应用激光, 2017, 37 (1): 139, 网络出版: 2017-06-27   

基于GA-BP神经网络的计算机智能化图像识别技术探究

Research on Computer Intelligent Image Recognition Technology based on GA-BP Neural Network
作者单位
中共张家口市委党校, 河北 张家口 075000
摘要
随着信息技术发展越来越迅速, 计算机智能化图像识别技术的发展也日益完善, 其发挥的作用也越来越重要。本文以神经网络方法为基础, 对计算机智能化图像识别技术进行了研究, 本文将遗传算法GA 与 BP 算法进行结合, 通过分析智能化图像识别原理、图像模式识别和BP 神经网络学习算法, 建立了GA-BP网络图像识别模型。采用四层神经网络, 输入节点设置为 256, 输出节点设置为5, 进行了GA-BP网络和BP 神经网络的对比实验, 结果表明, 在进行数字图像识别时, GA-BP网络正确识别率为 98.7%, BP 网络正确识别率为92.5%, GA-BP网络正确识别率比BP网络要高出6.2%, GA-BP网络克服了BP网络收敛速度慢和训练时间长的缺点。
Abstract
With the development of information technology more and more rapidly, the development of computer intelligent image recognition technology is also becoming more and more perfect, and its function is more and more important. This paper is based on the neural network method, the intelligent computer image recognition technology is studied in this paper, genetic algorithm and GA BP algorithm are combined, through the analysis of intelligent image recognition principle, image pattern recognition and BP neural network learning algorithm, a GA-BP network model for image recognition. The four layer neural network, the input node is set to 256, the output node is set to 5, conducted a comparative experiment of GA-BP and BP neural network. The results show that the digital image recognition, the correct recognition rate is up to 98.7% GA-BP network BP network, the correct recognition rate was 92.5%, the GA-BP network recognition rate is up to 6.2% compared with BP network, GA-BP network to overcome the slow convergence of BP network and the shortcomings of long training time.

曹永峰, 赵燕君. 基于GA-BP神经网络的计算机智能化图像识别技术探究[J]. 应用激光, 2017, 37(1): 139. Cao Yongfeng, Zhao Yanjun. Research on Computer Intelligent Image Recognition Technology based on GA-BP Neural Network[J]. APPLIED LASER, 2017, 37(1): 139.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!