Image compression using single layer linear neural networks

AbstractImages and text form an integral part of website designing. Images have an engrossing appeal and that’s why they attract more and more visitors. But, due to expensive bandwidth and time-consuming downloads; it has become essential to compress images. There are various methods and techniques available to compress images. In this paper, an effective technique is introduced called Wavelet-Modified Single Layer Linear Forward Only Counter Propagation Network (MSLLFOCPN) technique to solve image compression. This technique inherits the properties of localizing the global spatial and frequency correlation from wavelets. Function approximation and prediction are obtained from neural networks. Consequently counter propagation network was considered for its superior performance and the research helps to propose a new neural network architecture named single layer linear counter propagation network (SLLC). Several benchmark images are used to test the proposed technique combined of wavelet and SLLC network. The experiment results when compared with existing and traditional neural networks shows that picture quality, compression ratio and approximation or prediction are highly enhanced