自动车牌定位及字符分割研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
智能交通是当前交通管理发展的主要方向,汽车牌照识别技术则是智能交通系统的核心,在城市道路管理、港口、机场、高速公路和停车场等项目管理中占有重要地位。车牌自动识别系统分为车牌定位、车牌字符分割和字符识别三个部分,其中车牌定位和字符分割是核心技术,直接影响系统的识别率和速度。本文针对车牌定位和车牌字符分割进行了较系统的研究。
     首先,以图像处理技术为基础,对采集到的车牌图像进行预处理,得到质量较好的汽车图像,这为后续的车牌定位及字符分割处理打下良好的基础;其次,根据车牌图像具有丰富的纹理和车牌区域为矩形且边缘互相平行等特征,提出了一种基于方向场和车牌边缘信息的车牌定位方法,并针对车牌图像存在的倾斜和变形,提出了一种基于方向场的车牌水平倾斜校正和基于单个字符投影的竖直变形校正方法;最后,利用统计的方法,对字符特征进行分析,采用垂直投影法对字符进行分割。
     在上述算法的基础上,我们用Visual C++完成一个实验系统,通过对200多幅车辆图像进行测试。实验结果表明,对各种不同大小、光照条件不同的图像,建议方法都能准确地定位车牌和分割字符。这些为下一步的字符识别及完成车牌自动识别系统的工作奠定了基础,具有较好的理论研究意义和实际应用价值。
The intelligent transportation is the main direction of the development of transportation management. License plate recognition (LPR) technology is a key of intelligent transportation systems. It is important in the project management of urban road management, ports, airports, expressway and parking area, etc. Usually, the LPR system consists of three main parts: license plate localization, character segmentation, and character recognition. The license plate localization and character segmentation are the most crucial stage. It result has an important impact on the accuracy and speed for the LPR system. The propose algorithm with research to the license plate location and character segmentation.
     Firstly, the vehicle license plate image is preprocessed with image processing technology to get better quality vehicle image. It has built a good foundation for license plate localization and character segmentation. Secondly, the license plate upper and lower borders are parallel each other. There are rich edge and texture information. We present an algorithm based on orientation field and edge information for location of license plates. Furthermore, we present a new algorithm based on orientation field for horizontal skew correction and an algorithm based on single-character projection for vertical distortion correction. Finally, character feature is analyzed with statistic method, and license plate character is segmented by vertical projection method.
     Based on the above algorithm, we develop practical experimental system with Visual C++ and it is tested with 200 various vehicle images. Experimental results show that proposed method can accurately localization and character segmentation various license plate of different size and illumination. The research is an important foundation for next character recognition and LPR system completing, and it has both better the theoretical research significance and applied value.
引文
[1] http://itsdeployment2.ed.ornl.gov/technology_overview/. Last day of access, August 10th 2005.
    [2] T. Sirithinaphong and K. Chamnongthai, The recognition of car license plate for automatic parking system[C]. in Proc. 5th Int. Symp. Signal Processing and its Applications, (1998):455–457.
    [3] N. H. C. Yung, et al., Recognition of vehicle registration mark on moving vehicles in an outdoor environment[J]. in Proc. IEEE Int. Conf. Intelligent Transportation Systems, (1999), pp. 418–422.
    [4] J. R. Cowell, Syntactic pattern recognizer for vehicle identification numbers[J]. Image and Vision Comput., (1995), 13(1):13–19.
    [5] R. A. Lotufo, et al., Automatic numberplate recognition[J].Inst. Elect. Eng. Colloquium on Image Analysis for Transport Applications, (1990),pp. 6/1–6/6.
    [6] Kamat, et al., An efficient implementation of hough transform for detecting vehicle license plates using DSP[J]. In Proceedings of real-time technology and applications .(1995),pp. 58-59.
    [7] S. M. Youssef and S. B. AbdelRahman, A smart access control using an efficient license plate location and recognition approach[J]. Expert Systems with Applications,(2008),34(1):256-265.
    [8] T. Naito, Robust recognition methods for inclined license plates under various illumination condition outdoors[J].Proc., IEEE/IEEJ/JSAI Int. Conf. on Intelligent Transportation Systems,(1999), pp.697-702.
