IMPLEMENTATION OF A VECTOR QUANTIZATION CODEBOOK DESIGN TECHNIQUE BASED ON A COMPETITIVE LEARNING ARTIFICIAL NEURAL NETWORK

被引:0
|
作者
AHALT, SC
CHEN, PK
CHOU, CT
JUNG, TP
机构
[1] Department of Electrical Engineering, The Ohio State University, Columbus, 43210, Ohio
来源
JOURNAL OF SUPERCOMPUTING | 1992年 / 5卷 / 04期
关键词
NEURAL NETWORKS; VECTOR QUANTIZATION; PARALLEL COMPUTING; IMAGE COMPRESSION;
D O I
10.1007/BF00127951
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We describe an implementation of a vector quantization codebook design algorithm based on the frequency-sensitive competitive learning artificial neural network. The implementation, designed for use on high-performance computers, employs both multitasking and vectorization techniques. A C version of the algorithm tested on a CRAY Y-MP8/864 is discussed. We show how the implementation can be used to perform vector quantization, and demonstrate its use in compressing digital video image data. Two images are used, with various size codebooks, to test the performance of the implementation. The results show that the supercomputer techniques employed have significantly decreased the total execution time without affecting vector quantization performance.
引用
收藏
页码:307 / 330
页数:24
相关论文
共 50 条
  • [1] Codebook Design for Vector Quantization Based on a Kernel Fuzzy Learning Algorithm
    Xie, Zongbo
    Feng, Jiuchao
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2011, 30 (05) : 999 - 1010
  • [2] A compensated fuzzy Hopfield neural network for codebook design in vector quantization
    Liu, SH
    Lin, JS
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2000, 14 (08) : 1067 - 1079
  • [3] A learning-based codebook design for vector quantization using evolution strategies
    Zhang, S
    Salari, E
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XXVII, PTS 1AND 2, 2004, 5558 : 41 - 46
  • [4] An improvement on competitive learning neural network by LBG vector quantization
    Basil, G
    Jiang, J
    IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS VOL 1, 1999, : 244 - 249
  • [5] Codebook Design for Vector Quantization Based on a Kernel Fuzzy Learning Algorithm
    Zongbo Xie
    Jiuchao Feng
    Circuits, Systems, and Signal Processing, 2011, 30 : 999 - 1010
  • [6] The application of Fuzzy Hopfield Neural Network to design better codebook for image vector quantization
    Lin, JS
    Liu, SH
    Lin, CY
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1998, E81A (08): : 1645 - 1651
  • [7] Fast image vector quantization using a modified competitive learning neural network approach
    Li, R
    Sherrod, E
    Kim, J
    Pan, G
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 1997, 8 (04) : 413 - 418
  • [8] Expansive and competitive learning for vector quantization
    Muñoz-Perez, J
    Gomez-Ruiz, JA
    Lopez-Rubio, E
    Garcia-Bernal, MA
    NEURAL PROCESSING LETTERS, 2002, 15 (03) : 261 - 273
  • [9] Expansive and Competitive Learning for Vector Quantization
    J. Muñoz-Perez
    J. A. Gomez-Ruiz
    E. Lopez-Rubio
    M. A. Garcia-Bernal
    Neural Processing Letters, 2002, 15 : 261 - 273
  • [10] Codebook enhancement in vector quantization image compression using backpropagation neural network
    Al-Allaf O.N.A.
    Journal of Applied Sciences, 2011, 11 (17) : 3152 - 3160