Visual entropy-based classified bath fractal transform for image coding

A novel image coding method using the visual entropy (VE)-based classification of image blocks and classified bath fractal transform (CBFT) algorithm, VECBFT, is proposed. At first the VE is introduced conceptually and the implementation of VE-based classification of image blocks is presented. Secondly, the CBFT is described generally. Finally, a combination of the VE and CBFT generates a new algorithm-VECBFT, which allows the decoded images to keep a good subjective quality with some improvements of the compression performance. The VECBFT can be an attempt to integrate human visual system (HVS) into an adaptive algorithm for image compression.

[1]  Allen Gersho,et al.  Image compression with variable block size segmentation , 1992, IEEE Trans. Signal Process..

[2]  Bhaskar Ramamurthi,et al.  Classified Vector Quantization of Images , 1986, IEEE Trans. Commun..

[3]  D. M. Monro,et al.  Fractal approximation of image blocks , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Joseph Naor,et al.  Multiple Resolution Texture Analysis and Classification , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.