STUDY OF FACE RECOGNITION TECHNIQUES USING VARIOUS MOMENTS

Abstract

The field of face recognition has been explored a lot and the work is still going on. In the presented work we have proposed a novel approach for face recognition using moments. Four methods have been used for feature extraction: Hu moments, Zernike moments, Legendre moments and Cumulants. Hu moments are a set of seven moments which have been derived from the conventional geometric moments. These are invariant against rotation, scaling and translation. Legendre moments and Zernike moments have an orthogonal basis set and can be used to represent an image with a minimum amount of information redundancy. They are based on the theory of orthogonal polynomials and can be used to recover an image from moment invariants. Cumulants are sensitive to the image details and therefore are suitable for representing the features of images. For feature extraction, moments of different orders are calculated which form the feature vectors. The obtained feature vectors are stored in the database and are classified using three classifiers: Minimum Distance Classifier, Support Vector Machine and K Nearest Neighbor. For testing the proposed approach, the ORL (Olivetty Research Laboratories) database is used. It consists of 40 subjects, each having 10 orientations.