| 改进BP神经网络在物体识别中的应用 |
| |
| 引用本文： | 王灵刚,张蕾,普杰信,李洁.改进BP神经网络在物体识别中的应用[J].电光与控制,2012,19(4):68-71. |
| |
| 作者姓名： | 王灵刚 张蕾 普杰信 李洁 |
| |
| 作者单位： | 1. 中国航空工业洛阳电光设备研究所,河南洛阳,471009
2. 河南科技大学电子信息工程学院,河南洛阳,471003 |
| |
| 基金项目： | 河南省基础与前沿技术研究计划项目(102300410113); 河南省重点科技攻关项目(092102210293) |
| |
| 摘 要： | 针对传统BP神经网络容易陷入局部极小、收敛速度慢和确定隐含层的神经元个数比较困难等缺点,从结构和算法两方面对BP神经网络进行改进。改进后的网络具有较快的收敛速度和较短的运行时间,加强了BP神经网络的学习能力和自适应能力,并将其应用于物体的分类识别,取得了良好的效果。仿真结果表明了此改进方法的可行性和有效性。
|
| 关 键 词： | 物体识别 BP算法 神经网络 改进 |
| 收稿时间： | 2011/10/12 |
Application of Improved BP Neural Network in Object Recognition |
| |
| WANG Linggang
,
ZHANG Lei
,
PU Jiexin
,
LI Jie.Application of Improved BP Neural Network in Object Recognition[J].Electronics Optics & Control,2012,19(4):68-71. |
| |
| Authors: | WANG Linggang ZHANG Lei PU Jiexin LI Jie |
| |
| Affiliation: | 1(1.Luoyang Institute of Electro-Optical Equipment,AVIC,Luoyang 471009,China; 2.Electronic Information Engineering College,Henan University of Science & Technology,Luoyang 471003,China) |
| |
| Abstract: | Since the Back Propagation(BP) neural network has such shortcomings as being prone to fall into local minimum,low speed of convergence and difficult in determining the numbers of neural cell for the hidden layers,the BP neural network was improved from the structure and the algorithm in this paper.The improved BP neural network has faster convergence speed and shorter running time.And the learning ability and adaptability of the BP neural network was strengthened accordingly.The improved method was applied to object recognition and obtained a favorable result.The feasibility and validity of it was proved by a series of simulation experiments. |
| |
| Keywords: | object recognition BP algorithm neural network improvement |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
