Adaptive searchless fractal image compression in DCT domain

Abstract

In this paper, an adaptive searchless fractal image compression technique in the frequency domain is proposed. Proposed methods aim to improve image compression fidelity criteria in discrete cosine transform domain (DCT). In this work spatial domain, adaptive methods are exercised in discrete cosine domain for optimisation of image encoding. Variance-based selection of image blocks and adaptive threshold are two simple adaptive techniques administered on attaining objectives of image compression. First, range block exclusion adaptive method removes homogenous range blocks before FIC coding. This exclusion consequently recedes the number of range-domain blocks matching operations. Proposed hybrid compression algorithm localises domain block location about range block without searching entire domain pool. Second technique implemented is domain pool size reduction. Variances of range and domain blocks are compared. Domain blocks that are within threshold value are kept in the pool. Finally to further optimise the performance of encoding adaptive threshold in quadtree partitioning is applied in along with variance domain selection approach. Simulation results substantiate that adaptive techniques have higher coding performance in terms of encoding time, peak signal to noise ratio and compression ratio in contrast to the fractal image encoding without adaptive techniques.