Facial Asymmetry in Frequency Domain: The "Phase" Connection

Facial asymmetry has now been established as a useful biometric for human identification in the presence of expression variations ([1]). The current paper investigates an alternative representation of asymmetry in the frequency domain framework, and its significance in identification tasks in terms of the phase component of the frequency spectrum of an image. The importance of the latter in face reconstruction is well-known in the engineering literature ([2]) and this establishes a firm ground for the success of asymmetry as a potentially useful biometric. We also point out some useful implications of this connection and dual representation. Moreover, the frequency domain features are shown to be more robust to intra-personal distortions than the corresponding spatial measures and yield error rates as low as 4% on a dataset with images showing extreme expression variations.

[1]  Nikolaus F. Troje,et al.  How is bilateral symmetry of human faces used for recognition of novel views? , 1998, Vision Research.

[2]  Aleix M. Martínez,et al.  Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per Class , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Sinjini Mitra,et al.  Local facial asymmetry for expression classification , 2004, CVPR 2004.

[4]  Yanxi Liu,et al.  Facial asymmetry quantification for expression invariant human identification , 2003, Comput. Vis. Image Underst..

[5]  Alan V. Oppenheim,et al.  Discrete-Time Signal Pro-cessing , 1989 .

[6]  Srinivas Gutta,et al.  An investigation into the use of partial-faces for face recognition , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[7]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Takeo Kanade,et al.  Comprehensive database for facial expression analysis , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[9]  Pradeep K. Khosla,et al.  "Corefaces" - robust shift invariant PCA based correlation filter for illumination tolerant face recognition , 2004, CVPR 2004.

[10]  M. Hayes.  The reconstruction of a multidimensional sequence from the phase or magnitude of its Fourier transform , 1982 .

[11]  Steven M. Seitz,et al.  View morphing , 1996, SIGGRAPH.

[12]  E. Koff,et al.  Facial asymmetry during emotional expression: Gender, valence, and measurement technique , 1998, Neuropsychologia.

[13]  Yuri M. Bayakovsky,et al.  Russia: computer graphics education takes off in the 1990s , 1996, COMG.

[14]  Marios Savvides,et al.  Eigenphases vs eigenfaces , 2004, ICPR 2004.