{"title":"Car number plate recognition for smart building management","authors":"A. Visvanathan, T. Chattopadhyay","doi":"10.1109/ICDSP.2014.6900802","DOIUrl":null,"url":null,"abstract":"The traditional OCR based approach for number plate recognition does not work for the variations in painting style of the number plates. In this paper authors have presented an image retrieval based method to recognize the car number plate captured using a smart phone to facilitate the Car management system of a Smart office premise. In the proposed method a smart phone is used to capture the images and extract features of the car number plate. These features are matched against predefined set of same car number plate images in the database. The character images are matched in an efficient manner to make it a real time solution. The proposed method recognizes the car with almost 93.75% accuracy and is already deployed in our office premise.","PeriodicalId":301856,"journal":{"name":"2014 19th International Conference on Digital Signal Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 19th International Conference on Digital Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDSP.2014.6900802","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
The traditional OCR based approach for number plate recognition does not work for the variations in painting style of the number plates. In this paper authors have presented an image retrieval based method to recognize the car number plate captured using a smart phone to facilitate the Car management system of a Smart office premise. In the proposed method a smart phone is used to capture the images and extract features of the car number plate. These features are matched against predefined set of same car number plate images in the database. The character images are matched in an efficient manner to make it a real time solution. The proposed method recognizes the car with almost 93.75% accuracy and is already deployed in our office premise.