A new hybrid approach for still image compression based on Vector Quantization (VQ), Fractal Approximation and Wavelet Transforms is proposed. It aims to improve in terms of bit rate and Peak-to-Peak Signal-to-Noise (PSNR) the hybrid approach for image compression based on VQ and fractal approximation developed in the literature. Also it tends to limit the blocking effects which usually appears at low bit rates by partitioning the Wavelet Transforms domain instead of the spatial domain. By this approach, the constraint of contraction mapping is not required, fractal approximation that uses the self-similarity of grey patterns works on the approximated image.
展开▼
