Pose insensitive Face Recognition Using Feature Transformation

Summary Face recognition has diverse applications especially as an identification solution which can meet the crying needs in security areas. Pose problem is a big challenge applying this technology under real world conditions. Appearance based approach was proposed. Face recognition was implemented by reconstructing frontal view features using linear transformation. Experiments on popular FERET database proved that the proposed method can cope with the head rotation roughly within half profile view. Compared with algorithms model based approaches, feature transformation method is not dependent on heavy computation and has merit of easy implementing in live conditions. Popular feature extractions, least square (LS) and total least square (TLS) solution in calculating were compared as well as..

[1]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[2]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[3]  Jerry M. Mendel,et al.  The constrained total least squares technique and its applications to harmonic superresolution , 1991, IEEE Trans. Signal Process..

[4]  David Beymer,et al.  Face recognition from one example view , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Xiaoguang Lu,et al.  Image Analysis for Face Recognition , 2005 .

[7]  Konstantinos N. Plataniotis,et al.  Regularization studies of linear discriminant analysis in small sample size scenarios with application to face recognition , 2005, Pattern Recognit. Lett..

[8]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[9]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[11]  P. Jonathon Phillips,et al.  Face Recognition Vendor Test 2002: Overview and Summary , 2003 .

[12]  Jianqiang Yi,et al.  Effective pose estimation from point pairs , 2005, Image Vis. Comput..

[13]  J. Mendel,et al.  Constrained total least squares , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Timothy F. Cootes,et al.  Automatic Interpretation and Coding of Face Images Using Flexible Models , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Daijin Kim,et al.  Generating frontal view face image for pose invariant face recognition , 2006, Pattern Recognit. Lett..

[16]  Timothy F. Cootes,et al.  View-based active appearance models , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[17]  Xin Liu,et al.  Pose Normalization Using Generic 3D Face Model as a Priori for Pose-Insensitive Face Recognition , 2004, SINOBIOMETRICS.

[18]  Samy Bengio,et al.  STATISTICAL TRANSFORMATION TECHNIQUES FOR FACE VERIFICATION USING FACES ROTATED IN DEPTH , 2004 .

[19]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[20]  Marian Stewart Bartlett,et al.  Face recognition by independent component analysis , 2002, IEEE Trans. Neural Networks.

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

[22]  Kai Zhang,et al.  Multi-view face identification and pose estimation using B-spline interpolation , 2005, Inf. Sci..