    [9] C. Busch, et al., Feature based recognition of traffic video streams for online route tracing[J].Proc., IEEE Conf. on Vehicular Technology, (1998) ,3:1790-1794 ".
    [10] R. Zunino and S. Rovetta, "Vector Quantization for license-plate location and image coding[J].IEEE Trans. Ind. Electron. (2000),47:159-167 .
    [11] http://www.hw99.com/.
    [12] http://www.dragonskytech.com/.
    [13] Takashi.N, et al., Robust license plate recognition method for passing vehicles under outside environment[J].IEEE Transactions on Vehicular Technology,(200),49,(6):2309-2319.
    [14]高守传,姚领田.Visual C++实践与提高——数字图像处理与工程应用篇[M].北京:中国铁道出版社, 2005,20
    [15]陈轩飞.车牌识别技术的研究[D].长沙:中南大学, 2004.11.
    [16]孟杰,基于灰度图像的车牌定位及字符分割算法研究[J],陕西:长安大学, 2008.
    [17]田村秀行.计算机图像处理技术[M].北京:北京师范大学, 2001.
    [18]王耀南,李树涛.计算机图像处理与识别技术[M].北京:高等教育出版社, 2001.
    [19]阮秋琦.数字图像处理学(第二版)[M].北京:电子工业出版社2007.
    [20]廖金周,宣国荣.车牌的自动分割[J].微型电脑应用, vol. 7, pp. 32-34, 1999.
    [21]张引,潘云鹤.面向车辆牌照字符识别的预处理算法[J].计算机应用与研究, vol. 7 pp. 85-87, 1999.
    [22]公安部道路交通管理标准化技术委员会, GA36-1992,中华人民共和国公共安全行业标准—中华人民共和国机动车号牌[S].北京:中国标准出版社.
    [23]刘庆祥,蒋天发.智能车牌自动识别系统中图像获取技术的研究[J].武汉理工大学学报(工程), vol. 27, p. 127一130, 2003.
    [24] S. L. Chnag, et al., Automatic License Plate Recognition[J]. IEEE Transactions on Intelligent Transportation Systems, vol. 5, p. 42一53, 2004.
    [25] W. Wei, et al., An automatic method of location for number plate using color features[C].in: Proceedings of 2001 international conference on image processing, 2001. pp.782-785.
    [26] H.J.Kim, et al., Automatie Roecngition of Car License Plates Using Color lmage Poreessing[J]. Engineering Desingand Automation, vol. 3, p. 215一225, 1997.
    [27] G. Jie and S. P. fei, Color and Texture Analysis Based Vehicle License Plate Location[J]. Journal of Image and Graphics, pp. 362-366, 2002.
    [28] K. Kim, et al., Color texture-based object detection: an application to license plate localization[C]. in: Proceedings of the .rst international workshop on pattern recognition with support vector machines, 2002. pp.293-309.
    [29] S. H. Park, et al., Locating car license plate using neural networks[J].Electron. Letter, 1999,35 (17):1475-1477.
    [30] Xinxiang, Method of License Plate Location Based on HSV and Mathematical Morphology[J].Video Engineering,(2009),06.
    [31] Z. LIJING, et al., A Mothed of Vehicle License Plate Location Based on HSV Space[J], Microcomputer Information, pp. 86-89, 2008.
    [32] W. Zhu, et al., A study of locating vehicle license plate basedon color feature and mathematical morphology[J],Signal Processing,(2002),1(7):748-751.
    [33] RodolofZunino and SteafnoRovetta., Vector Quantization for License-Plate Location and Image Coding[C], IEEE Transactions on Industrial Electronics, vol. 47, pp. 159-167, 2000.
    [34]王.枚,彩色图像特征融合规则及其在车牌定位中的应用[J].计算机应用研究,(2008),25(1):288-290.
    [35]杨文霞.基于车体对称及颜色聚类的车牌自动定位方法[J].计算机应用研究,(2005),2:225-229.
    [36]周泽华.基于多颜色模型的车牌定位方法[J].模式识别,(2007),1(1):283-285.
    [37]朱明旱,罗大庸.基于颜色相似度的车牌定位算法[J].计算机测量与控制,(2005),13(8):835-837.
    [38] W. Jia, et al., Region-based license plage detection[J].Journal of Network and Computer Applications,(2007),30:1324-1333.
