Independent components of face images : A representation for face recognition

Methods for obtaining representations of face images based on independent component analysis (ICA) are presented. A global ICA representation is compared to a global representation based on principal component analysis (PCA) for recognizing faces m o s s changes in lighting and changes in pose. For each set of face images, a set of statistically independent source images was found through an unsupervised learning algorithm that maximized the mutual information between the input and the output of a nonlinear transformation (Bell & Sejnowski, 1995). These source images comprised the kernels for the representation. The independent component, kernels gave superior class discriminabiity to the principal component kernels. Recognition across changes in pose with the ICA representation was 93%, compared to 87% with a PCA representation, and across changes in lighting ICA gave 100% correct recognition, compared to 90% with PCA.

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

[2]  Penio S. Penev,et al.  Local feature analysis: A general statistical theory for object representation , 1996 .

[3]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[4]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[5]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[6]  Marian Stewart Bartlett,et al.  Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor Networks , 1996, NIPS.

[7]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.