A Discriminant Pseudo Zernike Moments in Face Recognition

This paper introduces a novel discriminant moment-based method as a feature extraction technique for face recognition. In this method, pseudo Zernike moments are performed before the application of Fisher’s Linear Discriminant to achieve a stable numerical computation and good generalization in small-sample-size problems. Fisher’s Linear Discriminant uses pseudo Zernike moments to derive an enhanced subset of moment features by maximizing the between-class scatter, while minimizing the within-class scatter, which leads to a better discrimination and classification performance. Experimental results show that the proposed method achieves superior performance with a recognition rate of 97.51% in noise free environment and 97.12% in noise induced environment for the Essex Face94 database. For the Essex Face95 database, the recognition rates obtained are 91.73% and 90.30% in noise free and noise induced environments, respectively. ACM Classification: I.5.4. (Computer Methodologies-Pattern Recognition – Applications)