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795).