3D Face Recognition Using Radon Transform and Symbolic Factorial Discriminant Analysis

Automatic recognition of human faces is considered to be a challenging task despite significant progress in both computer vision and pattern recognition. A facial recognition system is a computer application of automatically identifying or verifying a person from a digital image or a video frame from a video source. Often, variations such as in-depth pose changes or illumination variations increase the dissimilarity of two face images of the same person more than the dissimilarity of different persons’ face images. In this paper, we have proposed a novel method for three dimensional (3D) face recognition using Radon transform and Symbolic Factorial Discriminant Analysis (Symbolic FDA) is proposed. In this method, the Symbolic Factorial Discriminant Analysis (Symbolic FDA) based feature computation takes into account of face image variations to a larger extent and has the advantage of dimensionality reduction. The experimental results have yielded 99.80% recognition performance with reduced computational cost, which compares well with other state-of-the-art methods