[1]孙庭强,郑彦.一种基于字符组合的复杂环境车牌检测方法[J].计算机技术与发展,2018,28(10):168-172.[doi:10.3969/ j. issn.1673-629X.2018.10.035]
　SUN Ting-qiang,ZHENG Yan.A License Plate Detection Based on Character Combination in Complex Scenes[J].,2018,28(10):168-172.[doi:10.3969/ j. issn.1673-629X.2018.10.035]
点击复制

一种基于字符组合的复杂环境车牌检测方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年10期
页码:
168-172
栏目:
智能、算法、系统工程
出版日期:
2018-10-10

文章信息/Info

Title:
A License Plate Detection Based on Character Combination in Complex Scenes
文章编号:
1673-629X(2018)10-0168-05
作者:
孙庭强; 郑彦
南京邮电大学 计算机学院,江苏 南京 210003
Author(s):
SUN Ting-qiang; ZHENG Yan
School of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
区域生长; 稳定粒度区间; 聚类分析; 特征子集; 字符组合
Keywords:
region growing; stable granularity interval; clustering analysis; feature subset; character combination
分类号:
TP301
DOI:
10.3969/ j. issn.1673-629X.2018.10.035
文献标志码:
A
摘要:
多变的自然环境如光照变化、天气变化等,以及复杂的监控场景如拍摄背景、拍摄距离、拍摄角度、设备像素等因素,严重影响了车牌检测算法的准确性与可靠性。环境的复杂性使得车牌定位变得更加困难,传统的基于车牌定位的检测与识别方法识别率不高。 新型的基于字符组合的车牌检测与识别方法,跳过车牌定位过程转为直接定位字符,对复杂背景以及光照强度变化等具有较好的鲁棒性。 但是基于字符组合的车牌检测与识别方法也有其不足,识别准确率对字符分割具有更强的依赖性,且对于字符形变的鲁棒性低。对此,文中分别提出了一种基于多粒度区域生长的字符分割算法和一种基于多特征聚类的字符组合检测算法。 实验结果表明,多粒度区域生长分割得到的目标字符区域及其稳定粒度区间,很好地保证了分割的可靠性,通过多粒度决策融合提高了字符识别率;利用特征子集进行字符组合聚类分析,对字符形变具有良好的鲁棒性。
Abstract:
Changeable natural environment like illumination intensity and weather changes,and complex surveillance scenes like background,distance,shooting angle and device pixel,all these factors seriously affect the accuracy and reliability of the license plate detection algorithm. The complexity of the scenes makes it more difficult to locate the license plates,which causes the low recognition rate of traditional license plate detection and recognition method based on locating plate. A new license plate detection and recognition method based on character combination locate the plate characters directly instead of license plate itself,which has a better robustness to complex background and illumination intensity change. While the new method also has shortcomings due to its stronger dependence on character segmentation and low robustness to character deformation. According to the shortcomings,we propose a character segmentation algorithm based on multi-grain region growing and a character combination detection algorithm based on multi-feature clustering. Experiment shows that the target character regions and their stable granularity interval ensure the reliability of segmentation and the accuracy of identification via multi-grain decision fusion. Also,using feature subsets to do character combination clustering has a good robustness to character deformation.

相似文献/References:

[1]黄荔丽 王博亮 黄晓阳.基于DICOM格式的肝脏肿瘤CT图像分割[J].计算机技术与发展,2008,(01):48.
　HUANG Li-li,WANG Bo-liang,HUANG Xiao-yang.Segmentation of Liver Tumor in CT Image Based on DICOM Format[J].,2008,(10):48.
[2]施展 周昌乐.舌象裂纹提取及特征分析[J].计算机技术与发展,2007,(05):245.
　SHI Zhan,ZHOU chang-le.Fissure Extraction and Analysis of Image of Tongue[J].,2007,(10):245.
[3]张丽红 张慧 王晓凯.边缘检测和区域生长相结合的图像ROI提取方法[J].计算机技术与发展,2011,(04):234.
　ZHANG Li-hong,ZHANG Hui,WANG Xiao-kai.An ROI Search Method for Color Images Based on Edge Detection and Region Growing[J].,2011,(10):234.
[4]梁杰 张丽红 李林.HSI和区域生长结合的火灾图像分割方法[J].计算机技术与发展,2012,(01):191.
　LIANG Jie,ZHANG Li-hong,LI Lin.Research on Image Segmentation of Fire Based on HSI and Region Growing[J].,2012,(10):191.
[5]赵 珊,杨桃丽.一种基于相干系数的复数图像滤波方法[J].计算机技术与发展,2020,30(02):7.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 002]
　ZHAO Shan,YANG Tao-li.A Coherent Coefficient Based Filter of Complex Number Images[J].,2020,30(10):7.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 002]

更新日期/Last Update: 2018-10-10