Face Recognition Based on Grey Wolf Optimization for Feature Selection

Face recognition systems are progressively becoming popular as means of determining the people’s identities. Moreover, face images are the only biometric trait that can be found in legacy databases and international terrorist watch-lists and can be taken without the need to the cooperation of subjects. In this paper, we present an effective face recognition system that consists of a set of steps: image preprocessing in which the person’s face is detected and the median filter is applied for noise removal, feature extraction using Gabor filters, feature reduction using principle component analysis, feature selection using the grey wolf optimization (GWO) algorithm, and classification using k-NN classifier. The proposed system has been evaluated using Yale face database. The experimental results have revealed that the proposed system can achieve recognition accuracy up to 97%. Also, the performance of the proposed system is compared to the performance of other face recognition system and the obtained results have revealed that the proposed system is better in terms of both recognition accuracy and run time.