    [39] V. Shapiro and D. Dimov, Adaptive License Plate Image Extraction[J].International Conference on Computer Systems and Technologies, (2003),pp. - IIIA.2-1 -IIIA.2-7.
    [40] S. Gendy, et al., Automatic car registration plate recognition using fast hough transform[C]. in: Proceedings of the institute of electrical and electronics engineers 31st annual 1997 international carnahan conference on security technology, 1997.
    [41] Z. Chen, et al., Automatic License Plate Location and Recognition Based on Feature Salience[J]. INTERNATIONAL JOURNAL OF COMPUTATIONAL COGNITION, (2007), 5:1-9.
    [42] V. Kamat and S. Ganesan, An efficient implementation of the hough transform for detecting vehicle license plates using dsp's[C].in: Proceedings of 1995 real-time technology and applications symposium, 1995.
    [43] D. Zheng, et al., An efficient method of license plate location[J].Pattern Recognition Letters, 2005. 26:2431-2438.
    [44] Y. Yanamura, et al., Extraction and tracking of the license plate using hough transform and voted block matching[J].in: Proceedings of IEEE intelligent vehicles symposium, 2003. pp.243-246.
    [45] H. Bai, et al., A fast license plate extraction method on complex background[C].in: Proceedings of 2003 IEEE intelligent transportation systems conference, 2003. pp.985-987.
    [46] H. Bai and C. Liu, A hybrid license plate extraction method based on edge statistics and morphology[C]. in: Proceedings of the 17th international conference on pattern recognition, 2004. pp.831-834.
    [47] C.Wu, et al., A macao license plate recognition system[C].IEEE Proceeding forthe Fourth International Conference on Machine Learning and Cybernetics,2005,1:4506-4510.
    [48] C.T.Hsieh,et al.,Multiple license plate detection for complex background[C].IEEE Proceedings of the 19th International Conference on Advanced Information Networking and Applications(AINA'05),2005.
    [49] S. Kim, et al., A robust license-plate extraction method under complex image conditions[C] in: Proceedings of the 16th international conference on pattern recognition, 2002. pp.216-219.
    [50] L. Wang and M. Dai, Application of new feature in fingerprint classification[J]. Pattern recognition letter,2007,28:1640-1650.
    [51] A.M.Bazen and S.H.Gerez, Directional field computation for fingerprints based on the principal component analysis of local gradients[C].Proceedings of ProRISC200,11th Annual Workshop on Circuits, Systems and Signal Processing, Veldhoven,Netherlands,2000.
    [52] L.Wang, et al., Fingerprint Image Segment based on GaussianHermite Moments[C].The First International Conference on Advanced Data Mining and Applications(ADMA2005),Wuhan,China,2005.
    [53] B.M.Mehtre, et al.Segmentation fingerprint images using the directional image[J].Pattern Recognition,1987,20:429-435.
    [54]翟波.基于方向信息的指纹图像预处理[J].计算机工程与科学,(2005),27(7):60-62.
    [55]周嫒嫒,张成.基于块方向的指纹图像预处理算法[J].微型机与应用,(2004),12:26-29
    [56]臧兰云,刘瑞华.指纹方向图提取算法研究[J].计算机工程,(2005),31:239-241.
    [57] A. Jain, et al., On-line fingerprint verification [J] . IEEE Trans. Pattern Anal. Machine Intell,1997,19:302-314.
    [58] A. M. Bazen and S. H. Gerez, Systematic methods for the computation of the directional fields and singular points of fingerprints[J].IEEE Trans. Pattern Anal. Machine Intell,2002, 24: 905-919.
    [59] F. Cheng and A. N. Venetsanopoulos, An adaptive morphological filter for image processing[J]. IEEE Transactions on Image Processing, 1992,1(4): 533–539.
    [60] A. G. Hanbury and J. Serra, Analysis of oriented textures using mathematical morphology[J]. in Vision with Non-Traditional Sensors, 2002,9.
    [61] J. Illingworth, and J. Kittler.The adaptive Hough Transform[J].IEEE Trans.Pattern analysis and Machine Intelligence, 1987, 9( 5):690-697
    [62] Zhenhui Zhang ,Shaohong Yin.Hough Transform and Its Application in Vehicle License Plate Tilt Correction[J].Computer and Information Science,2008,1(3):116-119.
