GA-ANN based technique for face recognition : PCA features vs average grey level value features

This paper investigates a feature selection and classification technique for face recognition using genetic algorithms and artificial neural networks. The experiments using average grey level value features and PCA features have been conducted on a face image dataset which is extracted from FERET benchmark database. For average grey level value features experiments, different sizes of feature extraction areas and different feature combination sequences are investigated. The effects of aging process on the proposed technique are also investigated. A detailed comparative analysis of experimental results is included in this paper.