图像超分辨率在模糊车牌识别系统中的应用
|
摘要
车牌识别技术种类繁多,理想情况下识别率已达到99%,而对于远距离模糊不清的抓拍图片,识别效果还不够,为此提出一种利用图像超分辨率重建技术提高模糊车牌识别率的方法。首先利用图像处理方法对图片进行分割;其次利用支持向量机(SVM)对分割得到的图块进行分类,筛选出车牌图块;再利用多帧低分辨率车牌图块进行最大后验估计(MAP)超分辨率重建,得到比较清晰、便于识别的车牌;最后利用人工神经网络(ANN)方法进行光学字符识别(OCR),最终得到识别结果。实验表明,与传统车牌识别技术相比,该方法具有更强的鲁棒性,且在模糊车牌识别中正确率明显提高。
Nowadays plate recognition technology is blooming everywhere. Some people even claim that their recognition rate has reached 99%. However,those are some of the ideal cases of recognition rate,for those long-distance blurred snapped pictures,their methods will seem powerless. In this paper,a method of using image super-resolution reconstruction technology to improve the recognition rate of fuzzy license plates is proposed. This method first uses image processing to segment the image,and then uses support vector machine(SVM)to classify and screen out the license plate tiles,and then uses the multi-frame low-resolution plate tiles to perform maximum a posteriori(MAP)estimation super-resolution reconstruction and obtain a relatively clear and easy recognition of the plate,and finally use the artificial neural network(ANN)method for optical character recognition(OCR)to get the plate recognition results.Experiments show that this method is more robust than the traditional license plate recognition technology,and the correct rate is significantly improved.
Nowadays plate recognition technology is blooming everywhere. Some people even claim that their recognition rate has reached 99%. However,those are some of the ideal cases of recognition rate,for those long-distance blurred snapped pictures,their methods will seem powerless. In this paper,a method of using image super-resolution reconstruction technology to improve the recognition rate of fuzzy license plates is proposed. This method first uses image processing to segment the image,and then uses support vector machine(SVM)to classify and screen out the license plate tiles,and then uses the multi-frame low-resolution plate tiles to perform maximum a posteriori(MAP)estimation super-resolution reconstruction and obtain a relatively clear and easy recognition of the plate,and finally use the artificial neural network(ANN)method for optical character recognition(OCR)to get the plate recognition results.Experiments show that this method is more robust than the traditional license plate recognition technology,and the correct rate is significantly improved.
引文
[1]李晶晶.基于实时视频的车牌识别系统[D].成都:电子科技大学,2010.
[2] DANIEL L B,SHERVIN E,DAVID M E,et al.深入理解OpenCV:实用计算机视觉项目解析[M].刘波,译.北京:机械工业出版社,2014.
[3] SHI X,ZHAO W,SHEN Y. Automatic license plate recognition system based on color image processing[C]. International Conference on Computational Science and ITS Applications,2005:1159-1168.
[4] XU H K,YU F H,JIAO J H,et al. A new approach of the vehicle license plate location[C]. International Conference on Parallel and Distributed Computing,Applications and Technologies,2005:1055-1057.
[5] MATAS J,ZIMMERMANN K. Unconstrained licence plate and text localization and recognition[C]. Intelligent Transportation System,2005:225-230.
[6] HONGLIANG B,CHANGPING L. A hybrid license plate extraction method based on edge statistics and morphology[C]. International Conference on Pattern Recognition,2004:831-834.
[7] WANG S Z,LEE H J. Detection and recognition of license plate characters with different appearances[C]. Intelligent Transportation Systems,2003:979-984.
[8]付炜,赵正则,王大江.基于水平灰度跳边和垂直投影的车牌定位方法[J].电子测量技术,2008,31(3):61-65.
[9] COMELLI P,FERRAGINA P,GRANIERI M N,et al. Optical recognition of motor vehicle license plates[J]. Transactions on Vehicular Technology,2002,44(4):790-799.
[10] LU X,LING X,HUANG W. Vehicle license plate character recognition[C]. International Conference on Neural Networks and Signal Processing,2003:1066-1069.
