首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于改进BP神经网络的车牌字符识别
引用本文:王智文.基于改进BP神经网络的车牌字符识别[J].微电子学与计算机,2011,28(9):66-69.
作者姓名:王智文
作者单位:广西工学院计算机工程系,广西柳州,545006
基金项目:国家自然科学基金项目(60873179); 广西自然科学基金项目(2011GXNSFA018162); 深圳市科技计划基础研究项目(JC200903180630A); 高等学校博士学科点专项科研基金(20090121110032)
摘    要:在分析了BP网络学习算法的缺陷的基础上引入动量项和遗传算法对BP网络学习算法进行改进,大大提高了BP网络的收敛速度.对车牌字符图像进行分割并利用sobel算子进行边缘检测来提取字符特征.然后利用改进的BP网络来自动识别车牌字符,提高了识别的速度和正确率.

关 键 词:BP网络  动量项  遗传算法  车牌字符定位  车牌字符分割  车牌字符识别

Vehicle License Plate Recognition Based on Improved BP Network
WANG Zhi-wen.Vehicle License Plate Recognition Based on Improved BP Network[J].Microelectronics & Computer,2011,28(9):66-69.
Authors:WANG Zhi-wen
Institution:WANG Zhi-wen(Department of Computer and Engineering,Guangxi University of Technology,Liuzhou 545006,China)
Abstract:In this article,BP network learning algorithm is improved by using momentum and genetic algorithm after analyzing the defects of the BP network learning algorithm.So the convergence rate of BP network is speeded up greatly.The vehicle license plate character image is segmented and feature is extracted by edge detection using sobel operator.And then license plates of cars are automatically recognized by using improved BP neural network.This algorithm can improve the speed and accuracy for the automatic ident...
Keywords:BP network  momentum  genetic algorithm  license plate location  license plate character segmentation  license plate character recognition  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号