HOG-EBGM vs. Gabor-EBGM

This paper presents a comparison between a new face recognition algorithm based on EBGM which replaces Gabor features by HOG descriptors and the original EBGM. The experiments results show a better performance behavior using public available databases. This better performance is explained by the properties of HOG descriptors which are more robust to changes in illumination, rotation and small displacements, and to the higher accuracy of the face graphs obtained compared to classical Gabor-EBGM ones.

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

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

[3]  김성대.  Generalized Elastic Graph Matching for Face Recognition , 2006 .

[4]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Andrea Lagorio,et al.  On the Use of SIFT Features for Face Authentication , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[6]  Bruce A. Draper,et al.  The CSU Face Identification Evaluation System: Its Purpose, Features, and Structure , 2003, ICVS.

[7]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[11]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..