基于实时视频的车牌识别系统
|
摘要
车牌识别系统的存在是利用目前现有的计算机先进技术来实现对图像的处理,通过识别技术的应用来实现对车辆号牌的自动认读,提高车辆识别的效率,且对交通流没有影响。车牌识别系统在交通管控、交通流量管理、交通事故自动测报等多个方面均发挥了重要作用,被广泛应用于停车场、港口和机场、城市监控系统、公路流量观测站、桥梁和公路收费站、公路流量观测站等认证车牌的实际交通系统中,论文针对目前车牌识别系统存在的主要问题设计实现基于实时视频的车牌识别系统并对相关算法进行优化。
对于定位车牌所存在的区域困难现象,本文通过用车牌的区域定位算法来解决,这个算法是以固定颜色搭配为基础。由于车牌所设定的底色和字符色是由几种确定搭配组成的特性,提取彩色图像,同时以车牌区域的纹理特征进行定位车牌。运用该算法所具有的准确率较高而且所用的时间较短的特点,在复杂或者特殊情况下仍旧能够达到96%的定位率。本文提出一种随机直线检测法来定位车牌的边框,通过这种检测可以解决车牌所具有的倾斜角问题。与采用的Hough算法相比所用的时间较短,工作量也较少。本文在对局部与全局两类阈值法所具有的优劣的基础上,研究得出了图像二值化算法,该算法是局部与全局两类阈值法紧密结合的结果。研究得出的新算法能够对图像的细节进行保留,有效的清除伪影的干扰。图像二值化后车牌上的字符成为单独的字符,通过BP神经网络的识别,字符均识别率95.7%。通过采用以上优化算法,在深入分析车牌识别系统需求基础上设计实现了基于实时视频的车牌识别系统。
Based on computer image processing and recognition technology, vehicle recognition system achieves the automatic recognition of license plate reading, vehicle identification greatly improved work efficiency, without increasing the impact on traffic flow. License Plate Recognition System in traffic control, traffic management, traffic accidents and many other aspects of automatic forecasting have played an important role, is widely used in car parks, ports and airports, urban monitoring systems, road traffic observation stations, bridges and roads closed fee station, highway traffic observation station certification number plate, the actual traffic system, the paper license plate recognition system for the current main problems in the design to achieve real-time video-based license plate recognition system and related algorithms optimized.
For the difficulties of positioning vehicle plate, this dissertation solves the problem by the location algorithm based on a fixed color matching. As the background color and character color of the plate is determined by several characteristics with the composition of extracted color image. Then, the plate’s region is located by the texture of vehicle plate. This algorithm has a higher accuracy and shorter periods of time, it can still reach 96% of the targeted rate by the characteristics of the complex or exceptional circumstances. This dissertation presents a stochastic line detection method to locate the license plate of the border, and the algorithm can resolve the tilt angle of the license plate. In comparison with Hough method, this algorithm has less calculation and takes shorter periods of time. In this dissertation after analyzing the advantages and disadvantages of global and local algorithms, a new algorithm is put forward which is derived from the combination of them. The new algorithm can keep the details of the image, and effectively remove artifacts possess interference. After image binarization, the characters on the plate split into separate characters, and the characters are recognized by BP neural network, average rate of recognition is 95.7%. By using the above optimization algorithm, a real-time video-based vehicle plate recognition system is achieved in-depth analysis of demand on the vehicle plate recognition system.
