渣土车车牌字符智能识别研究
|
摘要
考虑渣土车车牌的统一黄底且易生锈或遭受沙泥污染等因素,着重研究车牌字符识别中的关键技术问题。首先针对车牌为黄底黑字特点,基于图像颜色信息实现车牌快速粗定位;然后创新性的运用双线性拟合与错切变换相结合的方法,实现基于彩色车牌图像的倾斜校正;接着,采用改进的统计分析方法有效的消除了间隔符、多垂直边框的影响以及"川"字符难以分割的问题,进一步采用模板匹配法实现字符智能识别。最后,实验测试验证了所提方法的有效性。
Considering the factors such as yellow bottom positive figure,easy pollution,etc. of the muck car license plate,the intelligent recognition system of the license plate character is analyzed and investigated. Firstly,the quick approximate license plate localization is implemented based on the character of image color information,and the innovation using bilinear fit function and shear transformation to adjust the skewed license plate is presented. Then,the improved statistical analysis steps are used to efficiently eliminate the effects of space mark and boundaries and the segmentation difficult of character "chuan". Furthermore,the simple template matching method is used to realize the intelligent character recognition. Finally,the results of testing experiments confirm the effectiveness of the proposed method.
Considering the factors such as yellow bottom positive figure,easy pollution,etc. of the muck car license plate,the intelligent recognition system of the license plate character is analyzed and investigated. Firstly,the quick approximate license plate localization is implemented based on the character of image color information,and the innovation using bilinear fit function and shear transformation to adjust the skewed license plate is presented. Then,the improved statistical analysis steps are used to efficiently eliminate the effects of space mark and boundaries and the segmentation difficult of character "chuan". Furthermore,the simple template matching method is used to realize the intelligent character recognition. Finally,the results of testing experiments confirm the effectiveness of the proposed method.
引文
[1]李悦,刘晨.基于历史车牌识别数据的套牌车并行检测方法[J].计算机应用,2016,36(3):864-870.LI Y,LIU CH.Parallel discovery of fake plates based on historical automatic number plate recognition data[J].Journal of Computer Applications,2016,36(3):864-870.
[2]RAJPUT H,SOM T,KAR S.An automated vehicle license plate recognition system[J].Computer,2015,48(8):56-61.
[3]ZHAO J L,MIN H G,LI X C,et al.A license plate recognition algorithm under low illumination environment[C].1st International Smart Cities Conference(ISC2),IEEE,2015:1-6.
[4]WANG Y,BAN X,CHEN J,et al.License plate recognition based on SIFT feature[J].OptikInternational Journal for Light and Electron Optics,2015,126(21):2895-2901.
[5]FU R.The research and design of vehicle license plate recognition system in traffic management system[J].International Journal of Signal Processing,Image Processing and Pattern Recognition,2016,9(3):445-456.
[6]曹岩.基于形态学梯度重建的车牌定位方法[J].计算机工程与科学,2015,37(7):1372-1380.CAO Y.A novel license plate location method based on morphological gradient reconstruction[J].Computer Engineering&Science,2015,37(7):1372-1380.
[7]费继友,谢金路,李花,等.基于字符特征约束的自适应车牌校正提取[J].仪器仪表学报,2016,37(3):632-639.FEI J Y,XIE J L,LI H,et al.Adaptive license plate correction and extraction based on character feature constraint[J].Chinese Journal of Scientific Instrument,2016,37(3):632-639.
[8]段建民,刘冠宇,郑榜贵.基于视觉及多特征的前方车辆检测算法[J].北京工业大学学报,2015,41(9):1326-1333.DUAN J M,LIU G Y,ZHENG B G.Front vehicle identification algorithm based on visual and multifeature[J].Journal of Beijing University of Technology,2015,41(9):1326-1333.
[9]ZANG D,CHAI Z,Zh ANG J,et al.Vehicle license plate recognition using visual attention model and deep learning[J].Journal of Electronic Imaging,2015,24(3):033001-033001.
[10]胡良梅,杨慧,张旭东,等.融合RGB特征和Depth特征的3D目标识别方法[J].电子测量与仪器学报,2015,29(10):1431-1439.HU L M,YANG H,ZHANG X D,et al.3D object recognition method based on the fusion of RGB and depth feature[J].Journal of Electronic Measurement and Instrumentation,2015,29(10):1431-1439.
[11]吴惟希.一种基于色彩的车牌图像定位算法[J].信息安全研究,2016,2(1):58-65.WU W X.A colors based algorithm for license plate location[J].Journal of Information Security Research.2016,2(1):58-65.
