基于MSER与边缘投影的车牌定位算法
|
摘要
针对基于颜色或边缘的车牌定位算法常出现误定位的问题,提出一种适用于嵌入式平台的基于MSER与边缘投影相结合的车牌定位算法。对RGB彩色图像进行灰度变换突出车牌区域,使用MSER算法进行连通域分析获取车牌位置;对于车牌和车身颜色一致的情况,设计垂直边缘投影算法进行补充定位;利用车牌的字符间距特征进一步提高车牌定位的准确度。实验结果表明,该算法对车牌倾斜、弯折、光照不均、大小不一、背景杂乱、分辨率低等情况具有很好的鲁棒性,准确率可达97.1%,适合应用于嵌入式车牌识别系统。
To solve the problem of current license plate location algorithms based on color or edge usually get false positive candidate regions,a method of license plate location which combined MSER feature and edge projection algorithm was presented.Gray level transformation was applied on RGB color images to highlight license plate regions,MSER algorithm was used to perform connected component analysis to obtain the position of license plates.For the case of the color of the license plate being the same as the color of the car,vertical edge projection algorithm was designed for complementary.By using the character spacing feature,the location accuracy was further improved.Experimental results show that the proposed method is robust to license tilt,buckling,complex background and low resolution with 97.1%accuracy and it is suitable to be applied to embedded license plate recognition system.
To solve the problem of current license plate location algorithms based on color or edge usually get false positive candidate regions,a method of license plate location which combined MSER feature and edge projection algorithm was presented.Gray level transformation was applied on RGB color images to highlight license plate regions,MSER algorithm was used to perform connected component analysis to obtain the position of license plates.For the case of the color of the license plate being the same as the color of the car,vertical edge projection algorithm was designed for complementary.By using the character spacing feature,the location accuracy was further improved.Experimental results show that the proposed method is robust to license tilt,buckling,complex background and low resolution with 97.1%accuracy and it is suitable to be applied to embedded license plate recognition system.
引文
[1]XIE Yongxiang,DONG Lanfang.License plate recognition in complex background base on HSV space and template matching[J].Journal of Graphics,2014,35(4):585-589(in Chinese).[谢永祥,董兰芳.复杂背景下基于HSV空间和模板匹配的车牌识别方法研究[J].图学学报,2014,35(4):585-589.]
[2]TIAN Hongpeng,JIAO Xin.License plate location method based on embedded Linux and OpenCV[J].Computer Engineering and Design,2014,35(11):3908-3912(in Chinese).[田红鹏,焦鑫.基于嵌入式Linux和OpenCV的车牌定位方法[J].计算机工程与设计,2014,35(11):3908-3912.]
[3]Wang C,Liu J.License plate recognition system[C]//International Conference on Fuzzy Systems and Knowledge Discovery.IEEE,2015:1708-1710.
[4]Amir Hossein Ashtari,Md Jan Nordin,Mahmood Fathy.An Iranian license plate recognition system based on color features[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(4):1690-1705.
[5]Dun Jingyu,Zhang Sanyuan,Ye Xiuzi,et al.Chinese license plate localization in multi-lane with complex background based on concomitant colors[J].IEEE Intelligent Transportation Systems Magazine,2015,7(3):51-61.
[6]Muhammad Rizwan Asif,Qi Chun,Sajid Hussain,et al.Multiple license plate detection for Chinese vehicles in dense traffic scenarios[J].IET Intelligent Transport Systems,2016,10(8):535-544.
[7]Thanh-Sach Le,Van-Nhan Tran,Kazuhiko Hamamoto. A robust and flexible license plate detection method[C]//International Conference on Advanced Technologies for Communications.IEEE,2015:326-331.
[8]Feng Fujian, Wang L.Approach for license plate location using texture direction and edge feature[C]//Chinese Conference on Image and Graphics Technologies.Springer Berlin Heidelberg,2015:80-86.
[9]Yu Shouyuan,Li Baopu,Zhang Qi,et al.A novel license plate location method based on wavelet transform and EMD analysis[J].Pattern Recognition,2015,48(1):114-125.
[10]Al-Ghaili AM,Mashohor S,Ramli AR,et al.Vertical edge based car license plate detection method[J].IEEE Transactions on Vehicular Technology,2013,62(1):26-38.
[11]Yuan Yule,Zou Wenbin,Zhao Yong,et al.A robust and efficient approach to license plate detection[J].IEEE Transactions on Image Processing,2017,26(3):1102-1114.
[12]Gu B.Visual attention saliency model for license plate location[J].International Journal of Signal Processing Image Processing and Pattern Recognition,2015,8(2):267-274.
[13]Greenhalgh J, Mirmehdi M.Recognizing text-based traffic signs[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(3):1360-1369.
[14]Gou C,Wang K,Yao Y,et al.Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(4):1096-1107.
[2]TIAN Hongpeng,JIAO Xin.License plate location method based on embedded Linux and OpenCV[J].Computer Engineering and Design,2014,35(11):3908-3912(in Chinese).[田红鹏,焦鑫.基于嵌入式Linux和OpenCV的车牌定位方法[J].计算机工程与设计,2014,35(11):3908-3912.]
[3]Wang C,Liu J.License plate recognition system[C]//International Conference on Fuzzy Systems and Knowledge Discovery.IEEE,2015:1708-1710.
[4]Amir Hossein Ashtari,Md Jan Nordin,Mahmood Fathy.An Iranian license plate recognition system based on color features[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(4):1690-1705.
[5]Dun Jingyu,Zhang Sanyuan,Ye Xiuzi,et al.Chinese license plate localization in multi-lane with complex background based on concomitant colors[J].IEEE Intelligent Transportation Systems Magazine,2015,7(3):51-61.
[6]Muhammad Rizwan Asif,Qi Chun,Sajid Hussain,et al.Multiple license plate detection for Chinese vehicles in dense traffic scenarios[J].IET Intelligent Transport Systems,2016,10(8):535-544.
[7]Thanh-Sach Le,Van-Nhan Tran,Kazuhiko Hamamoto. A robust and flexible license plate detection method[C]//International Conference on Advanced Technologies for Communications.IEEE,2015:326-331.
[8]Feng Fujian, Wang L.Approach for license plate location using texture direction and edge feature[C]//Chinese Conference on Image and Graphics Technologies.Springer Berlin Heidelberg,2015:80-86.
[9]Yu Shouyuan,Li Baopu,Zhang Qi,et al.A novel license plate location method based on wavelet transform and EMD analysis[J].Pattern Recognition,2015,48(1):114-125.
[10]Al-Ghaili AM,Mashohor S,Ramli AR,et al.Vertical edge based car license plate detection method[J].IEEE Transactions on Vehicular Technology,2013,62(1):26-38.
[11]Yuan Yule,Zou Wenbin,Zhao Yong,et al.A robust and efficient approach to license plate detection[J].IEEE Transactions on Image Processing,2017,26(3):1102-1114.
[12]Gu B.Visual attention saliency model for license plate location[J].International Journal of Signal Processing Image Processing and Pattern Recognition,2015,8(2):267-274.
[13]Greenhalgh J, Mirmehdi M.Recognizing text-based traffic signs[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(3):1360-1369.
[14]Gou C,Wang K,Yao Y,et al.Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(4):1096-1107.