对于定位车牌所存在的区域困难现象,本文通过用车牌的区域定位算法来解决,这个算法是以固定颜色搭配为基础。由于车牌所设定的底色和字符色是由几种确定搭配组成的特性,提取彩色图像,同时以车牌区域的纹理特征进行定位车牌。运用该算法所具有的准确率较高而且所用的时间较短的特点,在复杂或者特殊情况下仍旧能够达到96%的定位率。本文提出一种随机直线检测法来定位车牌的边框,通过这种检测可以解决车牌所具有的倾斜角问题。与采用的Hough算法相比所用的时间较短,工作量也较少。本文在对局部与全局两类阈值法所具有的优劣的基础上,研究得出了图像二值化算法,该算法是局部与全局两类阈值法紧密结合的结果。研究得出的新算法能够对图像的细节进行保留,有效的清除伪影的干扰。图像二值化后车牌上的字符成为单独的字符,通过BP神经网络的识别,字符均识别率95.7%。通过采用以上优化算法,在深入分析车牌识别系统需求基础上设计实现了基于实时视频的车牌识别系统。
Based on computer image processing and recognition technology, vehicle recognition system achieves the automatic recognition of license plate reading, vehicle identification greatly improved work efficiency, without increasing the impact on traffic flow. License Plate Recognition System in traffic control, traffic management, traffic accidents and many other aspects of automatic forecasting have played an important role, is widely used in car parks, ports and airports, urban monitoring systems, road traffic observation stations, bridges and roads closed fee station, highway traffic observation station certification number plate, the actual traffic system, the paper license plate recognition system for the current main problems in the design to achieve real-time video-based license plate recognition system and related algorithms optimized.
For the difficulties of positioning vehicle plate, this dissertation solves the problem by the location algorithm based on a fixed color matching. As the background color and character color of the plate is determined by several characteristics with the composition of extracted color image. Then, the plate’s region is located by the texture of vehicle plate. This algorithm has a higher accuracy and shorter periods of time, it can still reach 96% of the targeted rate by the characteristics of the complex or exceptional circumstances. This dissertation presents a stochastic line detection method to locate the license plate of the border, and the algorithm can resolve the tilt angle of the license plate. In comparison with Hough method, this algorithm has less calculation and takes shorter periods of time. In this dissertation after analyzing the advantages and disadvantages of global and local algorithms, a new algorithm is put forward which is derived from the combination of them. The new algorithm can keep the details of the image, and effectively remove artifacts possess interference. After image binarization, the characters on the plate split into separate characters, and the characters are recognized by BP neural network, average rate of recognition is 95.7%. By using the above optimization algorithm, a real-time video-based vehicle plate recognition system is achieved in-depth analysis of demand on the vehicle plate recognition system.
引文
[1]余彦翔.基于灰度纹理分析的车牌定位算法研究:[硕士学位论文].南京:东南大学,2003.
[2]陈震,高满屯,杨声云.基于Hough变换的直线跟踪方法.计算机应用,2003,23(10):31-32.
[3]汪哲慎,李翠华.基于改进Hough变换的建筑目标搜索与识别.中国图像图形学报,2005,10(4):463-467.
[4]徐刚锋,李飚,沈振康.一种提取直线的随机方法.中国图像图形学报,2003,8(12):1418-1421.
[5] Natio.Takashi, Tsukada. Toshihiko, Yamada. Kei-ichi. Moving-vehicle license plate recognition method robust to changes in lighting conditions, Systems and Computers in Japan, 2002, 31(11): 82-91.
[6]廖翔云,徐锦标,龚仕伟.车牌识别技术研究.微机发展,2003,13(6):31-35.
[7]李小平,任江兴,杨德刚.车牌识别系统中若干问题的探讨.北京理工大学学报,2001,21(1):116-119.
[8] Ji-Lin. Li, Jia-Tao. Song, Li-Ya. Ding. Vehicle License Plate Recognition System with High Performance, ACTA AUTOMATICA SINICA, 2003, 29(3):457-465.
[9]姚德宏.基于神经网络的汽车牌照提取研究.计算机应用,2001,21(6):41-44.
[10]陈斌,游志胜.车牌号码松弛模板匹配方法.计算机应用,2001,21,(8):154-157.
[11] Bao-qing. Li. A Color Image Edge Detector Based on Quaternion Representation, Journal of Image and Graphics, 2003,8 (7):774-777.
[12]赵雪春,戚飞虎.基于彩色分割的车牌自动识别技术.上海交通大学学报,1998,32(10):4-9.
