Pseudo-Zernike Moment Invariants for Recognition of Faces Using Different Classifiers in FERET Database
A. Nabatchian, Iman Makaremi, Esam Abdel‐Raheem, Majid A. Ahmadi · 2008
Face recognition, the main biometric used by human beings, has plenty of applications in identity validation and recognition and has become one of the hottest topics in the area of image processing and pattern recognition. Pseudo-Zernike moment invariant was chosen as the feature extractor due to its good results among other moment invariants. In this paper pseudo-Zernike moment invariant has been applied on the FERET database of faces which includes a variety of images with different illuminations and facial expression. Performance of kNN, SVM, and HMM classifiers for this application is studied.