A Complementary Local Feature Descriptor for Face Identification
Jonghyun Choi, William R. Schwartz, Huimin Guo and Larry S. Davis
IEEE Workshop on Applications of Computer Vision 2012
[ Circular Center Symmetric-Pairs of Pixels (CCS-POP) ]

Abstract
In many descriptors, spatial intensity transforms are often packed into a histogram or encoded into binary strings to be insensitive to local misalignment and compact. Discriminative information, however, might be lost during the process as a trade-off. To capture the lost pixel-wise local information, we propose a new feature descriptor, Circular Center Symmetric-Pairs of Pixels (CCS-POP). It concatenates the symmetric pixel differences centered at a pixel position along various orientations with various radii; it is a generalized form of Local Binary Patterns, its variants and Pairs-of-Pixels (POP). Combining CCS-POP with existing descriptors achieves better face identification performance on FRGC Ver. 1.0 and FERET datasets compared to stateof- the-art approaches.

Paper

[PDF]

Code Download

MATLAB Code
CPP-MEX (x64): MATLAB Interface of binary of C++ Implementation for 64 bit Windows

Citation

@inproceedings{choiSGD12wacv,
	author    = {Jonghyun Choi, William R. Schwartz, Huimin Guo and Larry S. Davis},
	title     = {A Complementary Local Feature Descriptor for Face Identification},
	booktitle = {IEEE Workshop on Applications of Computer Vision (WACV)},
	year      = {2012}
}

Contact

Bug report or any questions
Send an email to Jonghyun Choi jhchoi_[at]_umd_[dot]_edu