Neural network technology for pattern recognition, stock prediction and market forecasting

High Performance Face Recognition Based on Wavelet and Neural Networks

Download now Matlab source code
Requirements: Matlab, Matlab Image Processing Toolbox, Matlab Neural Network Toolbox, Matlab Wavelet Toolbox.

Wavelet transforms are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. We demonstrate experimentally that when Wavelet coefficients are fed into a backpropagation neural network for classification, a high recognition rate can be achieved by using a very small proportion of transform coefficients. This makes Wavelet-based face recognition much more accurate than other approaches.

The code has been tested with AT&T database achieving an excellent recognition rate of 97.90% (40 classes, 5 training images and 5 test images for each class, hence there are 200 training images and 200 test images in total randomly selected and no overlap exists between the training and test images).

Index Terms: Face recognition, neural networks, feature extraction, wavelet transform, face matching, face identification, wavelet, ann, artificial neural networks, nn.

Release 1.0 Date 2006.05.29
Major features:

• Face recognition based on Wavelet and Neural Networks
• High recognition rate: 97.90% using AT&T Database
• Easy and intuitive GUI
• Demo code (protected P-files) available for performance evaluation