International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 77 - Number 13 |
Year of Publication: 2013 |
Authors: Md. Mozammel Haque, Md. Al-amin Bhuiyan |
10.5120/13541-0861 |
Md. Mozammel Haque, Md. Al-amin Bhuiyan . ART Network based Face Recognition with Gabor Filters. International Journal of Computer Applications. 77, 13 ( September 2013), 8-12. DOI=10.5120/13541-0861
Face recognition is emerging as an active research area in numerous commercial and law enforcement applications. Different existing methods perform well under certain conditions. Gabor-based face representation has achieved enormous success in face recognition. This research addresses a novel algorithm for face recognition using neural networks trained by Gabor features. The system is commenced on convolving a face image with a series of Gabor filter coefficients at different scales and orientations. The novel contribution of this paper is the scaling of rms contrast. The neural network employed for face recognition is based on the multilayer perceptron (MLP) architecture with ART algorithm. The effectiveness of the algorithm has been justified over a face database with images captured at different illumination conditions.