中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/29218
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 78852/78852 (100%)
Visitors : 37997426      Online Users : 833
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/29218


    Title: Handwritten Chinese characters recognition by greedy matching with geometric constraint
    Authors: Hsieh,AJ;Fan,KC;Fan,TI
    Contributors: 資訊工程研究所
    Keywords: RELAXATION;GRAPH
    Date: 1996
    Issue Date: 2010-06-29 20:16:40 (UTC+8)
    Publisher: 中央大學
    Abstract: In this paper, a greedy matching algorithm with geometric constraint for solving the polygonal arcs matching (boundary line segments matching) is proposed. Assume the matched cost and the unmatched penalty of each line segment are given, as well as any two matched pairs in the matching which preserves the geometric relation. Our goal is to find a matching such that (1) the sum of costs of matched line segments and the penalties of unmatched line segments is minimum, and (2) the matching preserves the geometric relation. The proposed greedy matching algorithm consists of two main modules. The first is an optimal matching module, which utilizes the optimization matching method to find an optimal matching without the geometric constraint. The second module is an evaluation and update module, which deletes the matched pair with a geometric relation having the maximum inconsistency after each matched pair has been evaluated, and a new matching is found again. The algorithm continues until a stable matching is found. To verify the validity of the proposed algorithm, we implement it to recognize handwritten Chinese postal characters. We selected 51 Chinese postal characters as the prototype characters, and the experiments are conducted on 2550 samples, with each category containing 50 variations. The recognition rate is 91.8%. Experimental results reveal the feasibility of our proposed method in recognizing handwritten Chinese postal characters.
    Relation: IMAGE AND VISION COMPUTING
    Appears in Collections:[Graduate Institute of Computer Science and Information Engineering] journal & Dissertation

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML464View/Open


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

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明