Face Recognition Using Histogram-based Features in Spatial and Frequency Domains

Previously, we proposed an efficient algorithm using vector quantization (VQ) histogram for facial image recognition in low-frequency DCT domains. In this paper, we newly utilize Local Binary Pattern (LBP) histogram in spatial domain. These two histograms, which contain both spatial and frequency domain information of a facial image, are utilized as a very effective personal feature. Publicly available AT&T database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using combined histogrambased features can achieve much higher recognition rate. Keywords-Face recognition; Vector quantizaiton (VQ); Local Binary Patterns (LBP); DCT coefficients.