An Orientation-based Face Recognition Algorithm

Yufeng Zheng


Face recognition, Hamming distance, Face pattern byte (FPB), Gabor wavelet transform (GWT), orientation coding


A new face recognition algorithm is proposed in this paper, which utilizes facial orientation code optimized for Hamming distance. Gabor wavelet transform is a common tool for orientation analysis in a 2D image; whereas Hamming distance is an efficient distance measurement for multiple classifications such as face recognition. Specifically, at each frequency band, an index number representing the strongest orientational response is selected, and then encoded in binary format to favor the Hamming distance calculation. Multiple-band orientation codes are then organized into a face pattern byte (FPB) by using order statistics. With the face pattern bytes, Hamming distances are calculated and compared to achieve face identification. A set of experiments are conducted to compare the proposed FPB method with one classical method, PCA (principal component analysis). Experimental results tested with one visible database and two thermal face databases show that the FPB algorithm is very promising in contrast with PCA. We also found that the face recognition performance on thermal databases are higher than visible database.

Important Links:

Go Back