An Application of Character Components Segmentation on Printed Chinese Character Recognition System
碩士 === 淡江大學 === 資訊管理學系碩士班 === 96 === In this paper, we purpose to construct a printed Chinese OCR system by segmenting an optical character, which included character segmentation kernel and character recognition kernel. Character segmentation kernel segments Chinese character into two parts by the d...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/35052909540642918306 |
id |
ndltd-TW-096TKU05396003 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-096TKU053960032016-05-18T04:13:37Z http://ndltd.ncl.edu.tw/handle/35052909540642918306 An Application of Character Components Segmentation on Printed Chinese Character Recognition System 應用字元切割方法於印刷體中文字辨識系統 Shiang-Lu Lin 林向如 碩士 淡江大學 資訊管理學系碩士班 96 In this paper, we purpose to construct a printed Chinese OCR system by segmenting an optical character, which included character segmentation kernel and character recognition kernel. Character segmentation kernel segments Chinese character into two parts by the distinctions of Chinese. Character recognition kernel achieves 6-layers feature filters by three character features, which are total pixel count feature, crossing count feature and peripheral background area feature. After these feature filters processed, the system will evaluate the remaining candidate characters by template matching. Our experiment shows that the OCR with segmentation method has better performance on the template-matching stage. Ming-Yu Yang 楊明玉 2008 學位論文 ; thesis 54 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 淡江大學 === 資訊管理學系碩士班 === 96 === In this paper, we purpose to construct a printed Chinese OCR system by segmenting an optical character, which included character segmentation kernel and character recognition kernel. Character segmentation kernel segments Chinese character into two parts by the distinctions of Chinese. Character recognition kernel achieves 6-layers feature filters by three character features, which are total pixel count feature, crossing count feature and peripheral background area feature. After these feature filters processed, the system will evaluate the remaining candidate characters by template matching. Our experiment shows that the OCR with segmentation method has better performance on the template-matching stage.
|
author2 |
Ming-Yu Yang |
author_facet |
Ming-Yu Yang Shiang-Lu Lin 林向如 |
author |
Shiang-Lu Lin 林向如 |
spellingShingle |
Shiang-Lu Lin 林向如 An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
author_sort |
Shiang-Lu Lin |
title |
An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
title_short |
An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
title_full |
An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
title_fullStr |
An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
title_full_unstemmed |
An Application of Character Components Segmentation on Printed Chinese Character Recognition System |
title_sort |
application of character components segmentation on printed chinese character recognition system |
publishDate |
2008 |
url |
http://ndltd.ncl.edu.tw/handle/35052909540642918306 |
work_keys_str_mv |
AT shianglulin anapplicationofcharactercomponentssegmentationonprintedchinesecharacterrecognitionsystem AT línxiàngrú anapplicationofcharactercomponentssegmentationonprintedchinesecharacterrecognitionsystem AT shianglulin yīngyòngzìyuánqiègēfāngfǎyúyìnshuātǐzhōngwénzìbiànshíxìtǒng AT línxiàngrú yīngyòngzìyuánqiègēfāngfǎyúyìnshuātǐzhōngwénzìbiànshíxìtǒng AT shianglulin applicationofcharactercomponentssegmentationonprintedchinesecharacterrecognitionsystem AT línxiàngrú applicationofcharactercomponentssegmentationonprintedchinesecharacterrecognitionsystem |
_version_ |
1718271558816890880 |