National Taiwan Ocean University Institutional Repository:Item 987654321/18523
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28607/40644
Visitors : 4808003      Online Users : 239
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item:

Title: 英文文件中之字元特徵擷取與辨識
Literal Feature Extraction and Recognition In An English Document
Authors: Ying-Liang Hsieh
Contributors: NTOU:Department of Electrical Engineering
Keywords: 字元辨識;特徵擷取;特徵比對
character recognition;feature extraction;feature matching
Date: 2005
Issue Date: 2011-07-04
Abstract: 本文主要是利用影像處理的原理來發展一套OCR字元辨識系統,該系統主要是用來辨識英文文件中的英文字元。在本系統中,首先,將輸入的測試樣板作影像前處理,藉以強調原始影像中的特徵部份,其中,考量到測試樣板中的字元可能與參考樣板不同,所以必須對輸入的測試樣板作正規化以及閉運算處理,然後,再利用投影法作影像分割並擷取各字元的特徵量,最後,利用最小平方遞迴演算法作特徵量比對,並輸出比對結果。經過實地驗證發現,本系統對於標準字型或是字型稍有汙損之測試樣板的辨識率可達99%以上。
The purpose of this thesis is to develop an optical character recognition system according to the theory of image processing for recognizing the English character in a document. For a start, we perform the operation of image preprocessing, so as to emphasize the key feature of an original image, in which due to the shape of a test pattern may differ from the same of a sample pattern, thus normalization and closing are both essential operations in said image preprocessing stage. In the second stage, we divide the image into a number of regions using projection approach, wherein each said region is thought of as a character. Next, to extract the feature from each character and then to employ recursive least square algorithm to perform feature matching and output the result thereafter. As for the accuracy of said recognition system, that is 99% for standard character as well as for defected character.
Appears in Collections:[Department of Electrical Engineering] Dissertations and Theses

Files in This Item:

File Description SizeFormat

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