Noiseless coding of VQ index using index grouping algorithm

In a memoryless vector quantization (VQ) of images, each image block is quantized independently, while its corresponding index is sent to the decoder. Since the image blocks are highly correlated, many blocks may correspond to the same index. This paper presents a noiseless coding algorithm which groups up the blocks with the same index and then encodes the group path efficiently. Simulation results indicate that the new algorithm improves coding efficiency without introducing any extra loss of information.

[1]  Chaur-Heh Hsieh,et al.  New Fuzzy Clustering Algorithms For Vector Quantization Of Images , 1993, IEEE 1993 International Conference on Consumer Electronics Digest of Technical Papers.

[2]  Chaur-Heh Hsieh,et al.  Image compression using finite-state vector quantization with derailment compensation , 1993, IEEE Trans. Circuits Syst. Video Technol..

[3]  Nasser M. Nasrabadi,et al.  Image coding using vector quantization: a review , 1988, IEEE Trans. Commun..

[4]  Robert M. Gray,et al.  Finite-state vector quantization for waveform coding , 1985, IEEE Trans. Inf. Theory.