[13] R C Gonzalez, R E Woods. Digital Image Processing. Addison-Wesley, Reading, MA, 1992.
[14]谭明金.Visual C++图形编程技巧与实例.北京:人民邮电出版社,2002.2-4.
[15]何斌,马天宇,王运坚等.Visual C++数字图像处理.北京:人民邮电出版社,2002.181～182,394-425.
[16]郭大波.彩色汽车图像车牌定位技术分析.山西大学学报,2005,28(1):40-43.
[17] Yao-Quan.Yang, Jie.Bai,Rui-Li.Tian. A Vehicle License Plate Recognition System Based on Fixed Color Collocation.ICMLC 2005,vol(8):5394-5395.
[18]汪志兵,崔慧娟.一种基于纹理特征抽取的车牌定位预处理方法.计算机应用研究,2004,21(1):255-257.
[19]穆长江,苑玮琪.基于纹理特征的车牌定位方法.控制工程,2004,11(6):574-576.
[20]徐刚锋,李飚,沈振康.一种提取直线的随机方法.中国图像图形学报,2003,8(12):1418-1421.
[21]李文举,梁德群,崔连延.一种新的车牌倾斜校正方法.信息与控制,2004,33(2):231-235.
[22]曹中华,周定康,谢旭什.基于矩特性的变形图像矫正.计算机应用与软件,2004,21(4):89-90.
[23]黄新.汽车牌照自动识别系统中字符的分割和识别.[硕士学位论文].南京:南京航空航天大学,2002.
[24] Otsu N.A Threshold selection method from gray-level histograms. IEEE Trans Systems, Man and Cybernetics,1979,9(1):62-66.
[25]李填,夏良正.一种新的二维最大熵图像阈值分割方法.南京航空航天大学学报,1994,12(1):104-106.
[26] Bemsen J.Dynamic thresholding of gray-level images[A].Proc.8th Int.Conf.on Pattern Recognition[C].Los Angeles:IEEE Computer Society Press,1986:1251-1255.
[27]左奇,史忠科.基于机器视觉的胶囊完整性检测系统研究.西安交通大学学报,2002,36(12):1262-1265.
[28]张树波,赖剑煌.车牌定位和分割的一种综合方法.中山大学学报,2004,43(2):126-127,132.
[29]陈黎,黄心汉.基于聚类分析的车牌字符分割方法.计算机工程与应用,2002,38(6):221-222,256.
[30]边肇祺,张学工.模式识别.北京:清华大学出版社,2000.1-2.
[31] Mori. S, Yamamoto. K, and Yasuda. M, Research on Machine Recognition of Handprinted Characters, IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(4):386-405.
[32] Hildebrandt.T.H. and Liu.W, Optical Recognition of Handwritten Chinese Characters. Advances Since 1980, Pattern Recognition, 1993 26(2):205-225.
[33] Nabil Jean Naccache,Rajjan Shin Ghal. A Proposed Algorithm for Thinning Binary Patterns. IEEE Trans on systems, man, and cybemetics,1984,14( 3):231-235.
[34]昊佑寿,丁晓青.汉字识别原理方法与实现.北京:高等教育出版社,1992. 109-110.
[35]魏海坤.神经网络机构设计的理论与方法.北京:国防工业出版社,2005.26-30.
[36] Simon Haykin.神经网络原理.北京:机械工业出版社,2004.109-179.
[37] Wei. W, X. Huang, M. Wang. An automatic system of vehicle number-plate recognition based on neural networks, Journal of Systems Engineering and Electronics, 2001,12(2): 63-72.
[38] Daqi Gan. The Optimal Number of Hide Nodes in Multilayed Feedforward Neural Networks. IEEE.SMC CECA, LILLE, France, July, 1996.
[39]应宏微,姚明海,张永华.基于纹理分析和垂直投影的车牌定位算法.控制工程,2004,11(5):432-435.
