Codebook ordering for vector quantization



Journal Title

Journal ISSN

Volume Title


Texas Tech University


Address predictive vector quantization (APVQ) utilizes an ordered codebook to exploit the dependency among close input vectors. The Kohonen algorithm is often chosen in APVQ. However, the Kohonen algorithm is not applicable while a codebook already exists. In this thesis three methods of ordering an existing codebook have been developed. Theoretically these codebook ordering methods can be utilized in any vector quantization in order to reduce the output bit rate. Here we apply it to two types of vector quantization approaches, geometric vector quantization (GVQ) and vector quantization based on the LBG algorithm. The results of codebook ordering on vector quantization based on the LBG algorithm are quite good. However, codebook ordering does not have good performance on GVQ. Therefore, while applying codebook ordering to one specific VQ, we should consider the property of this VQ in order to achieve a satisfactory result.



Geometric quantization, Algebraic, Geometry, Differential, Geometry, Wavelets (Mathematics), Vector spaces, Algorithms