Face Recognition utilising Elman neural networks

Processing photos and recognizing them by facial architectural features lies among the basic applications of the neural network systems. This study aims investigate face recognition through utilising Elman Neural Networks. In this paper, the remittance waves (Wavelet) are used in order to withdraw more accurate details of the image, and then features were extracted based on the seven resolution and the four statistical properties (location measurement mean, standard deviation and skewness and kurtosis), which address the problems of image capture by the surveillance cameras. This study found that the recognition percentage reached 92%. This study indicated the ability of the seven resolutions and the four statistical features (measuring the middle position, measuring the standard deviation, measuring the inclination and measuring the inclination coefficient) in providing fixed characteristics that can be used as image features for the purpose of recognizing the wanted people. The study also concluded that the success of the neural network in recognizing the wanted due to its ability of handling ongoing data, and that the merging between the engineering features (the seven resolutions and for statistical features) gives good results in recognizing the wanted people.