Full metadata record
DC FieldValueLanguage
dc.contributor.author陳志明en_US
dc.contributor.authorChen Jyh Mingen_US
dc.contributor.author傅先生en_US
dc.contributor.authorMr. Fuen_US
dc.date.accessioned2014-12-12T02:13:19Z-
dc.date.available2014-12-12T02:13:19Z-
dc.date.issued1994en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#NT830392032en_US
dc.identifier.urihttp://hdl.handle.net/11536/58953-
dc.description.abstract本論文的目的是應用類神經網路於手寫中文相似字之辨識。相似字辨識一 直是文字辨識的核心問題,其困難的原因是由於相似字之間字形與字形相 同的部份很多,而且手寫字的變異度較大,以致難以正確分類。本研究利 用類神經網路來建構相似字分類器,以完成相似字的辨識。本相似字分類 器包括三個主要的部份,分別是(1)相似字集之建立,(2)特徵擷取, (3)以模組化類神經網路完成辨識。根據所提方法實驗之結果,藉由此相 似字分類器的加入,系統的整體正確率由 86.01% 提昇至 90.12% ,而在 駁回率為 6.7%時,其辨識率可達 94.11%。本論文所能辨識的字為教育部 所選定的 5401 個常用字,並以工研院電通所研發之手寫中文字資料庫為 訓練及測試樣本進行實驗,因此所建立之系統具有廣泛性及一般性。 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%.zh_TW
dc.language.isozh_TWen_US
dc.subject類神經網路;手寫中文相似字;模組化類神經網路zh_TW
dc.subjectNeural network;Similar handwritten Chinese character;Modular neural networken_US
dc.title類神經網路辨識手寫中文相似字之研究zh_TW
dc.titleRecognition of similar handwritten Chinese characters by artificial neural networksen_US
dc.typeThesisen_US
dc.contributor.department資訊科學與工程研究所zh_TW
Appears in Collections:Thesis