[11]陈玮,曹志广,李剑平.改进的模板匹配方法在车牌识别中的应用[J].计算机工程与设计,2013,34(5):1808-1811.
[12]邹星.一种基于模板库的车牌字符识别算法[J].计算机技术与发展,2010,20(4):128-131.
[13]张燕,任安虎.多特征与BP神经网络车牌识别系统研究[J].科学技术与工程,2012,12(22):5645-5648.
[14] CHEN N,XING L. Research of license plate recognition based on improved BP neural network[C]. International Conference on Computer Application and System Modeling,2010:482-485.
[15] KO M A,KIM Y M. A simple OCR method from strong perspective view[C]. Applied Imagery Pattern Recognition Workshop,2004:235-240.
[16]罗辉武,唐远炎,王翊,等.基于结构特征和灰度特征的车牌字符识别方法[J].计算机科学,2011,38(11):267-270.
[17]姜少波,甘彤,马彪彪.图像处理技术在模糊车牌清晰化中的应用[J].电子技术与软件工程,2018(7):84-85.
[18] CAPEL,PETER D. Super-resolution and image mosaicing[D]. Oxford:University of Oxford,2001.
[19] FARSIU S,MILANFAR P,ELAD M. A practical approach to superresolution[J]. Proceedings of SPIE-The International Society for Optical Engineering,2006,6077:24-38.
[2] DANIEL L B,SHERVIN E,DAVID M E,et al.深入理解OpenCV:实用计算机视觉项目解析[M].刘波,译.北京:机械工业出版社,2014.
[3] SHI X,ZHAO W,SHEN Y. Automatic license plate recognition system based on color image processing[C]. International Conference on Computational Science and ITS Applications,2005:1159-1168.
[4] XU H K,YU F H,JIAO J H,et al. A new approach of the vehicle license plate location[C]. International Conference on Parallel and Distributed Computing,Applications and Technologies,2005:1055-1057.
[5] MATAS J,ZIMMERMANN K. Unconstrained licence plate and text localization and recognition[C]. Intelligent Transportation System,2005:225-230.
[6] HONGLIANG B,CHANGPING L. A hybrid license plate extraction method based on edge statistics and morphology[C]. International Conference on Pattern Recognition,2004:831-834.
[7] WANG S Z,LEE H J. Detection and recognition of license plate characters with different appearances[C]. Intelligent Transportation Systems,2003:979-984.
[8]付炜,赵正则,王大江.基于水平灰度跳边和垂直投影的车牌定位方法[J].电子测量技术,2008,31(3):61-65.
[9] COMELLI P,FERRAGINA P,GRANIERI M N,et al. Optical recognition of motor vehicle license plates[J]. Transactions on Vehicular Technology,2002,44(4):790-799.
[10] LU X,LING X,HUANG W. Vehicle license plate character recognition[C]. International Conference on Neural Networks and Signal Processing,2003:1066-1069.
[11]陈玮,曹志广,李剑平.改进的模板匹配方法在车牌识别中的应用[J].计算机工程与设计,2013,34(5):1808-1811.
[12]邹星.一种基于模板库的车牌字符识别算法[J].计算机技术与发展,2010,20(4):128-131.
[13]张燕,任安虎.多特征与BP神经网络车牌识别系统研究[J].科学技术与工程,2012,12(22):5645-5648.
[14] CHEN N,XING L. Research of license plate recognition based on improved BP neural network[C]. International Conference on Computer Application and System Modeling,2010:482-485.
[15] KO M A,KIM Y M. A simple OCR method from strong perspective view[C]. Applied Imagery Pattern Recognition Workshop,2004:235-240.
[16]罗辉武,唐远炎,王翊,等.基于结构特征和灰度特征的车牌字符识别方法[J].计算机科学,2011,38(11):267-270.
[17]姜少波,甘彤,马彪彪.图像处理技术在模糊车牌清晰化中的应用[J].电子技术与软件工程,2018(7):84-85.
[18] CAPEL,PETER D. Super-resolution and image mosaicing[D]. Oxford:University of Oxford,2001.
[19] FARSIU S,MILANFAR P,ELAD M. A practical approach to superresolution[J]. Proceedings of SPIE-The International Society for Optical Engineering,2006,6077:24-38.