手寫體數(shù)字識別系統(tǒng)的設(shè)計與實現(xiàn)手寫體數(shù)字識別系統(tǒng)的設(shè)計與實現(xiàn)中文摘要英文摘要設(shè)計方案系統(tǒng)設(shè)計流程預(yù)處理特征提取BP神經(jīng)網(wǎng)絡(luò)識別系統(tǒng)界面總結(jié)致謝手寫體數(shù)字識別系統(tǒng)的設(shè)計與實現(xiàn)手寫體數(shù)字識別是多年來的研究熱點，也是字符識別中的一個重要問題。手寫體數(shù)字識別在郵政、金融領(lǐng)域應(yīng)用廣泛。當(dāng)涉及到數(shù)字識別時，人們往往要求識別器有很高的識別可靠性，特別是有關(guān)金額的數(shù)字識別時，因此，針對這類問題的處理系統(tǒng)設(shè)計的關(guān)鍵環(huán)節(jié)之一，就是設(shè)計出高可靠性和高識別率的手寫體數(shù)字識別方法。本文在對手寫識別主要方法分析和研究的基礎(chǔ)上，設(shè)計了一個基于BP神經(jīng)網(wǎng)絡(luò)的手寫體數(shù)字識別系統(tǒng)。該系統(tǒng)首先對數(shù)字字符進行灰度化、二值化、細化、分割等預(yù)處理，然后采用逐象素特征提取法的特征提取方法提取字符特征，最后使用訓(xùn)練好的BP神經(jīng)網(wǎng)絡(luò)識別手寫的數(shù)字。實驗表明，本系統(tǒng)對于較規(guī)范的手寫體數(shù)字的識別達到了很好的識別效果。DESIGNOFHANDWRITTENDIGHTRECOGNITIONSYSTEMHandwrittennumeralrecognitionisahotspotofstudyforyears,andisaimportantissueofcharacterrecognition.Handwrittennumeralrecognitionisappliedbroadlyinpostandfinancialenvironment.Whencomedowntonumeralrecognition,theemphasespeoplethinkisitsdependability,especiallyrefertomoney-digitrecognition.Sooneofthekeystepsforthesequestionsisdesigningahigh-dependabilityandhigh-accuracyhandwrittennumeralrecognitionsystem.Basedontheanalysisandresearchofthemethodofhandwrittenrecognition,thedesignofahandwrittennumeralrecognitionsystembasedonBPneuralnetworkisachievedinthispaper.Infirst,itisthepretreatmentofgraying,partition,thinningprogress,cutsapartetc.Thenalgorithmofpixel-by-featureextractionhasbeenadoptedinhandwrittennumeralrecognition.Finally,recognizenumberusingtheBPneuralnetworkwhichwaswelltrained.Experimentshowrecognitionsysteminthi