Authors: Seongsoo Cho; Bhanu Shrestha; Jongsup Lee
Addresses: Department of Electronic Engineering, Kwangwoon University, 20 Kwangwoon-ro, Nowon-gu, Seoul, 139-701, Korea ' Department of Electronic Engineering, Kwangwoon University, 20 Kwangwoon-ro, Nowon-gu, Seoul, 139-701, Korea ' Department of LINC, Dongguk University, #710, 82-1 Pil-dong 2-ga, Jung-gu, Seoul 100-272, Korea
Abstract: The proposed work is a mathematical and morphological erosion calculation method through defuzzification. It defines a λ-fuzzy set measure in all subsets of defuzzification, which measures degrees of inclusion on the fuzzy set measure of each subset, replaces as a result of the fuzzy integral by performing defuzzification of images within the mask of such measures, and defines a fuzzy morphological calculation operator by an erosion on the basis of the fuzzy set measure. The experimental results show 92% of the heterogeneous template matching and 98% of the matching based on the fuzzy set measure. The heterogeneous matching and the average fuzzy matching time took 27.4 and 12.3 s, respectively. The proposed method achieved not only reduction in detecting time by skipping the templates but also the more strong detections on the facial colour and the face in the similar background when compared with the heterogeneous template-matching method.
Keywords: face recognition; blocking process; character generation; facial images; image recognition; biometrics; fuzzy measures; defuzzification; fuzzy sets; facial colour.
International Journal of Security and Networks, 2014 Vol.9 No.4, pp.185 - 189
Received: 11 Mar 2014
Accepted: 12 Mar 2014
Published online: 04 Dec 2014 *