    [63] L.Liu, S. Y. Zhang, Y. Zhang and X.Z. Ye. Slant correction of vehicle license plate image[J]. Lecture Notes in Computer Science,2005 ,3617:237-244.
    [64] X. Pan, X.Z. Ye and S.Y. Zhang. A hybrid method for robust car plate character recognition[J]. Engineering Applications of Artificial Intelligence 2005,18 :963-972.
    [65] Liu Shaomei Yang Dingcai.License plate slant correction method based on least square and principal component analysis[J];Electronic Measurement Technology;2008,04.
    [66]黄骥,吴一全.基于颜色对特征点主成分分析的车牌校正方法[J].中国图象图形学报,2008,13(4):642-647.
    [67]朱程辉,吴德会.基于主元分析的倾斜车牌图像校正方法研究[J].微电子学与计算机,2006,23(1):177-180.
    [68]李文举,梁德群,崔连延.一种新的车牌倾斜校正方法[J].信息与控制, 2004, 33(2): 231-235.
    [69] J.Shen and S.Castan, "An Optimal linear operator for step edge detection[J].CVGIP:Graphical Model and Image Processing,(1992),54(2):121-124."
    [70] Kiyoshi Arai, Tsuneya Kurihara, Ken-ichi Anjyo.Bilinear interpolation for facial expression and metamorphosis in real-time animation [J].Visual Computer,(2005),6:105-116.
    [71] K.T. Gribbon, C.T. Johnston, and D.G. Bailey.A Real-time FPGA Implementation of a Barrel Distortion Correction Algorithm with Bilinear Interpolation[J].Image and Vision Computing NZ,2003,11:408-413.
    [72]周开军,陈三宝,徐江陵.复杂背景下的车牌定位和字符分割研究[J].计算机工程,(2007),33(4):198-200.
    [73]朱俊梅,陈少平.基于改进的投影方法的车牌图像字符分割[J].中南民族大学学报(自然科学版),2007,20(4):58-61.
    [74] Shigueo Nomuraa,KeijiYamanakab,Osamu Kataia.Anovel adaptive morphological approach for degraded character image segmentation[J].Pattern Recognition,2005,38:1961-1975.
    [75]迟晓君,孟庆春.基于投影特征值的车牌字符分割算法[J].计算机应用研究,2006,7:652-653.
    [76]周景超,陈锋,陈为多,王家捷.车牌字符分割的研究和实现[J].计算机工程,2006,32(5):238-240.
    [77] Yanamura Y.,Goto M.,Nishiyama D,Soga M,Nakatani H,Saji H. Extraction andtracking of the license plate using Hough transform and voted block matching[J].IEEE IV2003 Intelligent Vehicles Symposium.2003:243~246.
    [78]张云刚,张长水.利用Hough变换和先验知识的车牌字符分割算法[J].计算机学报,(2004),27(1):130-135.
    [79]陈黎,黄心汉,王敏,李炜.基于聚类分析的车牌字符分割方法[J].计算机工程与应用,2002,6:221-223.
    [80] S. Belongie, J. Malik, and J. Puzicha, Shape matching and object recognition using shape contexts[J].IEEE Trans. on Pattern Analysis and Machine Intelligence,(2002), 24(4):509-522.
    [81]罗文村.基于阈值法与区域生长法综合集成的图像分割法[J].现代计算机,2001,45(5):43-47.
    [82]李文举,梁德群,王新年,于东.质量退化的车牌字符分割方法[J].计算机辅助设计与图形学学报,2004,16(5):895-899.
    [83] B. D. Trier, Goal-Directed Evaluation of Binarization Methods[J].IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,(1995),17(12):1191-1021.
    [84] C. Moonsoo, et al., Improved Binarization Algorithm for Document Image by Histogram and Edge Detection[C]. Proceedings of the Thrid International Conference on Document Analysis and Recognition,1995,2:14-16.
    [85] T. S and W. L, An Original Multi-scale Algorithm to Binarize Image[C]. Proceedings 16th International Conference on Pattern Recognition,2002,4:322-325.
    [86]龙钧宇,金连文.一种基于全局均值和局部方差的图像二值化方法[J].计算机工程.2004,30(2):70-73.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700