Optimal face recognition method using ant colony based Back Propagation network

This paper introduces a novel method for human face recognition that employs a new back propagation neural network (BPN) training algorithm performed with an ant colony optimization (ACO) to get the optimal connection weights of the BPN of the classification phase. The aim is to automate the face recognition system using computational intelligence. The input image undergoes histogram equalization that enhances the image contrast by transforming the values in the color map of an indexed image, so that the histogram of the output image approximately matches with specified histogram. Feature extraction is then performed using DWT. Haar wavelet has been applied and the result generated is the DWT coefficients as a feature vector. ACO is used to select the optimal feature sets from the feature vector set. The selected features are fed to a back propagation network hybrid with ant colony optimization (BPN-ACO) for classification. The system was tested on the FIA database. Experimental results for human face recognition confirm that the proposed method lends itself to higher classification accuracy relative to existing techniques.