低分辩率的车牌汉字识别是字符识别中的一个难题。随着智能交通和模式识别技术的发展,传统的基于二值图的识别方法已不能满足实际要求。该文采用基于灰度图的汉字识别方法,避免了在传统二值化过程中不必要的结构信息丢失。该文将局域二值模式(Local Binary Patterns,LBP)算子运用于字符识别,使得车牌汉字的识别率由过去的74.25%提高到98.80%;并在已有的局域二值模式算子的基础上提出了一种改进的局部二值模式(Advanced Local Binary Pattern, ALBP)算法,使得汉字的识别时间大幅度缩短。实验结果表明,该文提出的方法对于低质量的车牌灰度汉字具有较强的鲁棒性,与传统识别方法相比,识别准确率和识别速度都有了较大的改进。
Abstract
Low-resolution Chinese character recognition of vehicle license plate is a challenge issue in the character recognition. With the development of intelligent traffic, the traditional approaches based on binary images cannot meet the practical requirement. This paper applied a gray-scale image based recognition approach, avoiding the undesired structural information loss from the traditional binarization process. We introduce Local Binary Patterns(LBP) into Chinese characters recognition for the first time and achieve good results. In addition, we present an improved and efficient Advanced LBP(ALBP) operator as feature extraction, which further improves the processing speed. Experiments prove our approach is robust against low quality characters, and it is more adaptive than conventional approach both on precision (from 74.25% to 98.80) and recognition speed.
Key words artificial intelligence; pattern recognition; Chinese character recognition; ALBP; precision; recognition speed
关键词
人工智能 /
模式识别 /
汉字识别 /
ALBP /
识别准确率 /
识别速度
{{custom_keyword}} /
Key words
artificial intelligence /
pattern recognition /
Chinese character recognition /
ALBP /
precision /
recognition speed
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Peifeng Hu, Yannan Zhao, Zebong Yang, etc. Recognition of Gray Character Using Gabor Filters[C]//Proceedings of the Fifth International Conference Information Fusion, 2002,1: 419-424.
[2] Timo Ojala, Matti Pietikinen and Topi Menp. Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns[C]//Proc. 6th European Conference on Computer Vision, 2000,1842: 404-420.
[3] Timo Ojala, Matti Pietikinen and Topi Menp. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7): 971-987.
[4] 练秋生,刘春亮.基于Gabor 滤波器和LBP 的分级掌纹识别[J]. Computer Engineering and Applications. 2007,43(6): 212-215.
[5] Jun Sun, Yoshinobu Hotta, Yutaka Katsuyama, etc. Camera based Degraded Text Recognition Using Grayscale Feature[C]//Proceedings of ICDAR. Seoul, Korea, 2005:182-186.
[6] Hiroyuki Ishida, Shinsuke Yanadume, Tomokazu Takahashi, etc. Recognition of low-resolution characters by a generative learning method[C]//1st International Workshop on CBDAR,Seoul,Korea,2005: 45-51.
[7] Nei Kato, Masato Suzuki, Shin’ichiro Omachi, etc. A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21(3): 258-262.
[8] 吴天雷,马少平.基于重叠动态网格和模糊隶属度的手写汉字特征抽取[J].电子学报,2004,32(2): 186-190.
[9] 王华,丁晓青.多字体印刷藏文字符识别[J].中文信息学报,2002,17(6): 47-52.
[10] 刘伟,朱宁波,何浩智,等.基于弹性网格模糊特征的手写体汉字识别方法[J].中文信息学报,2007,21(3): 118-121.
[11] 陈光,张洪刚,郭军.一种新的加权动态网格汉字特征抽取方法[J].中文信息学报,2007,21(2): 89-93.
[12] 王学文,丁晓青,刘长松. 基于Gabor变换的高鲁棒汉字识别新方法[J].电子学报,2002,30(9): 1317-1322.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2061 KB)