[40]黄凯奇,王桥,吴镇扬.基于视觉特性和颜色空间的多尺度彩色图像增强算法.电子学报,32(4):673-676.
[41]华继钊,郭振民,李志军.基于彩色图像的增强算法.微电子学与计算机,2004,21(7):63-65.
[42] Jenn-Kwei.Tyan, Neubauer, Claus, Goganovic, Ljubisa. Character segmentation algorithm for recognition of vehicle license plate, Proceedings of SPIE - The International Society for Optical Engineering, 1999(38):12-21.
[43]孔明,孙希平,王永骥.一种改进的基于类间方差的阈值分割法.华中科技大学学报,2004,32(7):46-47.
[44]芮挺,沈春林,张金林.车牌识别中倾斜牌照的快速矫正算法.计算机工程,2004,30(13):121-124.
[45] Xiao-tiao. Zou, Xue-quan.Chen, Ji-rong.Chen. An intelligent vehicle license plate recognition system, Proceedings of SPIE - The International Society for Optical Engineering, v 4556, 2001, 15-19.
[46]李文举,梁德群,王新年.质量退化的车牌字符分割方法.计算机辅助设计与图形学学报,2004,16(5):697-700.
[47]张旭,王宏安,戴国忠.面向车牌识别的区域分割技术.计算机工程,2002,28(4):113-115.
[48]吴炜,余艳梅,刘大宇.一种基于Hausdorff距离的车牌字符识别算法.计算机应用研究,2004,21(2):258-260.
[49]英孝宏,戚飞虎.一种基于纹理和颜色综合特征的车牌定位新方法.计算机工程,2004,30(13):125-127.
[50]王润生.图象理解.长沙:国防科技大学出版社,1995,98-147.
[51] Oivind Due Trier,Anil K.Jain. Goal-Directed Evaluation of Binarization Methods. IEEE Trans on patern analysis and machine intelligence,1995, 17(12):973-1001.
[52] Trier O D, Jain A K, Taxt T. Feature extraction method for character recognition-A survey [J].Pattern Recognition,1996,9(4):641-662.
[53] Song Jia-Tao, Liu Ji-Lin. Analysis and extraction of structural features of alphabetic and digital characters on vehicle license plate [J]. Journal of Image and Graphics,2002,7(A)(9)945-949 (in Chinese).
[54] Coetzee C,Botha C,Weber D.PC-based number plate recognition system[C].Proceedings of IEEE International symposium on industrial electronics.1998, 605-610.
[55] Dai Yan, Ma Hong-Qing, Liu Ji-Lin, Li Lan-Gang. A high performance license plate recognition system based on Web technique [C].Proceedings of 2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland,2001,325-329.
[56] Morios , Suen C Y , Yamamoto K。Historical review of OCR research and delelopment[C].Proceeding of IEEE,1992,80(7):1029-1058.
[57] Jiang Wei-Feng,Liu Ji-Lin.Recognition of a linuted Chinese character set based on PCA learning subspace algorithm [J].Journal of Image and Graphics,2001,6 (A):186-190.
[58] Wang Shu-He.Theory of Graph and Algorithms [C].Press of University of Science&Technology of P.R.China, 1990.
[2]陈震,高满屯,杨声云.基于Hough变换的直线跟踪方法.计算机应用,2003,23(10):31-32.
[3]汪哲慎,李翠华.基于改进Hough变换的建筑目标搜索与识别.中国图像图形学报,2005,10(4):463-467.
[4]徐刚锋,李飚,沈振康.一种提取直线的随机方法.中国图像图形学报,2003,8(12):1418-1421.
[5] Natio.Takashi, Tsukada. Toshihiko, Yamada. Kei-ichi. Moving-vehicle license plate recognition method robust to changes in lighting conditions, Systems and Computers in Japan, 2002, 31(11): 82-91.
[6]廖翔云,徐锦标,龚仕伟.车牌识别技术研究.微机发展,2003,13(6):31-35.
