English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90451/105768 (86%)
Visitors : 11045891      Online Users : 565
RC Version 6.0 © 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://asiair.asia.edu.tw/ir/handle/310904400/214


    Title: 3D Effects Elimination Towards Text Recognition In Natural Scene Images
    3D Effects Elimination Towards Text Recognition In Natural Scene Images
    Authors: Ladeev Dmitry
    Contributors: 資訊工程學系碩士班
    Date: 2006
    Issue Date: 2009-10-09 16:36:24 (UTC+8)
    Publisher: 亞洲大學
    Abstract: 3D text recognition is an area that develops fast in the past years due to the great improvement in the computational capabilities of hand devises and computer systems, and the increase in the imaging quality of digital cameras.
    3D text recognition using digital cameras is different from traditional 2D text recognition using scanners in many ways. 3D effects have to be considered and eliminated before the performing of 3D text recognition.Hence, new methodologies have to be developed for 3D text recognition.
    This work is devoted to the preprocessing part of 3D text recognition by performing image enhancement and binarization for further processing and recognition.
    Experiments were conducted on various 3D text images. The results verify the validity and efficiency of the proposed method in the binarization of 3D text images. Moreover, the recognition rate can be enhanced by using the proposed binarization method before the recognition.
    Appears in Collections:[資訊工程學系] 博碩士論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML680View/Open


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


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback