Presentation 2006-11-10
Vector Quantization Algorithm for Hardware Implementation
Shigeki MATSUBARA, Hiroomi HIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a new vector quantization algorithm that is suitable for hardware implementation. Conventional methods use distance calculations such as Euclid or Manhattan distance to evaluate the similarity between the input and codebook vectors. The proposed algorithm tests if the input vector elements are bounded between the predefined certain ranges and the weighted sum of the test results is used to evaluate the similarity. As no complex calculation is employed, the algorithm can be implemented in hardware easily. The proposed algorithm is verified by the recognition tests. The results show that the system can classify the input data very accurately in spite of the very simple algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Vector quantization / Distance calculation / Hardware implementation / Pattern recognition
Paper # NC2006-62
Date of Issue

Conference Information
Committee NC
Conference Date 2006/11/3(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Vector Quantization Algorithm for Hardware Implementation
Sub Title (in English)
Keyword(1) Vector quantization
Keyword(2) Distance calculation
Keyword(3) Hardware implementation
Keyword(4) Pattern recognition
1st Author's Name Shigeki MATSUBARA
1st Author's Affiliation Oita University()
2nd Author's Name Hiroomi HIKAWA
2nd Author's Affiliation Oita University
Date 2006-11-10
Paper # NC2006-62
Volume (vol) vol.106
Number (no) 341
Page pp.pp.-
#Pages 6
Date of Issue