銀行支票中非金額打印體漢字串識(shí)別.pdf

1、聲明本學(xué)位論文是我在導(dǎo)師的指導(dǎo)下取得的研究成果，盡我所知，在本學(xué)位論文中，除了加以標(biāo)注和致謝的部分外，不包含其他人已經(jīng)發(fā)表或公布過(guò)的研究成果，也不包含我為獲得任何教育機(jī)構(gòu)的學(xué)位或?qū)W歷而使用過(guò)的材料。與我一同工作的同事對(duì)本學(xué)位論文做出的貢獻(xiàn)均已在論文中作了明確的說(shuō)明。研究生簽名：蔓堡當(dāng)!墊蘭7秒l弓年弓月噦?cè)諏W(xué)位論文使用授權(quán)聲明南京理工大學(xué)有權(quán)保存本學(xué)位論文的電子和紙質(zhì)文檔，可以借閱或上網(wǎng)公布本學(xué)位論文的部分或全部?jī)?nèi)容，可以向有關(guān)部門(mén)或機(jī)

2、構(gòu)送交并授權(quán)其保存、借閱或上網(wǎng)公布本學(xué)位論文的部分或全部?jī)?nèi)容。對(duì)于保密論文，按保密的有關(guān)規(guī)定和程序處理。研究生簽名：玉蘭也沙127年弓月哆日碩士論文AbstractResearchonPrintedChinesecharacterstringrecognitionnotonlyhelpsfurtherimprovetheautomaticprocessiondegreeoffinancialnotesrecognitionsystem，

3、butalsoisconducivetobringPrintedChinesecharacterstringrecognitioninfinancialnotesrecognitiontowardthepracticalBesides，ithasabroadapplicationprospectsSo，itisavaluableresearchtopicInthisdissertation，PrintedChinesecharacter

4、stringwhichisnon—amountincheckimageofCCBisselectedastheresearchobjectSeveralkeytechniqueswhicharepre—processing，segmentationrecognitionandpost—processingarediscussedChangecolorimageintograyimageFortheredsealinsomecheckim

5、age，effective伊ayprocessingstrategyisraisedFirst，judgethecolorofChinesecharacterstringFortheblueandblackChinesecharacterstringimage，analgorithmonthebasisofkeepingtheimageinformationofChinesecharacterstringregionisraisedte

6、movetheeffectoftheredsealFortheredChinesecharacterstringimage，wetrytosolovetheobviousgapsituationbetweenChinesecharacterstringandsealUsingtheweightedaverageaveragemethodtogray，andthenlookforablankareabasedongrayprojectio

7、nofitsbinaryimagetoseparateChinesecharacterstringimageandsealTiltcorrectionofChinesecharacterstringTiltoftenappearswhenChinesecharacterstringisprintedItneedstobecorrectedinordertothesubsequentsegmentationandfeatureextrac

8、tionFirstthemethodofstraightfitisusedtocalculatetheinclinationangleThismethodCansolvemostoftheinclinedsituationFortheremainingsituationwhichChinesecharacterstringisnotthewholeinclined，themethodofsegmentedpolylinefitispro

9、posedandhasachivedverygoodresultsTwoclassifiersisusedtoChinesecharacterrecognitionFirstgradecoarseclssificationiskeytoimproverecognitionspeedAcoarseclssificationschemebasedontheclasscenterandnearestneighbormethodispresen

10、tedinthedissertationAnimprovednearestneighborclssificationisraisedinfmeclassificationExperimentresultsshowthatproposedmethodhasexcellentperformanceonrecognitionspeedandrecognitionrateRecognitionpostprocessingAmethodwhich

11、combinesNgramlanguagemodelbasedonstatistical、ⅣimChinesecharacterrecognitionisdiscussedinthisdissertationFortheparticularityofChinesecharacterstringtoberecognition，apostprocessingmethodbasedonfindingandmatchingChinesechar