A Codebook Compression Method for Vector Quantization Algorithm

This study introduces a novel approach to enhance the compression ratio of the vector quantization (VQ) algorithm by specifically targeting the compression of its codebook. The VQ algorithm typically generates an index matrix and a codebook to represent compressed images. The proposed method focuses...

Full description

Saved in:
Bibliographic Details
Published inProceedings of engineering and technology innovation Online Vol. 26; pp. 45 - 54
Main Authors Abul Hasnat, Dibyendu Barman, Md Azizul Hoque, Santanu Halder, Debotosh Bhattacharjee
Format Journal Article
LanguageEnglish
Published Taiwan Association of Engineering and Technology Innovation 29.02.2024
Subjects
codebook
peak signal-to-noise ratio
quantization
structural similarity index
Online AccessGet full text

Cover

More Information
Summary:This study introduces a novel approach to enhance the compression ratio of the vector quantization (VQ) algorithm by specifically targeting the compression of its codebook. The VQ algorithm typically generates an index matrix and a codebook to represent compressed images. The proposed method focuses on reducing the size of the codebook, which comprises N codewords, each with elements quantized into four levels. Each 8-bit element in a codeword is compressed to 2-bits, and the encoded codeword is accompanied by the minimum value and a threshold value in the codebook. Experimental results on benchmark color images, such as baboon, airplane, Lena, and others, demonstrate a significant reduction of 62.50% in the size of the VQ codebook.
ISSN:2413-7146
2518-833X
DOI:10.46604/peti.2024.13268