COMPARATIVE ANALYSIS OF DIGITAL IMAGE COMPRESSION USING ANN AND RLE

Abstract

Image compression helps in fast data transfer and effective memory utilization. The objective of image compression is to reduce data redundancy of the image while retaining high image quality. This paper describes an approach for wavelet based image compression using Multi Layer Feed Forward Neural Network with Error Back Propagation training algorithm applied to second and third level approximation component and modified Run Length Coding is applied to second and third level Horizontal and vertical components and threshold is used to discard insignificant coefficients. The experimental results on several images indicate that the proposed algorithm is superior to the existing algorithm in terms of Compression Ratio (CR) by 30% to 40% with different wavelets.. The performance of the proposed algorithm is also compared with different discrete wavelet transform (DWT) techniques.