Wavelet Based Subband Vector Quantization Algorithm for Gray Images

Wavelet decomposition coefficients of a gray level image are vector quantized with flexible, variable sized codewords and a wavelet based tree search algorithm. Vector quantization codewords are designed as rectangles with ratio 1 to 2, which is more efficient in encoding different subbands with minimum error. The performance of the discrete cosine transform is observed in different bands. The low frequency subband is scalar quantized due to the poor performance of DCT in this band.

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

[2]  Jianqin Zhou,et al.  On discrete cosine transform , 2011, ArXiv.

[3]  Pamela C. Cosman,et al.  Vector quantization of image subbands: a survey , 1996, IEEE Trans. Image Process..

[4]  C. Chui,et al.  Wavelets : theory, algorithms, and applications , 1994 .

[5]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[6]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[7]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.