An efficient method for recognition of human faces using higher orders Pseudo Zernike Moment Invariant

Abstract

This paper introduces a new method for the recognition of human faces in 2-dimensional digital images using a new localization of facial information and Pseudo Zernike Moment Invariants (PZMI) as features and a radial basis function (RBF) neural network as the classifier. In this paper the effect of two parameters in recognition rate improvement are studied. These include the order of the PZMI as well as facial candidate ratio (FCR) of images. The tests are carried out on the Olivetti Research Laboratory (ORL) database and a comparative study with two of the existing techniques are included to show the effectiveness of the proposed technique.