自适应复杂天气的车牌定位方法

J4 ›› 2014, Vol. 36 ›› Issue (02): 292-297.

自适应复杂天气的车牌定位方法

于明，路倩倩，刘玉菲，王妃

（河北工业大学计算机科学与软件学院，天津 300401）

收稿日期:2012-09-10 修回日期:2012-12-04 出版日期:2014-02-25 发布日期:2014-02-25
基金资助:
河北省科技支撑计划资助项目（11213518D）

Adaptive license plate location in complex weather

YU Ming，LU Qianqian，LIU Yufei，WANG Fei

（School of Computer Science and Engineering,Hebei University of Technology,Tianjin 300401,China）

Received:2012-09-10 Revised:2012-12-04 Online:2014-02-25 Published:2014-02-25

摘要/Abstract

摘要：

针对传统的车牌定位算法受天气、光照影响而造成的低定位率问题，提出了一种自适应的车牌定位算法。算法根据车牌颜色特征和图像清晰度判断不同天气及对比度，利用小波系数调整法调整图像对比度，最后利用垂直投影和模板匹配相融合的方法进行车牌定位。所提出的定位算法具有广泛的适应性和较高的车牌定位率，可以在晴天、阴雨天、雾天、傍晚等多种不同光照条件下，对不同对比度的图像进行车牌定位。实验结果表明，该定位方法的车牌平均定位率达到93.4%。

关键词: 对比度, 色彩特征, 小波系数增强, 车牌定位

Abstract:

According to the problem that the traditional license plate algorithms have low location rate when the images are collected in the changing weather or insufficient light, an adaptive license plate location algorithm is proposed. The algorithm determines the different weather and the image contrast by the color characteristics and image definition. The wavelet transform coefficients are used to reduce noise and stretch the contrast, achieving the effect of image enhancement. At last, it combines vertical protection and template matching algorithms to locate the license plate. The tests show that the use of the algorithm can effectively remove the noise, and solve the differentcontrast license plate location in the sun, rain, fog and dusk conditions. The average rate of license plate location is 93.4%.

Key words: image contrast;color characteristics;enhancement of wavelet coefficients;license plate location

于明，路倩倩，刘玉菲，王妃. 自适应复杂天气的车牌定位方法[J]. J4, 2014, 36(02): 292-297.

YU Ming，LU Qianqian，LIU Yufei，WANG Fei. Adaptive license plate location in complex weather [J]. J4, 2014, 36(02): 292-297.

参考文献

［1］Zhou Dongsheng, Xue Yanbin, Deng Wenhui, et al. License plate locating method based on multifeature in color image［J］. Journal of the Hebei Academy of Sciences, 2010,27(4):911.(in Chinese)
［2］Tang Lingjie, Hu Hongping. Vehicle plate location method based on mathematical morphology and projection［J］. Electronic Test, 2012(7):7680.(in Chinese)
［3］Wu Jiaming, Wu Yiquan. License plate location based on texture features chaotic particle swarm optimization［J］. CAAI Transactions on Intelligent Systems, 2011,6(4):333338. (in Chinese)
［4］Yue Zhaoxin, Zeng Huanglin. A new license plate positioning method based on improved edge characteristics extraction and BP network［J］. Computer Application and Software, 2011,28(12):8687.(in Chinese)
［5］Li Xiong, Pei Chengming, Zheng Hua. Kesearch on geometry morphology license plate recognition system based on IabVIEW［J］. Computer Simulation, 2012,29(4):353356.(in Chinese)
［6］Duan Qichang, Song Na. A method of vehicle license plate image denoising and location in low light level［C］∥Proc of 2010 WASE International Conference on Information Engineering,2010:194198.
［7］Zhang Yatao, Ji Shupeng, Wang Qiangfeng, et al. Definition evaluation algorithm based on regional contrast［J］. Journal of Applied Optics, 2012,33（2）:293298.(in Chinese)
附中文参考文献：
［1］周东升,薛彦兵,邓文慧,等.基于多种特征的彩色车牌定位方法研究［J］.河北省科学院学报, 2010,27(4):911.
［2］唐灵洁,胡红萍，白艳萍.一种基于数学形态学和投影的车牌定位方法［J］.电子测试, 2012（7）:7680.
［3］吴加明,吴一全. 基于Tent映射CPSO和车牌纹理特征的车牌定位［J］.智能系统学报, 2011,6(4):333338.
［4］岳兆新,曾黄麟.一种改进的基于边缘特征提取BP网络车牌定位的新方法［J］.计算机应用与软件, 2011,28(12):8687.
［5］李雄,裴承鸣,郑华.几何特征形态学车牌识别系统研究［J］.计算机仿真, 2012,29(4):353356.
［7］张亚涛，吉书鹏，王强锋,等.基于区域对比度的图像清晰度评价算法［J］.应用光学, 2012,33（2）293298.

[1]	王杨, 隆海燕, 贾曦然, . 基于人眼色彩差异化感知的图像质量评价研究[J]. 计算机工程与科学, 2023, 45(02): 295-303.
[2]	徐光柱, 匡婉, 万秋波, 雷帮军, 吴正平, 马国亮. 基于级联CNNs的非约束车牌精确定位[J]. 计算机工程与科学, 2022, 44(09): 1665-1675.
[3]	张贵仓, 苏金凤, 拓明秀. DTCWT域的红外与可见光图像融合算法[J]. 计算机工程与科学, 2020, 42(07): 1226-1233.
[4]	严春满，郝有菲，张迪，陈佳辉. 混合特征下最优阈值预测的图像匹配[J]. 计算机工程与科学, 2019, 41(10): 1803-1808.
[5]	周洲，黄茜，胡志辉. 基于显著性判别的缺陷检测方法[J]. 计算机工程与科学, 2018, 40(12): 2219-2223.
[6]	魏伟一,朱强军. 基于小波对比度和模函数的安全密写算法[J]. 计算机工程与科学, 2017, 39(09): 1653-1656.
[7]	陈清江，张彦博，柴昱洲，魏冰蔗 . 结合区域特性的有限离散剪切波图像融合[J]. 计算机工程与科学, 2017, 39(02): 351-358.
[8]	王钦民,李宽，杨灿群. 一种基于分类器投票的车牌定位方法[J]. J4, 2016, 38(06): 1200-1206.
[9]	曹岩. 基于形态学梯度重建的车牌定位方法[J]. J4, 2015, 37(07): 1372-1380.
[10]	熊春荣1,2，黄文明2. 基于扩展数学形态学的车牌定位算法[J]. J4, 2010, 32(8): 87-89.
[11]	李宇成,王目树. 一种快速的车牌定位与提取算法[J]. J4, 2010, 32(12): 42-45.
[12]	周爱平，梁久祯. 基于非下采样Contourlet变换多聚焦图像融合[J]. J4, 2010, 32(11): 71-74.
[13]	安勇张高伟. 基于灰度图像的车牌识别系统[J]. J4, 2006, 28(2): 61-62.
[14]	张国敏殷建平祝恩. 一种基于区域熵值的车牌定位方法[J]. J4, 2004, 26(5): 31-33.
[15]	刘杰康克军等. 小目标图象压缩的研究[J]. J4, 2001, 23(1): 44-46.