{"title":"Recognizing the Digital Code of Scanned Express Form Images through Template Matching","authors":"Yunjian Li, Guangzhu Xu, Jing Jing, Hongyang Li","doi":"10.1109/ICCECT.2012.231","DOIUrl":null,"url":null,"abstract":"With the rapid development of material flow industry and the prevalence of network shopping, customers are demanding to know their package delivery information urgently, and hoping they can track them quickly. Automatic and fast express number recognition technology can solve the problem. The article proposed an algorithm based on template matching to extract and recognize the express number of a non-ideal scanned express form. First, we used the method which called Hough transform to estimate the rotation angle of a raw image, and then the raw image can be corrected with a contrary angle. Second, we use the method of the edge features to position the barcode. Third, express number region can be found by positioning the barcode area. Finally, each digit in the express number area was segmented out and recognized by being compared with the templates stored in a database. The whole algorithm was evaluated throughly with real life express images. The results showed that the proposed method is fast, accurate and robust. This algorithm has potential application value.","PeriodicalId":153613,"journal":{"name":"2012 International Conference on Control Engineering and Communication Technology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Control Engineering and Communication Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCECT.2012.231","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
With the rapid development of material flow industry and the prevalence of network shopping, customers are demanding to know their package delivery information urgently, and hoping they can track them quickly. Automatic and fast express number recognition technology can solve the problem. The article proposed an algorithm based on template matching to extract and recognize the express number of a non-ideal scanned express form. First, we used the method which called Hough transform to estimate the rotation angle of a raw image, and then the raw image can be corrected with a contrary angle. Second, we use the method of the edge features to position the barcode. Third, express number region can be found by positioning the barcode area. Finally, each digit in the express number area was segmented out and recognized by being compared with the templates stored in a database. The whole algorithm was evaluated throughly with real life express images. The results showed that the proposed method is fast, accurate and robust. This algorithm has potential application value.