FACE RECOGNITION WITH LOCAL CONTOURLET COMBINED PATTERNS

This paper proposes a novel face image descriptor called local contourlet combined patterns (LCCP), based on the Non-Subsampled Contourlet Transform (NSCT), for face recognition. NSCT is a multiresolution analysis tool and can capture image information at multiple scales, orientations, and frequency bands. To adapt to the NSCT filter bank, a new encoding method named mean-based contrast patterns (MCP) is presented. We apply LBP and MCP to different levels' NSCT coefficient images respectively and then combine them to obtain a robust representation. Futhermore, block-based kernel Fisher linear discriminant (BKFLD) is used to select the most discriminative feature sets. Face recognition experiments on FERET database demonstrate the effectiveness of our proposed approach.