A Wavelet Based Approach for Compression of Color Images

The use of color in image analysis and compression is becoming more and more popular. The high quality color images are in demand, but the bandwidth and power resources are limited, this shows the requirement of effective color image compression algorithm which is suitable to human visual system. However most of the existing algorithms are designed for gray scale visual information. In this work a unique wavelet based approach is proposed for compression of color images. Wavelet families are used to characterize the quality of image by calculating quality estimation parameters, which are, peak signal to noise ratio, energy retained, entropy and redundancy. The entropy calculations are done using color histogram and coding programme is developed for estimation of PSNR, ER and redundancy of the compressed image. The results are analyzed and a set of criteria is determined for the acceptability of coding algorithm. Results show that Biorthogonal wavelet filter outperforms the orthogonal one in quality of compressed image but the orthogonal filter is more energy preserving.