DSpace JSPUI

Compression of digital images has been considered as a major area of research for the last two decades and a number of image compression standards have been developed for different applications. The important roles of a compression algorithm are to reduce bandwidth requirement for transmission and memory requirements for storage of all forms of data. In the contemporary multimedia communication world, large memories as well as more than ever before new technologies are available providing high-speed digital communications. Image compression is still of great importance because along with the advances in technologies there is increasing demand for image communication as well as higher quality image printing and display. In this work, the focus is on some key new technologies for image compression with significant attention on the application of Neural Network (NN) for image compression. This work at the outset dwells with presentation of image compression codecs. Emphasis is given on Discrete Cosine Transform (DCT) based JPEG technique and subband coding using multilevel Wavelet Transform (WT). Looking through the shortcomings like blocking artifacts associated with DCT at low bit rates and computational as well as memory complexity associated with DWT, the present work concentrates on developing a new technology using Artificial Neural Network (ANN).