Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (27): 180-184.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Study of key technology in license plate recognition system

LI Yucheng,YANG Guangming,WANG Mushu   

  1. Department of Automation,North China University of Technology,Beijing 100144,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-09-21 Published:2011-09-21

车牌识别系统中关键技术的研究

李宇成,杨光明,王目树   

  1. 北方工业大学 自动化系,北京 100144

Abstract: For the defects of the key technology of the existing license plate recognition system,the key technologies of the system are improved.The techniques of license plate location and extraction adopt the method combining the image 2D energy and the HIS color space.Besides,the existing method of energy and image segmentation is improved.For the tilt correction technology,a new method based on the gravity of the density of the binary image is presented,in the recognition technology,a new method is introduced combining the feature extraction and multiply BP neural network learning.Considering the similarity of the characters in the license plate,a two-step neural network is proposed to recognize the characters.Experimental results show that the system with the key technology of the license plate recognition system is more of robustness and more of precision.

Key words: license plate extraction, license plate correction, license plate segmentation, license plate recognition, neural network, intelligent transportation system

摘要: 针对现有的车牌识别系统中的多项关键技术做了改进。车牌定位与提取技术采用了基于图像二维能量与HIS彩色空间相结合的方法,并对现有的能量算法与彩色图像分割算法做了改进。在倾斜校正中,给出了一种基于车牌二值图像的密度重心的校正方法;在识别技术中,引入了特征提取与多级BP神经网络算法相结合的分类识别方法,对车牌中部分相似字符采用二级神经网络进行精细识别。实验表明,通过对车牌识别系统中关键技术的改进可以大大提高该系统的鲁棒性与准确率。

关键词: 车牌提取, 车牌校正, 车牌分割, 车牌识别, 神经网络, 智能交通