Hyperbolic tangent function based two layers structure neural network

The objective of image compression is to reduce irrelevance and redundancy of the image data in order to be able to store or transmit data in an efficient form. The best image quality at a given compression rate is the main goal of image compression. In this paper, we present a hyperbolic tangent function based back propagation network to improve the quality of image compression. Hyperbolic tangent function has better properties than sigmoid function as the new back propagation network´s activation function for image compression. The new hyperbolic tangent function based back propagation network and it´s arithmetic are presented and described in the paper. It has been proved in many examples that the new network gets good results in the compression quality and compression speed at a given compression rate.