Font Size: a A A

Research On The Construction Of Corpus And The Identification Of Some Chinese Characters In The Collection Of Qin Bamboo Slips Collected By Yuelu Academy

Posted on:2020-11-20Degree:MasterType:Thesis
Country:ChinaCandidate:Z WuFull Text:PDF
GTID:2415330620951525Subject:Chinese Language and Literature
Abstract/Summary:PDF Full Text Request
Qin Bamboo Slips Collected by Yuelu Academy,which was buried for more than t wo thousands years from Qin dynasty,was purchased and collected by Yuelu Academ y of Hunan University.From 2010 to 2018,there were five volumes of Qin Bamboo Slips Collected by Yuelu Academy published.The character collection of the first thre e volumes were used as main image materials with Vol.4.The first three volumes are the main language materials.The electronic corpus software that can be used offline in the Windows operating system is constructed,and the related high-frequency Chines e character intelligent recognition research is carried out.Compared with traditional manual research methods,combined with computer resear ch can greatly improve the efficiency of researchers.The electronic corpus constructed in this paper retains valuable pre-Qin electronic corpus for Chinese studies.The identi fication and intelligent processing of the Qin Bamboo Slips image explored in this pa per has practical meaning and value for the literature collation,character collection an d so forth.There are four chapters in this article.The first chapter is the introduction,which i ntroduces the background,significance and overall research summary.The second chap ter starts from the general construction process of the corpus,introduces the overall o verview structure of the corpus,the simple implementation process and several main f unctions.The third chapter introduces the Qin Bamboo Slips image processing method and the character image intelligent recognition algorithm.The image processing include s the text image processing and single character image processing.The character imag e recognition algorithm uses the KNN algorithm.The fourth chapter is based on the ex ploration of the content described in Chapters 2 and 3,based on the tools and algorit hms,and selects some examples from the Vol.4.The conclusion after the text summari zes the contents of this study and its shortcomings,and proposes the direction of futu re research improvement.
Keywords/Search Tags:Yuelu Jian, Qin Jian, corpus, text recognition, image processing
PDF Full Text Request
Related items