A comparative Study for Designing an Efficient Intelligence System for the Process of Discrimination

Abstract

Face recognition is one of the most important biometrics techniques used to identify people. The research aims to build an efficient system by devising a new method of discrimination that includes advanced image processing techniques and intelligent techniques. This work has been implemented in several stages, the first of which is the arrangement of the database, Followed by pre-processing based on the integration of Gaborand DCT conversion. And then adopt two methods in extracting statistical features, the first dependent first-class statistics, the second dependent second-class statistics of the GLCM matrix and then draw the important features of them. In the phase of discrimination, two types of artificial neural networks were used after their construction in the 2016 MATLAB environment, BPNN and Elman. Finally, the efficiency of the methods used and the identification of the best were compared.