Title :
An efficient method for recognition of human faces using higher orders Pseudo Zernike Moment Invariant
Author :
Haddadnia, Javad ; Ahmadi, Majid ; Faez, Karim
Author_Institution :
ECE Dept., Windsor Univ., Ont., Canada
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.
Keywords :
Zernike polynomials; face recognition; feature extraction; image classification; radial basis function networks; 2D digital images; Olivetti Research Laboratory database; Pseudo Zernike Moment Invariant; Zernike polynomials; facial candidate ratio; facial information localization; feature extraction; human face recognition; image classification; radial basis function neural network; two dimensional digital images; Application software; Data mining; Face recognition; Facial features; Feature extraction; Humans; Image recognition; Image segmentation; Java; Shape measurement;
Conference_Titel :
Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on
Conference_Location :
Washington, DC, USA
Print_ISBN :
0-7695-1602-5
DOI :
10.1109/AFGR.2002.1004175
