Recognition of similar handwritten Chinese characters by artificial neural networks
碩士 === 國立交通大學 === 資訊工程研究所 === 83 === This thesis presents an application of neural networks on off- line similar handwritten Chinese character recognition. The proposed method consists of three components:(1)confusing character sets construction,(2)featur...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
1995
|
Online Access: | http://ndltd.ncl.edu.tw/handle/08846493337872930669 |
id |
ndltd-TW-083NCTU0392032 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-083NCTU03920322015-10-13T12:53:37Z http://ndltd.ncl.edu.tw/handle/08846493337872930669 Recognition of similar handwritten Chinese characters by artificial neural networks 類神經網路辨識手寫中文相似字之研究 Chen Jyh Ming 陳志明 碩士 國立交通大學 資訊工程研究所 83 This thesis presents an application of neural networks on off- line similar handwritten Chinese character recognition. The proposed method consists of three components:(1)confusing character sets construction,(2)feature selection,(3)modular neural network recognition. In order to evaluate the proposed recognition system, we choose 5401 frequently used Chinese characters as our trainning and testing domain. The database of each testing and trainning sample character was created by the Computer and Communication Laboratory of Industrial Technology Research Institute. Because the samples in this database were collected by more than 2600 people, our recognition system could reach a high generality and user-independence. Experimental results show that, the method improves recognition rate from 86.01% to 90.12%. Mr. Fu 傅先生 1995 學位論文 ; thesis 51 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 資訊工程研究所 === 83 === This thesis presents an application of neural networks on off-
line similar handwritten Chinese character recognition. The
proposed method consists of three components:(1)confusing
character sets construction,(2)feature selection,(3)modular
neural network recognition. In order to evaluate the proposed
recognition system, we choose 5401 frequently used Chinese
characters as our trainning and testing domain. The database of
each testing and trainning sample character was created by the
Computer and Communication Laboratory of Industrial Technology
Research Institute. Because the samples in this database were
collected by more than 2600 people, our recognition system
could reach a high generality and user-independence.
Experimental results show that, the method improves recognition
rate from 86.01% to 90.12%.
|
author2 |
Mr. Fu |
author_facet |
Mr. Fu Chen Jyh Ming 陳志明 |
author |
Chen Jyh Ming 陳志明 |
spellingShingle |
Chen Jyh Ming 陳志明 Recognition of similar handwritten Chinese characters by artificial neural networks |
author_sort |
Chen Jyh Ming |
title |
Recognition of similar handwritten Chinese characters by artificial neural networks |
title_short |
Recognition of similar handwritten Chinese characters by artificial neural networks |
title_full |
Recognition of similar handwritten Chinese characters by artificial neural networks |
title_fullStr |
Recognition of similar handwritten Chinese characters by artificial neural networks |
title_full_unstemmed |
Recognition of similar handwritten Chinese characters by artificial neural networks |
title_sort |
recognition of similar handwritten chinese characters by artificial neural networks |
publishDate |
1995 |
url |
http://ndltd.ncl.edu.tw/handle/08846493337872930669 |
work_keys_str_mv |
AT chenjyhming recognitionofsimilarhandwrittenchinesecharactersbyartificialneuralnetworks AT chénzhìmíng recognitionofsimilarhandwrittenchinesecharactersbyartificialneuralnetworks AT chenjyhming lèishénjīngwǎnglùbiànshíshǒuxiězhōngwénxiāngshìzìzhīyánjiū AT chénzhìmíng lèishénjīngwǎnglùbiànshíshǒuxiězhōngwénxiāngshìzìzhīyánjiū |
_version_ |
1716868634142310400 |