[12]DUN J,ZHANG S,YE X,et al.Chinese license plate localization in multi-lane with complex background based on concomitant colors[J].Intelligent Transportation Systems Magazine,IEEE,2015,7(3):51-61.
[13]赵振兵,徐磊,戚银城,等.基于Hough检测和CV模型的航拍绝缘子自动协同分割方法[J].仪器仪表学报,2016,37(2):395-403.ZHAO ZH B,XU L,QI Y CH,et al.Automatic cosegmentation method for aerial insulator based on Hough detection and C-V model[J].Chinese Journal of Scientific Instrument,2016,37(2):395-403.
[14]NETO E C,GOMES S L,FILHO P P R,et al.Brazilian vehicle identification using a new embedded plate recognition system[J].Measurement,2015,70(6):36-46.
[15]RAJPUT H,SOM T,KAR S.Using radon transform to recognize skewed images of vehicular license plates[J].Computer,2016,49(1):59-65.
[16]PANCHAL T,PATEL H,PANCHAL A.License plate detection using harris corner and character segmentation by integrated approach from an image[C].Proceedings of International Conference on Communication,Computing and Virtualization(ICCCV),2016:419-425.
[17]路敬祎,薛征,邵克勇,等.基于改进的连通域算法与垂直投影相结合的车牌字符分割[J].自动化技术与应用,2015,34(12):93-97.LU J Y,XUE ZH,SHAO K Y.License plate character segmentation based on improved connected component and vertical projection[J].Techniques of Automation and Applications,2015,34(12):93-97.
[18]ABDELLA A A E S.Libyan licenses plate recognition using template matching method[J].Journal of Computer and Communications,2016,4(7):62-71.
[19]胡玉琛,刘一清.基于FPGA的车牌识别系统研究与实现[J].电子测量技术,2015,38(12):54-58.HU Y CH,LIU Y Q.Research and implementation of license plate recognition system based on FPGA[J].Electronic Measurement Technology,2015,38(12):54-58.
[20]李斌,孙显,吴其昌,等.一种基于活动基模型的近岸舰船检测算法[J].国外电子测量技术,2015,34(5):17-21.LI B,SUN X,WU Q CH,et al.Method on inshore ship detection based on active basis model[J].Foreign Electronic Measurement Technology,2015,34(5):17-21.
[21]Ch ENG R,BAI Y,HU H,et al.Radial wavelet neural network with a novel self-creating disk-cell-splitting algorithm for license plate character recognition[J].Entropy,2015,17(6):3857-3876.
[22]林青,周俊鹏,王连明.基于NDRAM算法的联想记忆网络在车牌汉字识别中的应用[J].东北师大学报:自然科学版,2015,47(4):64-68.LIN Q,ZHOU J P,WANG L M.Recognition of license plate Chinese character based on associative memory of the NDRAM algorithm[J].Journal of Northeast Normal University:Natural Science Edition,2015,47(4):64-68.
[23]李大中,赵杰.基于EMD和GA-SVM的超声检测缺陷信号识别[J].中国测试,2016,42(1):102-106.LI D ZH,ZHAO J.Flaw signal identification in ultrasonic testing based on EMD and GA-SVM[J].China Measurement&Test,2016,42(1):102-106.
[2]RAJPUT H,SOM T,KAR S.An automated vehicle license plate recognition system[J].Computer,2015,48(8):56-61.
[3]ZHAO J L,MIN H G,LI X C,et al.A license plate recognition algorithm under low illumination environment[C].1st International Smart Cities Conference(ISC2),IEEE,2015:1-6.
[4]WANG Y,BAN X,CHEN J,et al.License plate recognition based on SIFT feature[J].OptikInternational Journal for Light and Electron Optics,2015,126(21):2895-2901.
[5]FU R.The research and design of vehicle license plate recognition system in traffic management system[J].International Journal of Signal Processing,Image Processing and Pattern Recognition,2016,9(3):445-456.
[6]曹岩.基于形态学梯度重建的车牌定位方法[J].计算机工程与科学,2015,37(7):1372-1380.CAO Y.A novel license plate location method based on morphological gradient reconstruction[J].Computer Engineering&Science,2015,37(7):1372-1380.
[7]费继友,谢金路,李花,等.基于字符特征约束的自适应车牌校正提取[J].仪器仪表学报,2016,37(3):632-639.FEI J Y,XIE J L,LI H,et al.Adaptive license plate correction and extraction based on character feature constraint[J].Chinese Journal of Scientific Instrument,2016,37(3):632-639.
