Pseudo-Zernike Moment Invariants for Recognition of Faces Using Different Classifiers in FERET Database

Author

Nabatchian, A. ; Makaremi, I. ; Abdel-Raheem, E. ; Ahmadi, M.

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Windsor, Windsor, ON

Volume

1

fYear

2008

fDate

11-13 Nov. 2008

Firstpage

933

Lastpage

936

Abstract

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.

Keywords

biometrics (access control); face recognition; feature extraction; hidden Markov models; image classification; support vector machines; FERET database; HMM classifier; SVM; biometrics; face recognition; facial expression; feature extraction; image processing; kNN classifier; pattern recognition; pseudo-Zernike moment invariants; Biometrics; Face recognition; Feature extraction; Humans; Image databases; Image processing; Image recognition; Lighting; Pattern recognition; Spatial databases; Classifier; Face Recognition; Pattern Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Convergence and Hybrid Information Technology, 2008. ICCIT '08. Third International Conference on

Conference_Location

Busan

Print_ISBN

978-0-7695-3407-7

Type

conf

DOI

10.1109/ICCIT.2008.132

Filename

4682151