Application of BP Neural Network with Chebyshev Mapping in Image Compression

The traditional BP neural network has two disadvantages: long training time and easily getting into local minimum. To solve above problem, the neural network with chaotic neuron was proposed. In this paper, the Chebyshev chaotic mapping is used to construct the neural network. In order to evaluate its performance, the scheme of image compression by the neural network was given. The traditional BP and the Chebyshev chaotic neural networks are applied in the image compression. The result of simulation test shows that chaotic neural network is superior to BP network in the effect of image reconstruction.