[7]李小平,任江兴,杨德刚.车牌识别系统中若干问题的探讨.北京理工大学学报,2001,21(1):116-119.
[8] Ji-Lin. Li, Jia-Tao. Song, Li-Ya. Ding. Vehicle License Plate Recognition System with High Performance, ACTA AUTOMATICA SINICA, 2003, 29(3):457-465.
[9]姚德宏.基于神经网络的汽车牌照提取研究.计算机应用,2001,21(6):41-44.
[10]陈斌,游志胜.车牌号码松弛模板匹配方法.计算机应用,2001,21,(8):154-157.
[11] Bao-qing. Li. A Color Image Edge Detector Based on Quaternion Representation, Journal of Image and Graphics, 2003,8 (7):774-777.
[12]赵雪春,戚飞虎.基于彩色分割的车牌自动识别技术.上海交通大学学报,1998,32(10):4-9.
[13] R C Gonzalez, R E Woods. Digital Image Processing. Addison-Wesley, Reading, MA, 1992.
[14]谭明金.Visual C++图形编程技巧与实例.北京:人民邮电出版社,2002.2-4.
[15]何斌,马天宇,王运坚等.Visual C++数字图像处理.北京:人民邮电出版社,2002.181～182,394-425.
[16]郭大波.彩色汽车图像车牌定位技术分析.山西大学学报,2005,28(1):40-43.
[17] Yao-Quan.Yang, Jie.Bai,Rui-Li.Tian. A Vehicle License Plate Recognition System Based on Fixed Color Collocation.ICMLC 2005,vol(8):5394-5395.
[18]汪志兵,崔慧娟.一种基于纹理特征抽取的车牌定位预处理方法.计算机应用研究,2004,21(1):255-257.
[19]穆长江,苑玮琪.基于纹理特征的车牌定位方法.控制工程,2004,11(6):574-576.
[20]徐刚锋,李飚,沈振康.一种提取直线的随机方法.中国图像图形学报,2003,8(12):1418-1421.
[21]李文举,梁德群,崔连延.一种新的车牌倾斜校正方法.信息与控制,2004,33(2):231-235.
[22]曹中华,周定康,谢旭什.基于矩特性的变形图像矫正.计算机应用与软件,2004,21(4):89-90.
[23]黄新.汽车牌照自动识别系统中字符的分割和识别.[硕士学位论文].南京:南京航空航天大学,2002.
[24] Otsu N.A Threshold selection method from gray-level histograms. IEEE Trans Systems, Man and Cybernetics,1979,9(1):62-66.
[25]李填,夏良正.一种新的二维最大熵图像阈值分割方法.南京航空航天大学学报,1994,12(1):104-106.
[26] Bemsen J.Dynamic thresholding of gray-level images[A].Proc.8th Int.Conf.on Pattern Recognition[C].Los Angeles:IEEE Computer Society Press,1986:1251-1255.
[27]左奇,史忠科.基于机器视觉的胶囊完整性检测系统研究.西安交通大学学报,2002,36(12):1262-1265.
[28]张树波,赖剑煌.车牌定位和分割的一种综合方法.中山大学学报,2004,43(2):126-127,132.
[29]陈黎,黄心汉.基于聚类分析的车牌字符分割方法.计算机工程与应用,2002,38(6):221-222,256.
[30]边肇祺,张学工.模式识别.北京:清华大学出版社,2000.1-2.
[31] Mori. S, Yamamoto. K, and Yasuda. M, Research on Machine Recognition of Handprinted Characters, IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(4):386-405.
[32] Hildebrandt.T.H. and Liu.W, Optical Recognition of Handwritten Chinese Characters. Advances Since 1980, Pattern Recognition, 1993 26(2):205-225.
[33] Nabil Jean Naccache,Rajjan Shin Ghal. A Proposed Algorithm for Thinning Binary Patterns. IEEE Trans on systems, man, and cybemetics,1984,14( 3):231-235.
[34]昊佑寿,丁晓青.汉字识别原理方法与实现.北京:高等教育出版社,1992. 109-110.
