English  |  正體中文  |  简体中文  |  Items with full text/Total items : 6481/11653
Visitors : 23398800      Online Users : 122
RC Version 3.2 © 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://ir.ncue.edu.tw/ir/handle/987654321/1726

Title: DWT Based Text Localization
Authors: Chung-Wei Liang;Po-Yueh Chen
Contributors: 資訊工程學系
Keywords: Text Extraction
Haar DWT
Thresholding
Morphological Operator
Logical and Operator
Date: 2004-02
Issue Date: 2010-11-12T07:09:26Z
Abstract: This paper presents an efficient yet simple method to extract text regions from static images or video sequences. The operation speed of Haar discrete wavelet transform (DWT) operates the fastest among all wavelets because its coefficients are either 1 or -1. This is one of the
reasons we employ Haar DWT to detect edges of candidate text regions. The resulted detail component sub-bands contain both text edges and non-text edges. However, the intensity of the text edges is different from that of the non-text edges. Therefore, we can apply thresholding to preliminary remove the non-text edges. Text regions are composed of vertical edges, horizontal edges and diagonal edges. Morphological dilation operators are applied to connect isolated text edges of each detail component sub-band in a transformed binary image. According to the experiment results, real text regions are the overlapped portion of three kinds of dilated edges. Hence, we can apply the logical AND operator to three kinds of dilated edges and obtain the final text regions correctly.
Relation: International Journal of Applied Science and Engineering, 1,2004:105-116
Appears in Collections:[資訊工程學系] 期刊論文

Files in This Item:

File SizeFormat
DWT based text localization.pdf3688KbAdobe PDF3017View/Open


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

 


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