计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (30): 44-46.
• 学术探讨 • 上一篇 下一篇
郝 雷,石圣羽,宗晓萍,淮小利
收稿日期:
修回日期:
出版日期:
发布日期:
通讯作者:
HAO Lei,SHI Sheng-yu,ZONG Xiao-ping,HUAI Xiao-li
Received:
Revised:
Online:
Published:
Contact:
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。
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.
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.
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.
0 / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://cea.ceaj.org/CN/
http://cea.ceaj.org/CN/Y2007/V43/I30/44