[35]魏海坤.神经网络机构设计的理论与方法.北京:国防工业出版社,2005.26-30.
[36] Simon Haykin.神经网络原理.北京:机械工业出版社,2004.109-179.
[37] Wei. W, X. Huang, M. Wang. An automatic system of vehicle number-plate recognition based on neural networks, Journal of Systems Engineering and Electronics, 2001,12(2): 63-72.
[38] Daqi Gan. The Optimal Number of Hide Nodes in Multilayed Feedforward Neural Networks. IEEE.SMC CECA, LILLE, France, July, 1996.
[39]应宏微,姚明海,张永华.基于纹理分析和垂直投影的车牌定位算法.控制工程,2004,11(5):432-435.
[40]黄凯奇,王桥,吴镇扬.基于视觉特性和颜色空间的多尺度彩色图像增强算法.电子学报,32(4):673-676.
[41]华继钊,郭振民,李志军.基于彩色图像的增强算法.微电子学与计算机,2004,21(7):63-65.
[42] Jenn-Kwei.Tyan, Neubauer, Claus, Goganovic, Ljubisa. Character segmentation algorithm for recognition of vehicle license plate, Proceedings of SPIE - The International Society for Optical Engineering, 1999(38):12-21.
[43]孔明,孙希平,王永骥.一种改进的基于类间方差的阈值分割法.华中科技大学学报,2004,32(7):46-47.
[44]芮挺,沈春林,张金林.车牌识别中倾斜牌照的快速矫正算法.计算机工程,2004,30(13):121-124.
[45] Xiao-tiao. Zou, Xue-quan.Chen, Ji-rong.Chen. An intelligent vehicle license plate recognition system, Proceedings of SPIE - The International Society for Optical Engineering, v 4556, 2001, 15-19.
[46]李文举,梁德群,王新年.质量退化的车牌字符分割方法.计算机辅助设计与图形学学报,2004,16(5):697-700.
[47]张旭,王宏安,戴国忠.面向车牌识别的区域分割技术.计算机工程,2002,28(4):113-115.
[48]吴炜,余艳梅,刘大宇.一种基于Hausdorff距离的车牌字符识别算法.计算机应用研究,2004,21(2):258-260.
[49]英孝宏,戚飞虎.一种基于纹理和颜色综合特征的车牌定位新方法.计算机工程,2004,30(13):125-127.
[50]王润生.图象理解.长沙:国防科技大学出版社,1995,98-147.
[51] Oivind Due Trier,Anil K.Jain. Goal-Directed Evaluation of Binarization Methods. IEEE Trans on patern analysis and machine intelligence,1995, 17(12):973-1001.
[52] Trier O D, Jain A K, Taxt T. Feature extraction method for character recognition-A survey [J].Pattern Recognition,1996,9(4):641-662.
[53] Song Jia-Tao, Liu Ji-Lin. Analysis and extraction of structural features of alphabetic and digital characters on vehicle license plate [J]. Journal of Image and Graphics,2002,7(A)(9)945-949 (in Chinese).
[54] Coetzee C,Botha C,Weber D.PC-based number plate recognition system[C].Proceedings of IEEE International symposium on industrial electronics.1998, 605-610.
[55] Dai Yan, Ma Hong-Qing, Liu Ji-Lin, Li Lan-Gang. A high performance license plate recognition system based on Web technique [C].Proceedings of 2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland,2001,325-329.
[56] Morios , Suen C Y , Yamamoto K。Historical review of OCR research and delelopment[C].Proceeding of IEEE,1992,80(7):1029-1058.
[57] Jiang Wei-Feng,Liu Ji-Lin.Recognition of a linuted Chinese character set based on PCA learning subspace algorithm [J].Journal of Image and Graphics,2001,6 (A):186-190.
[58] Wang Shu-He.Theory of Graph and Algorithms [C].Press of University of Science&Technology of P.R.China, 1990.