| 基于ART-2神经网络及不变矩特征的图像模式识别 |
| |
| 引用本文： | 郝雷,石圣羽,宗晓萍,淮小利.基于ART-2神经网络及不变矩特征的图像模式识别[J].计算机工程与应用,2007,43(30):44-46. |
| |
| 作者姓名： | 郝雷 石圣羽 宗晓萍 淮小利 |
| |
| 作者单位： | 河北大学,电子信息工程学院,河北,保定,071002 |
| |
| 基金项目： | 河北省自然科学基金
,
河北省教育厅科研项目
,
河北省科学技术研究与发展计划 |
| |
| 摘 要： | 将图像进行预处理并提取图像的特征,计算出图像的不变矩,利用ART-2神经网络完成了对图像的模式识别。通过实验证明ART-2神经网络具有较高的识别率,并很好地解决了神经网络在模式识别中面对识别对象出现新模式时,网络的可塑性与稳定性的矛盾。
|
| 关 键 词： | ART-2神经网络 特征提取 不变矩 模式识别 |
| 文章编号： | 1002-8331（2007）30-0044-03 |
| 修稿时间： | 2007-08 |
Application of ART-2 neural network and invariant moment in image pattern recognition |
| |
| HAO Lei,SHI Sheng-yu,ZONG Xiao-ping,HUAI Xiao-li.Application of ART-2 neural network and invariant moment in image pattern recognition[J].Computer Engineering and Applications,2007,43(30):44-46. |
| |
| Authors: | HAO Lei SHI Sheng-yu ZONG Xiao-ping HUAI Xiao-li |
| |
| Affiliation: | College of Electronic and Information Engineering, Hebei University, Baoding, Hebei 071002, China |
| |
| Abstract: | This paper mainly uses image pre-processing and feature extraction to calculate the invariant moment of image,and ultimately realizes the image pattern recognition based on ART-2 neural network.Experimental results show that ART-2 neural network has high recogintion rate.It also solves the contradiction between network's plasticity and stability,when new recogintion model appears. |
| |
| Keywords: | ART-2 neural network feature extraction invariant moment pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
