W. Jia, Huaifeng Zhang, Xiangjian He, Massimo Piccardi
{"title":"Mean shift for accurate license plate localization","authors":"W. Jia, Huaifeng Zhang, Xiangjian He, Massimo Piccardi","doi":"10.1109/ITSC.2005.1520110","DOIUrl":null,"url":null,"abstract":"This paper presents a region-based algorithm for accurate license plate localization, where mean shift is utilized to filter and segment color vehicle images into candidate regions. Three features are extracted in order to decide whether a candidate region represents a real license plate, namely, rectangularity, aspect ratio, and edge density. Then, the Mahalanobis classifier is used with respect to above three features to classify license plate regions and non-license plate regions. Experimental results show that the proposed algorithm produces high robustness and accuracy.","PeriodicalId":153203,"journal":{"name":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"96","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITSC.2005.1520110","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 96
Abstract
This paper presents a region-based algorithm for accurate license plate localization, where mean shift is utilized to filter and segment color vehicle images into candidate regions. Three features are extracted in order to decide whether a candidate region represents a real license plate, namely, rectangularity, aspect ratio, and edge density. Then, the Mahalanobis classifier is used with respect to above three features to classify license plate regions and non-license plate regions. Experimental results show that the proposed algorithm produces high robustness and accuracy.