{"title":"Notice of RetractionA scheme of improved training in license plate character recognition","authors":"Tianding Chen","doi":"10.1109/ICCT.2008.4716210","DOIUrl":null,"url":null,"abstract":"It utilizes back-propagation neural network (BPNN) as the recognition system tool. The identification is done by the back propagation neural network (BPNN). Moreover, we improve BPNN some limitation, such as slow learning speed in the training process, leading to partial minimum values that are difficult to converge, and the need to retrain an enormous volume of data whenever new training samples are added or deleted. The technologies and related models used for recognizing the license plates are clearly described and given to demonstrate the effectiveness of the proposed model. Experimental results show that our system can effectively recognize most license plates character, including 10 numbers and 26 alphabet characters. The recognition rate is 90%.","PeriodicalId":259577,"journal":{"name":"2008 11th IEEE International Conference on Communication Technology","volume":"49 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 11th IEEE International Conference on Communication Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCT.2008.4716210","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
It utilizes back-propagation neural network (BPNN) as the recognition system tool. The identification is done by the back propagation neural network (BPNN). Moreover, we improve BPNN some limitation, such as slow learning speed in the training process, leading to partial minimum values that are difficult to converge, and the need to retrain an enormous volume of data whenever new training samples are added or deleted. The technologies and related models used for recognizing the license plates are clearly described and given to demonstrate the effectiveness of the proposed model. Experimental results show that our system can effectively recognize most license plates character, including 10 numbers and 26 alphabet characters. The recognition rate is 90%.