•  
  •  
 

Corresponding Author

El-Bakry, Hazem

Subject Area

Computer and Control Systems Engineering

Article Type

Original Study

Abstract

In this paper, a fast biometric system for face recognition is introduced. We combine both fast and cooperative modular neural nets (MNNs) to enhance the performance of the detection process Such approach is applied to identify frontal views of human faces automatically in cluttered scenes. In the detection phase. neural nets are used to test whether a window of 20x20 pixels contains a face or not The large number of examples required for face and nonface images makes the convergence process very difficult during the learning process. A simple design for cooperative modular neural nets is presented to solve this problem by dividing these data into three groups Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. For the recognition phase, feature measurements are made through Fourier descriptors which are insensitive to rotation, translation and scaling Such feature is modified to reduce the number of neurons in the hidden layer. From these features, wavelet coefficients are extracted which have been shown to provide advantages in terms of better representation for a given data to be compressed finally, the resulted vector is fed to a neural net for face classification. Simulation results for the proposed algorithm show a good performance.

Download

Share

COinS