Image Compression Using Transform Coding Methods

The proposed work describes the algorithms for Image Compression using Transform Coding Methods: Modified Hermite Transform (MHT), Discrete Cosine Transform (DCT) and Wavelet Transform (WT). In MHT and DCT, the given image is divided into NxN subblocks and transformation is applied to each block. Then, a threshold value is selected such that to minimize the mean square value between Original image and Reconstructed image. Wavelet Transform decomposes signal into set of basis functions. These basis functions, called wavelets, are obtained from a single prototype wavelet by dilations and contractions as well as shifts. Using Discrete time Wavelet Transform any given image can be decomposed into 'n' levels. The lower levels of decomposition correspond to higher frequency sub bands. In particular, level 1 corresponds to highest frequency sub-band and it is the finest level of resolution. Correspondingly nth level corresponds to lowest frequency sub-bands and has coarsest resolution. In this work, different wavelet Transforms like Symlet, Haar, Daubechies and Coiflet will be used to compress the 1-D, 2-D and color images and these results will be compared with DCT and MHT results.