The early Japanese books reorganization by combining image processing and deep learning

作     者：Bing Lyu Hengyi Li Ami Tanaka Lin Meng 

作者机构：Graduate School of Science and EngineeringRitsumeikan UniversityKusatsuShigaJapan College of Science and EngineeringRitsumeikan UniversityKusatsuShigaJapan 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2022年第7卷第4期

页      面：627-643页

核心收录：

学科分类：0710[理学-生物学] 0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Art Research Center of Ritsumeikan University 

主　　题：character recognition deep learning image processing Japanese books reorganization Kuzushiji 

摘      要：Many early Japanese books record a large amount of information,including historical politics,economics,culture,and so on,which are all valuable *** books are waiting to be reorganized at the ***,a large amount of the books are described by Kuzushiji,a type of handwriting cursive script that is no longer in use today and only readable by a few ***,researchers are trying to detect and recognise the characters from these books through modern ***,the characteristics of the Kuzushiji,such as Connect-Separate-characters and Manyvariation,hinder the modern technique assisted ***-Separatecharacters refer to the case of some characters connecting each other or one character being separated into unconnected parts,which makes character detection *** is one of the typical characteristics of Kuzushiji,defined as the case that the same character has several variations even if they are written by the same person in the same book at the same time,which increases the difficulty of character *** this sense,this paper aims to construct an early Japanese book reorganisation system by combining image processing and deep learning *** experimentation has been done by testing two early Japanese *** terms of character detection,the final Recall,Precision and F-value reaches 79.8%,80.3%,and 80.0%,*** deep learning based character recognition accuracy of Top3 reaches 69.52%,and the highest recognition rate reaches 82.57%,which verifies the effectiveness of our proposal.