计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (4): 186-188.DOI: 10.3778/j.issn.1002-8331.2010.04.059

• 图形、图像、模式识别 • 上一篇    下一篇

多维联想记忆神经网络在图像回忆中的应用

杨家稳1,2,孙合明1,钟 青1,胡珊珊1   

  1. 1.河海大学 理学院,南京 210098
    2.滁州职业技术学院,安徽 滁州 239000
  • 收稿日期:2008-08-06 修回日期:2008-11-10 出版日期:2010-02-01 发布日期:2010-02-01
  • 通讯作者: 杨家稳

Application of multidimensional associative memory neural networks in image recalling

YANG Jia-wen1,2,SUN He-ming1,ZHONG Qing1,HU Shan-shan1   

  1. 1.College of Science,Hohai University,Nanjing 210098,China
    2.Chuzhou Vocational and Technical College,Chuzhou,Anhui 239000,China
  • Received:2008-08-06 Revised:2008-11-10 Online:2010-02-01 Published:2010-02-01
  • Contact: YANG Jia-wen

摘要: 多维联想记忆神经网络可以用来回忆灰度图像。投影算法是回忆算法中的一类。采用不规则凸多边形的笛卡儿积构成的凸集代替正多边形的笛卡儿积构成的凸集,前者比后者更紧凑。数值实例表明,应用前者回忆灰度图像要比应用后者回忆灰度图像得到的图像更清晰,回忆所花时间更短。

关键词: 多维联想记忆神经网络, 投影, 灰度图像

Abstract: Multidimensional associative memory neural networks can be used for grayscale image recalling.Projection algorithm is one kind of recalling algorithm.One convex set which is Cartesian product of nonregular convex polygons is used instead of the other convex set which is Cartesian product of regular polygons.The former convex set is tighter than the latter convex set.Numerical examples show that the restored image is clearer and the recalling process spends less time when the former convex set is used.

Key words: multidimensional associative memory neural networks, projection, grayscale image

中图分类号: