一种基于全局阈值二值化方法的BP神经网络车牌字符识别系统_张坤艳.pdf

CN43- 1258/T P 2010 32 2 ISSN 1007- 130X COMPUTER ENGINEERING SCIENCE Vol1 32,No1 2, 2010 : 1007- 130X(2010)02-0088-03 * P A Plate-Character Identification System ased on Globa-l Valve inarization and the P Neural Network 1 2 1 1 , , , 1 2 1 1 ZHANG Kun-yan , ZHONG Y-i ya , MIAO Song- chi , WANG Gui-juan ( 1. , 250 10 1;2. , 100 102 ( 1. School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250 10 1; 2. Beijing Institute of Economic Management, Beijing 100102, China : 本文针对车牌字符识别系统在工程应用中存在识别准确率不高效率低的问题, 从工程实 的角度描述了一 种新的基于 P 神经网络的识别系统在车牌字符识别中的应用详细介绍了车牌字符识别中的样本集和测试集的组织 图像二值化归一化图像去噪神经网络构建和训练实 结果表明, 本系统适用于自然场景中的车牌自动识别问题, 并 且具有较强的适应性 Abstract: In view of the shortcomings of the automobile license plate identification systems, such as the low identifica- tion accuracy and efficiency under practical conditions, a new identification system based on the P network is designed. In terms of engineering application, the character identification of automobile license plates is addressed in detail, including building the training sets of samples, image binarization, normalization, removal of noise, and neural netw ork construction. The experimental results show that the system has good performance even w hen the images have low quality and the license plates are located in a complicated natural scene. :车牌字符识别; P 网络; 图像二值化; 全局阈值; 去噪 Key words: automobile license plate character identification; P neural netw ork; image binarization;global valve;rem