Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map
碩士 === 國立臺灣科技大學 === 資訊工程系 === 97 === Based on the self-organization of Kohonen feature map (SOFM), recently, Pei et al. presented an efficient color palette indexing method to construct a color table for compression. Taking the palette indexing method as a representative, this thesis presents two ne...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/30896519415654495830 |
id |
ndltd-TW-097NTUS5392017 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097NTUS53920172016-05-02T04:11:27Z http://ndltd.ncl.edu.tw/handle/30896519415654495830 Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map 加速基於自組織特徵映射之調色盤建立法 Jyun-Pin Wang 汪均嬪 碩士 國立臺灣科技大學 資訊工程系 97 Based on the self-organization of Kohonen feature map (SOFM), recently, Pei et al. presented an efficient color palette indexing method to construct a color table for compression. Taking the palette indexing method as a representative, this thesis presents two new strategies, the pruning-based search strategy and the lookup table (LUT)-based update strategy, to speed up the learning process in the SOFM. The proposed search strategy is used to speed up the process for finding the winning neuron in each iteration; the proposed LUT-based update strategy is used to speed up the lateral update interaction between the winning neuron and its neighboring neurons in the SOFM. Based on four typical testing images, experimental results demonstrate that our proposed two strategies have 35% execution-time improvement ratio in average. The practical improvement ratio is very close to that in the theoretical analysis. Kuo-Liang Chung 鍾國亮 2009 學位論文 ; thesis 24 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 資訊工程系 === 97 === Based on the self-organization of Kohonen feature map (SOFM), recently, Pei et al. presented an efficient color palette indexing method to construct a color table for compression. Taking the palette indexing method as a representative, this thesis presents two new strategies, the pruning-based search strategy and the lookup table (LUT)-based update strategy, to speed up the learning process in the SOFM. The proposed search strategy is used to speed up the process for finding the winning neuron in each iteration; the proposed LUT-based update strategy is used to speed up the lateral update interaction between the winning neuron and its neighboring neurons in the SOFM. Based on four typical testing images, experimental results demonstrate that our proposed two strategies have 35% execution-time improvement ratio in average. The practical improvement ratio is very close to that in the theoretical analysis.
|
author2 |
Kuo-Liang Chung |
author_facet |
Kuo-Liang Chung Jyun-Pin Wang 汪均嬪 |
author |
Jyun-Pin Wang 汪均嬪 |
spellingShingle |
Jyun-Pin Wang 汪均嬪 Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
author_sort |
Jyun-Pin Wang |
title |
Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
title_short |
Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
title_full |
Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
title_fullStr |
Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
title_full_unstemmed |
Speedup of Color Palette Indexing in Self-Organization of Kohonen Feature Map |
title_sort |
speedup of color palette indexing in self-organization of kohonen feature map |
publishDate |
2009 |
url |
http://ndltd.ncl.edu.tw/handle/30896519415654495830 |
work_keys_str_mv |
AT jyunpinwang speedupofcolorpaletteindexinginselforganizationofkohonenfeaturemap AT wāngjūnpín speedupofcolorpaletteindexinginselforganizationofkohonenfeaturemap AT jyunpinwang jiāsùjīyúzìzǔzhītèzhēngyìngshèzhīdiàosèpánjiànlìfǎ AT wāngjūnpín jiāsùjīyúzìzǔzhītèzhēngyìngshèzhīdiàosèpánjiànlìfǎ |
_version_ |
1718254046420140032 |