[8]段建民,刘冠宇,郑榜贵.基于视觉及多特征的前方车辆检测算法[J].北京工业大学学报,2015,41(9):1326-1333.DUAN J M,LIU G Y,ZHENG B G.Front vehicle identification algorithm based on visual and multifeature[J].Journal of Beijing University of Technology,2015,41(9):1326-1333.
[9]ZANG D,CHAI Z,Zh ANG J,et al.Vehicle license plate recognition using visual attention model and deep learning[J].Journal of Electronic Imaging,2015,24(3):033001-033001.
[10]胡良梅,杨慧,张旭东,等.融合RGB特征和Depth特征的3D目标识别方法[J].电子测量与仪器学报,2015,29(10):1431-1439.HU L M,YANG H,ZHANG X D,et al.3D object recognition method based on the fusion of RGB and depth feature[J].Journal of Electronic Measurement and Instrumentation,2015,29(10):1431-1439.
[11]吴惟希.一种基于色彩的车牌图像定位算法[J].信息安全研究,2016,2(1):58-65.WU W X.A colors based algorithm for license plate location[J].Journal of Information Security Research.2016,2(1):58-65.
[12]DUN J,ZHANG S,YE X,et al.Chinese license plate localization in multi-lane with complex background based on concomitant colors[J].Intelligent Transportation Systems Magazine,IEEE,2015,7(3):51-61.
[13]赵振兵,徐磊,戚银城,等.基于Hough检测和CV模型的航拍绝缘子自动协同分割方法[J].仪器仪表学报,2016,37(2):395-403.ZHAO ZH B,XU L,QI Y CH,et al.Automatic cosegmentation method for aerial insulator based on Hough detection and C-V model[J].Chinese Journal of Scientific Instrument,2016,37(2):395-403.
[14]NETO E C,GOMES S L,FILHO P P R,et al.Brazilian vehicle identification using a new embedded plate recognition system[J].Measurement,2015,70(6):36-46.
[15]RAJPUT H,SOM T,KAR S.Using radon transform to recognize skewed images of vehicular license plates[J].Computer,2016,49(1):59-65.
[16]PANCHAL T,PATEL H,PANCHAL A.License plate detection using harris corner and character segmentation by integrated approach from an image[C].Proceedings of International Conference on Communication,Computing and Virtualization(ICCCV),2016:419-425.
[17]路敬祎,薛征,邵克勇,等.基于改进的连通域算法与垂直投影相结合的车牌字符分割[J].自动化技术与应用,2015,34(12):93-97.LU J Y,XUE ZH,SHAO K Y.License plate character segmentation based on improved connected component and vertical projection[J].Techniques of Automation and Applications,2015,34(12):93-97.
[18]ABDELLA A A E S.Libyan licenses plate recognition using template matching method[J].Journal of Computer and Communications,2016,4(7):62-71.
[19]胡玉琛,刘一清.基于FPGA的车牌识别系统研究与实现[J].电子测量技术,2015,38(12):54-58.HU Y CH,LIU Y Q.Research and implementation of license plate recognition system based on FPGA[J].Electronic Measurement Technology,2015,38(12):54-58.
[20]李斌,孙显,吴其昌,等.一种基于活动基模型的近岸舰船检测算法[J].国外电子测量技术,2015,34(5):17-21.LI B,SUN X,WU Q CH,et al.Method on inshore ship detection based on active basis model[J].Foreign Electronic Measurement Technology,2015,34(5):17-21.
[21]Ch ENG R,BAI Y,HU H,et al.Radial wavelet neural network with a novel self-creating disk-cell-splitting algorithm for license plate character recognition[J].Entropy,2015,17(6):3857-3876.
[22]林青,周俊鹏,王连明.基于NDRAM算法的联想记忆网络在车牌汉字识别中的应用[J].东北师大学报:自然科学版,2015,47(4):64-68.LIN Q,ZHOU J P,WANG L M.Recognition of license plate Chinese character based on associative memory of the NDRAM algorithm[J].Journal of Northeast Normal University:Natural Science Edition,2015,47(4):64-68.
[23]李大中,赵杰.基于EMD和GA-SVM的超声检测缺陷信号识别[J].中国测试,2016,42(1):102-106.LI D ZH,ZHAO J.Flaw signal identification in ultrasonic testing based on EMD and GA-SVM[J].China Measurement&Test,2016,42(1):102-106.