基于颜色特征与模板匹配的车牌识别系统设计与实现
|
摘要
为实现对国内蓝底白字车牌的快速识别,提出一种基于颜色特征与模板匹配的车牌识别系统。通过分析长宽比、白色比例对车牌候选区域进行多次筛选以检测车牌位置,然后对车牌区域进行图像灰度化、倾斜校正、二值化、擦除反色与裁剪后,利用垂直投影分割出字符,最后通过比较字符图像与模板字符的相似度识别出字符。通过对400张不同颜色和背景条件下的车辆图像进行测试,系统处理时间为1.97s,识别正确率达到92%。
In order to realize the fast recognition of domestic blue and white plate,the license plate recognition method based on the color feature and template matching was proposed.Through the analysis of the aspect ratio,the proportion of white in the license plate candidate area to detect the location of license plate,and then through the image was grayed,tilt was corrected,binarized,erasedand inversed,cropped,the character was segmented by using vertical projection,and finally through the similarity comparison of character image and template characters to identify the character.Through the 400 vehicle images was tested under different color and background,the recognition accuracy is 92%,and the system processing time is 1.97 s.
In order to realize the fast recognition of domestic blue and white plate,the license plate recognition method based on the color feature and template matching was proposed.Through the analysis of the aspect ratio,the proportion of white in the license plate candidate area to detect the location of license plate,and then through the image was grayed,tilt was corrected,binarized,erasedand inversed,cropped,the character was segmented by using vertical projection,and finally through the similarity comparison of character image and template characters to identify the character.Through the 400 vehicle images was tested under different color and background,the recognition accuracy is 92%,and the system processing time is 1.97 s.
引文
[1]AH ASHTARI,MJ NORDIN,M FATHY.Aniranian license plate recognition system based on color features[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(4):1690-1705.
[2]MF ZAKARIA,SA SUANDI.Malaysiancar number plate detection system based on template matching and colour information[J].International Journal on Computer Science and Engineering,2010,2(4):1159-1164.
[3]Y YANAMURA,M GOTO,D NISHIYAMA,et al.Extraction and tracking of the license plate using hough transform and voted block matching[J].IEEE Intelligent Vehicles Symposium,2003:243-246.
[4]F M KAZEMI,S SAMADI,H R POORREZA,et al.Vehicle recognition based on Fourier,wavelet and curvelet transforms—a comparative study[J].International Journal of Computer Science and Network Security,2007,7:939-940.
[5]HASAN,MAHMUDUL.Real time detection and recognition of license plate in bengali[J].Bourns College of Engineering,2013.
[6]C N E ANAGNOSTOPOULOS,I E ANAGNOSTOPOULOS,I D PSOROULAS,et al.License plate recognition from still images and video sequences:a survey[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(3):377-391.
[7]F WANG,L MAN,B WANG,et al.Fuzzy-based algorithm for color recognition of license plates[J].Pattern Recognition Letters,2008,29(7):1007-1020.
[8]S NOMURA,K YAMANAKA,O KATAI,et al.A novel adaptive morphological approach for degraded character image segmentation[J].Pattern Recognition,2005,38(11):1961-1975.
[9]PRIYA V LAKSHMI,PERUMAL K.Detecting the car number plate using segmentation[J].International Journal of Engineering and Computer Science,2014(10):8823-8829.
[10]GUPTA PRATIKSHA,G N PUROHIT,RATHORE MANISHA.Number plate extraction using template matching[J].International Journal of Computer Applications,2014,88(3):40-44.
[11]MH DASHTBAN,Z DASHTBAN,H BEVRANI.A novel approach for vehicle license plate localization and recognition[J].International Journal of Computer Applications.2011,26(11):22-30.
[12]马永慧.车牌识别系统中车牌定位与字符分割的研究[D].太原:中北大学,2013.
[2]MF ZAKARIA,SA SUANDI.Malaysiancar number plate detection system based on template matching and colour information[J].International Journal on Computer Science and Engineering,2010,2(4):1159-1164.
[3]Y YANAMURA,M GOTO,D NISHIYAMA,et al.Extraction and tracking of the license plate using hough transform and voted block matching[J].IEEE Intelligent Vehicles Symposium,2003:243-246.
[4]F M KAZEMI,S SAMADI,H R POORREZA,et al.Vehicle recognition based on Fourier,wavelet and curvelet transforms—a comparative study[J].International Journal of Computer Science and Network Security,2007,7:939-940.
[5]HASAN,MAHMUDUL.Real time detection and recognition of license plate in bengali[J].Bourns College of Engineering,2013.
[6]C N E ANAGNOSTOPOULOS,I E ANAGNOSTOPOULOS,I D PSOROULAS,et al.License plate recognition from still images and video sequences:a survey[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(3):377-391.
[7]F WANG,L MAN,B WANG,et al.Fuzzy-based algorithm for color recognition of license plates[J].Pattern Recognition Letters,2008,29(7):1007-1020.
[8]S NOMURA,K YAMANAKA,O KATAI,et al.A novel adaptive morphological approach for degraded character image segmentation[J].Pattern Recognition,2005,38(11):1961-1975.
[9]PRIYA V LAKSHMI,PERUMAL K.Detecting the car number plate using segmentation[J].International Journal of Engineering and Computer Science,2014(10):8823-8829.
[10]GUPTA PRATIKSHA,G N PUROHIT,RATHORE MANISHA.Number plate extraction using template matching[J].International Journal of Computer Applications,2014,88(3):40-44.
[11]MH DASHTBAN,Z DASHTBAN,H BEVRANI.A novel approach for vehicle license plate localization and recognition[J].International Journal of Computer Applications.2011,26(11):22-30.
[12]马永慧.车牌识别系统中车牌定位与字符分割的研究[D].太原:中北大学,2013.