Ke-Yong Shao, Yang Gao, Na Wang, Hongyan Zhang, Fei Li, Wen-Cheng Li
{"title":"Paper money number recognition based on intersection change","authors":"Ke-Yong Shao, Yang Gao, Na Wang, Hongyan Zhang, Fei Li, Wen-Cheng Li","doi":"10.1109/IWACI.2010.5585167","DOIUrl":null,"url":null,"abstract":"In reality, the paper money number recognition is significant, which can effectively prevent the illegal trade of paper money. First, this paper makes pretreatment to the paper money, and then for the rapidity and accuracy requirements, a new identification method is presented which based on intersection change and the distance difference between the two points of the character on the special location. By the intersection changes between character and horizontal line judge whether there arc. On the special line of intersection change, calculate the distance difference between two points from left to right, comparing with the setting threshold, to determine open arc or closed arc. Finally, some character could be distinguished by the opening direction of the open arc. In this method, the location of difference value is confirmed through the programming which adapts various circumstances, so the adaptability is very high. And as classification features is less, then computing is low. Therefore, this identification system owns the quick and accurate feature, and the accuracy reaches to 97.5%.","PeriodicalId":189187,"journal":{"name":"Third International Workshop on Advanced Computational Intelligence","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Third International Workshop on Advanced Computational Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWACI.2010.5585167","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
In reality, the paper money number recognition is significant, which can effectively prevent the illegal trade of paper money. First, this paper makes pretreatment to the paper money, and then for the rapidity and accuracy requirements, a new identification method is presented which based on intersection change and the distance difference between the two points of the character on the special location. By the intersection changes between character and horizontal line judge whether there arc. On the special line of intersection change, calculate the distance difference between two points from left to right, comparing with the setting threshold, to determine open arc or closed arc. Finally, some character could be distinguished by the opening direction of the open arc. In this method, the location of difference value is confirmed through the programming which adapts various circumstances, so the adaptability is very high. And as classification features is less, then computing is low. Therefore, this identification system owns the quick and accurate feature, and the accuracy reaches to 97.5%.