Face Recognition Using Legendre Moments

The wide range of variations in human face due to view point, pose, illumination and expression deteriorate the recognition performance of the existing Face recognition systems. This paper proposes a new approach to face recognition problem using Legendre moments for representing features and nearest neighbor classifier for classification. The Legendre moments are orthogonal and scale invariant in its characteristics and hence it is suitable for representing the features of the face images. The obtained feature vectors are transformed using Linear Discriminant Analysis and stored in the database and are compared using Nearest neighbor classifier during testing. For testing the proposed approach, Legendre feature vector of size 12 is used for the images of ORL (Olivetty Research Laboratories) database with 40 subjects and each of them having 10 orientations. Similarly the Hu moments, Discrete Cosine Transforms (DCT) are also used for feature extraction. The recognition percentage is compared with the proposed approach. The recognition percentage of 98.25% is achieved using Legendre moments which are comparatively superior than other Face recognition approaches using central moments (Hu), DCT or other statistical approaches.