A feature based face recognition technique using Zernike moments

Abstract

In this paper, a face recognition approach using Zernike moments is presented for the main purpose of detecting faces in surveillance cameras. Zernike moments are invariant
to rotation and scale and these properties make them an appropriate feature for automatic face recognition. A Viola-Jones detector based on the Adaboost algorithm is employed for detecting the face within an image sequence. Pre-processing is carried out wherever it is needed. A fuzzy enhancement algorithm is also applied to achieve uniform illumination. Zernike moments are then computed from each detected facial image. The final classification is achieved using a kNN classifier. The performance of the proposed methodology is compared on three different benchmark datasets. The results illustrate the efficacy of Zernike moments for the face recognition problem in video surveillance.