A robust license plate location algorithm based on multi-scale feature fusion corner detection and visual color features
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [22]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Scale, affine variance and complex background are important factors affecting the accuracy of license plate location. We presented a method of license plate location based on multi-scale product of corner detection and visual color features in difference of Gaussian (DOG) scale space. Based on the image edge information in DOG scale space, we first extracted scale-and-affine-invariant corner and color features through multi-scale multiplication, and then obtained the candidate license plate location by fusing the corner and the color features. Finally, we accurately located the license plate by using the distance between the feature points in the plate region and the intensive relationship of the points. Experiments on several real-world vehicle image data sets under complex conditions have verified the proposed method has high effectiveness and efficiency in locating license plates, and greater performance in robustness of noise and affine variance than other state-of-art license plate localization methods.

    Reference
    [1] Tarabek P. A real-time license plate localization method based on vertical edge analysis[C]//Computer Science and Information Systems(FedCSIS), 2012 Federated Conference on.[s. n.]:IEEE,2012:149-154.
    [2] Du Y, Shi W, Liu C. Research on an efficient method of license plate location[J].Physics Procedia,2012,24:1990-1995.
    [3] Wu F, Lin P, Chiu C. Extracting characters fromreal vehicle licence plates out-of-doors[J]. Computer Vision,IET,2007,1(1):2-10.
    [4] 万燕,徐勤燕,黄蒙蒙.复杂背景中基于纹理和颜色的车牌定位研究[J].计算机应用与软件,2013,30(10):259-262. WAN Yan, XU Qinyan, HUANG Mengmeng. On license plate location in complex background based on texture and colour[J]. Computer Applications and Software,2013,30(10):259-262.(in Chinese)
    [5] 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[J].计算机应用研究,2004,21(1):255-257. WANG Zhibing, CUI Huijuan. A pre-process method of vehicle license plate locating based on texture characteristic extraction[J]. Application Researchof Computers,2004,21(1):255-257.(in Chinese)
    [6] Faradj F, Rezaie A H, Ziaratban M. A morphological-based license plate location[C]//Image Processing,2007. ICIP 2007, IEEE International Conference on.[s. n.]:IEEE,2007:57-60.
    [7] Mai V D, Miao D, Wang R, et al. An improved method for Vietnam License Plate location[C]. Multimedia Technology (ICMT), 2011 International Conference on. IEEE,2011:2942-2946.
    [8] 吴艳,陈忠进,乐志文.Harris角点检测与AP聚类结合的车牌定位方法[J].广西科技大学学报,2014,25(2):54-57. WU Yan, CHEN Zhongjin, LE Zhiwen. Harris corner detection combined with AP clustering method of license plate location[J]. GuangXi University of Science and Technology,2014,25(2):54-57.(in Chinese)
    [9] Chen R, Luo Y. An improved license plate location method based on edgedetection[J]. Physics Procedia,2012,24:1350-1356.
    [10] Li G, Liu C, He M Q, Huang X Y. A location method for vehicle license plate based on color image and blackwhite texture[C]//International Workshop and Conference on Photonics and Nanotechnology 2007. International Society for Optics and Photonics,[s. n.]:IEEE,2007:67944-67949.
    [11] 王枚,苏光大,王国宏.复杂环境下的车牌定位及目标真实性验证算法[J].光学精密工程,2009,17(4):886-894. WANG Mei, SU Guangda, WANF Guohong. Vehicle license plate location and object authenticity confirmation under complex environments[J]. Optics and Precision Engineering,2009,17(4):886-894.(in Chinese)
    [12] 廉宁,徐艳蕾.基于数学形态学和颜色特征的车牌定位方法[J].工程图学学报,2014,35(5):774-779. LIAN Ning, XU Yanlei. Method of license plate location based on mathematicalmorphology and color characteristics[J]. Journal of Graphics,2014,35(5):774-779.(in Chinese)
    [13] 金玲玲,廖芹,汪刘一,等.汽车牌照的提取方法[J].华南理工大学学报(自然科学版),2002,30(7):95-98. JIN Linlin, LIAO Qin,WANG Liuyi, et al. The extracting method of car license plate[J]. Journal of South China Univer sity of Technology (Natural Science Edition),2002,30(7):95-98.(in Chinese)
    [14] 刘万军,姜庆玲,张闯,等.基于CNN彩色图像边缘检测的车牌定位方法[J].自动化学报,2009,35(12):1503-1512. LIU Wanjun, JIANG Qinglin, ZHANG Chuang, et al. A novel approach for vehicle license plate locating based on CNN color image edge detection[J]. Acta Automatica Sinica,2009,35(12):1503-1512.(in Chinese)
    [15] Kim K I, Jung K, Kim J H. Color texture-based object detection:an application to license plate localization[J]. Springer Berlin Heidelberg,2002:293-309.
    [16] 章品正,王健弘.一种应用机器学习的车牌定位方法[J].应用科学学报,2011,29(2):147-152. ZHANG Pinzheng, WANG Jianhong.Vehicle License Plate Location Based on MachineLearning[J]. Journal of Applied Sciences Electronics and Information Engineering,2011,29(2):147-152.(in Chinese)
    [17] 张小洪,李博,杨丹.一种新的Harris多尺度角点检测[J].电子与信息学报,2007,29(7):1735-1738. ZHANG Xiaohong, LI Bo, YANG Dan. A novel harris multi-scale corner detection algorithm[J]. Journal of Electronics & Information Technology,2007,29(7):1735-1738.(in Chinese)
    [18] 张小洪,雷明,杨丹.基于多尺度曲率乘积的鲁棒图像角点检测[J].中国图象图形学报,2007,12(7):1270-1275. ZHANG Xiaohong, LEI Ming, YANG Dan.Robust image corner detection basedon multi-scale curvature product[J]. Journal of Image and Graphics,2007,12(7):1270-1275.(in Chinese)
    [19] 徐玲,王成良,冯欣, 等.多尺度积的协方差矩阵行列式的角点检测方法[J].计算机工程与应用,2011,47(2):160-164. XU Ling, WANG Chengliang, FENG Xin, et al. Corner detection based on multi-scale multiplication determinant of covariance matrices[J]. Computer Engineering and Applications,2011,47(2):160-164.(in Chinese)
    [20] Lindeberg T. Scale-space for discrete signals[J]. IEEE Trans. PAMI,1980,207:187-217.
    [21] 曲颖.角点在轮廓高斯差尺度空间的行为分析和检测算法研究[D].重庆:重庆大学,2012. QU Ying. Behavior analysis and detection research of corner in contour different of gaussian scale space[D].Chongqing:Chongqing University,2012.(in Chinese)
    [22] Itti L, Koch C, Niebur E. A model of saliency-base visual attention for rapid scene analysis[J]. IEEE Trans.Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

陈庄,杨峰,冯欣,崔少国,李博.多尺度积角点检测和视觉颜色特征的鲁棒车牌定位算法[J].重庆大学学报,2016,39(2):89~98

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:November 23,2015
  • Online: May 16,2016
Article QR Code