D. Menotti, G. Chiachia, A. Falcão, Vantuil J. Oliveira Neto
{"title":"Vehicle License Plate Recognition With Random Convolutional Networks","authors":"D. Menotti, G. Chiachia, A. Falcão, Vantuil J. Oliveira Neto","doi":"10.1109/SIBGRAPI.2014.52","DOIUrl":null,"url":null,"abstract":"Despite decades of research on automatic license plate recognition (ALPR), optical character recognition (OCR) still leaves room for improvement in this context, given that a single OCR miss is enough to miss the entire plate. We propose an OCR approach based on convolutional neural networks (CNNs) for feature extraction. The architecture of our CNN is chosen from thousands of random possibilities and its filter weights are set at random and normalized to zero mean and unit norm. By training linear support vector machines (SVMs) on the resulting CNN features, we can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve. The results are obtained in a dataset that has 182 samples per digit and 28 per letter, and suggest the use of random CNNs as a promising alternative approach to ALPR systems.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"31","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIBGRAPI.2014.52","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 31
Abstract
Despite decades of research on automatic license plate recognition (ALPR), optical character recognition (OCR) still leaves room for improvement in this context, given that a single OCR miss is enough to miss the entire plate. We propose an OCR approach based on convolutional neural networks (CNNs) for feature extraction. The architecture of our CNN is chosen from thousands of random possibilities and its filter weights are set at random and normalized to zero mean and unit norm. By training linear support vector machines (SVMs) on the resulting CNN features, we can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve. The results are obtained in a dataset that has 182 samples per digit and 28 per letter, and suggest the use of random CNNs as a promising alternative approach to ALPR systems.