Wavelet Based Image Compression using Subband Threshold

    6 Votes

Wavelet based image compression has been a focus of research in recent days. In this paper, we propose a compression technique based on modification of original EZW coding. In this lossy technique, we try to discard less significant information in the image data in order to achieve further compression with minimal effect on output image quality. The algorithm calculates weight of each subband and finds the subband with minimum weight in every level. This minimum weight subband in each level, that contributes least effect during image reconstruction, undergoes a threshold process to eliminate low-valued data in it. Zerotree coding is done next on the resultant output for compression. Different values of threshold were applied during experiment to see the effect on compression ratio and reconstructed image quality. The proposed method results in further increase in compression ratio with negligible loss in image quality.

Image compression is a technique of encoding an image to store it or send it using as fewer bits as possible. Presently the most common compression methods for still images fall into two categories: Discrete Cosine Transform (DCT) based techniques and methods based on wavelet transform. Widely used image compression technique JPEG achieves compression by applying DCT to the image, whereas wavelet transform methods generally use discrete wavelet transform (DWT) for this purpose.

With the recent developments in wavelet compression, this method has arisen to be an efficient coding method for still image compression, outperforming today’s DCT based JPEG standards. This state of the art compression technique is accomplished in three stages: 1) wavelet transform, 2) zerotree coding and 3) entropy based coding. Wavelet transform decomposes the image into several multi-resolution subbands in an octave manner, and perfectly reconstructs the original image from them. This multi-level decomposition is done using two dimensional wavelet filters (basis function), among which Haar and Daubechies filters  are very popular. The appropriate choice of filters for the transform is very important in compression schemes to achieve high coding efficiency. Splitting of subband into next higher level four subbands using wavelet transform is shown in Figure.

Splitting of subband

Among the wavelet coding schemes, Shapiro was the first to develop Embedded Zerotree Wavelet (EZW) coding scheme in 1993. It utilizes dependencies among subbands decomposed by wavelets, and uses zero tree to achieve high compression. For successive approximation quantization, the coefficients in subbands are scanned in a pre-determined fashion and their values are compared with an octavely decreasing threshold. Higher compression ratio is achieved using variable length coding method that depends on this previously coded EZW data. Sometimes adaptive arithmetic coding is used for further compression with a cost of complexity and computation time.

Since the publication of EZW coder, there have been many developments in this field. SPIHT was the next to develop a better wavelet coder with improved performance. One of the advantages of these algorithms is that they are embedded in nature and can be stopped at any time whenever the desired results are achieved e.g, when the required compression ratio is achieved or desired reconstructed picture quality (PSNR) is obtained. Recently developed coders offer further improvements by modification of EZW with the cost of complexity and increased processing time, the factors making them difficult to implement for common applications. For this purpose, basic EZW coder was chosen for modifications that is a simple and most widely used wavelet image coder.

Download this file (Wavelet Based Image Compression.doc)Wavelet Based Image Compression[Seminar Report]488 Kb