Dual Objective Feature Selection and Scaled Educlidean Classification for Face Recognition

The statistical description of the face varies drastic ally with changes in pose, illumination and expression. These variations make face recognition (FR) even more challenging. In this paper, two novel techniques are proposed, viz., Dual Objective Feature Selection to learn and select only discriminant features and Scaled Euclidean Classification to exploit within-class information for smarter matching. The 1-D discrete cosine transform (DCT) is used for efficient feature extraction. A complete FR system for enhanced recognition performance is presented. Experimental results on three benchmark face databases, namely, Color FERET, CMU PIE and ORL, illustrate the promising performance of the proposed techniques for face recognition.