Face Recognition by Pupils' Locations-Introduced Gabor Wavelet Networks
Qiuqi Ruan · Signal Processing · 2009
Gabor wavelet networks are efficient for feature extraction and image representation.This paper approaches introducing pupils' locations information into the process of face feature extraction implemented by Gabor wavelet networks in order to improve the efficiency of feature extraction.The pupils' locations information was used in two ways.Firstly,it was used to form the T-shape initial lo- cation distribution of Gabor wavelets in network optimization phase for the purpose of extracting more u.seful feature for recognition given a certain amount of wavelets.Secondly,it was used as locating information in the reparameterization phase to greatly simplify the repa- rameterization procedure.After feature extraction by Gabor wavelet networks,this paper adopts the method of kernel associative memory (KAM) to classify the feature.The experimental result showed that utilizing pupils' locations information could obviously improve the efficiency of feature extraction,and that compared to methods of Euclidean Distance,normalized cross correlation and nearest feature line (NFL),KAM achieved a better recognition rate.