English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28607/40644
Visitors : 5354415      Online Users : 174
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/6094

Title: 改進動態空間扭曲演算法之二維影像辨識
An Improved Dynamic Space Warping Algorithm for 2D Image Recognition
Authors: Chia-Yen Hsu
徐嘉延
Contributors: NTOU:Department of Computer Science and Engineering
國立臺灣海洋大學:資訊工程學系
Keywords: 動態空間扭曲演算法;二維影像辨識
DSW Algorithm;2D Image Recognition
Date: 2009
Issue Date: 2011-06-22T08:43:07Z
Abstract: 本論文提出一個針對二維影像辨識之改進動態空間扭曲演算法。動態空間扭曲(Dynamic Space Warping; DSW)演算法為動態程式,主要用於二維影像辨識上,具有複雜的四維計算結構,其辨識能力佳,藉由內嵌可調整的扭曲(warping),能解決縮小、放大、旋轉等空間扭曲問題。DSW演算法非常可靠,但其龐大的計算量造成執行速度上的瓶頸。本論文提出的改進DSW演算法具備新的扭曲形態(warping pattern),實驗結果顯示,新的扭曲形態不僅增進了將近百分之五十的執行速度,而且依然保持良好辨識效能。
In this thesis, we proposed an improved dynamic space warping (DSW) algorithm for 2D image Recognition. DSW algorithm, a dynamic programming of 2D image recognition method with 4D complexity, can solve space warping problems such as shrinking, enlarging, rotation and distortion with good performance by embedding controllable warping distance. DSW algorithm is very reliable but the massive computation becomes the bottleneck of execution speed. We presented an improved DSW algorithm with new warping patterns, and the experimental results have shown new DSW algorithm not only speeds up the execution time almost 50% but also preserves good recognition performance.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M96570044
http://ntour.ntou.edu.tw/ir/handle/987654321/6094
Appears in Collections:

Files in This Item:

There are no files associated with this item.



All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback