Wavelet Based Image Compression Using Soft Computing Techniques

Abstract

The Wavelet Transform is a multi-resolution transform, that is, it allows a form of time–frequency analysis (or translation–scale in wavelet speak). When using the Fourier transform the result is a very precise analysis of the frequencies contained in the signal, but no information on when those frequencies occurred. The wavelet based image compression algorithms are used widely compared with other conventional compression algorithms. The wavelet coding based on the coefficient selection and sub band level. In this paper we have used two wavelets such as spherical and geometric wavelets. The spherical representation is a hierarchical description of how total energy gets distributed within each wavelet sub band.In the proposed method, we used fuzzy quantization technique for coefficient selection in the spherical wavelet. The other scheme introduces binary space partitioning scheme and geometric wavelet, where the existing pruning method of binary space partitioning is replaced by the genetic algorithm. We had another experiment with geometric wavelet with Artificial Bee Colony (ABC) algorithm. The experimental results for all the three methods are discussed in this paper. The advantages of these methods are the improved PSNR values at high and medium bit rates.