Image De-noising and Compression Using Discrete Wavelet Transform

Abstract

Image denoising and compression has remained a fundamental problem in the field of image processing aiming at the removal of noise which may corrupt an image during its acquisition or transmission while sustaining its quality. Wavelets gave a superior performance in image denoising and compression due to its properties such as multi resolution.In this thesis an adaptive method of image denoising in the wavelet sub band domain has been proposed.The idea behind using this technique the DWT process the horizontal ,vertical and diagonal details of the image without affect the approximation details, it improves the performance of the mathematical software(MATLAB) of denoising function. The experimental evaluation shows that it removes noise significantly and more effectively than the existed denoise technique it show that by applying different wavelet family types, different noise level and different level of decomposition.In the second phase of thesis after image became free of noise the compression technique jpeg 2000 has been applied to the image due to the development and demand of multimedia product grows increasingly fast, contributing to insufficient bandwidth of network and storage of memory device. Therefore, the theory of data Compression is useful because it helps reduce the consumption of expensive resources such as hard disk space or transmission bandwidth.In this thesis, the fundamental theory of image compression in chapter 2 has been briefly introduced,two typical standards JPEG and JPEG 2000 will be described and implemented to the denoise image in chapter 4. The last given image is compressed denoise image without degraded its quality.