Performance analysis of vector quantizer for imaging data clustering algorithms

Ting-Wei Hou, Houng Kuo Ku, Yuan Tsung Chen, Horng Show Koo

研究成果: Paper同行評審

摘要

Generalized Lloyd Algorithm(GLA) is the most famous known algorithm technique in the field of vector quantizer design. It runs very fast, but it can only find a poor local optimum in most cases. In 1989, Zeger proposed the Stochastic Relaxation Decoder(SRD) algorithm to overcome the weakness of the GLA. Theoretically, it has the ability to find the global optimum. In practice, it can achieve the near optimal performance. We proposed an improved approach named Codebook Reorganization Algorithm(CRA), for the vector quantizer design. The performance of CRA is superior to the above-mentioned algorithms demonstrated by the experimental results. It can find better codebooks than GLA. It also can find a codebook as good as SRD in less time.

原文English
頁面1649-1650
頁數2
出版狀態Published - 2006 十二月 1
事件13th International Display Workshops, IDW '06 - Otsu, Japan
持續時間: 2006 十二月 62006 十二月 6

Other

Other13th International Display Workshops, IDW '06
國家Japan
城市Otsu
期間06-12-0606-12-06

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Radiology Nuclear Medicine and imaging
  • Atomic and Molecular Physics, and Optics

指紋 深入研究「Performance analysis of vector quantizer for imaging data clustering algorithms」主題。共同形成了獨特的指紋。

引用此