首页 | 本学科首页   官方微博 | 高级检索  
     

尺度空间的联想记忆网络在灰度图中的应用
引用本文:冉天保,吴锡生.尺度空间的联想记忆网络在灰度图中的应用[J].计算机仿真,2007,24(7):156-159.
作者姓名:冉天保  吴锡生
作者单位:江南大学信息工程学院,江苏,无锡,214122
摘    要:形态联想记忆网络具有十分优越的抗膨胀噪声或者腐蚀噪声的能力,但抗混合噪声的能力很弱,而在实际中,随机噪声往往是混合型的,既有膨胀噪声又有腐蚀噪声.将形态学尺度空间和形态联想记忆网络相结合,得到了一种新的联想记忆网络,它也具有优越的抗膨胀噪声或者腐蚀噪声的能力,同时它对随机噪声有一定的鲁棒性.通过对含有随机噪声的灰度图像进行自联想记忆和识别处理实验,取得了较为理想的结果,验证了其具有良好的性能.

关 键 词:尺度空间  联想记忆  膨胀存储矩阵  腐蚀存储矩阵  灰度图像  形态学尺度空间  记忆网络  灰度图像  应用  Image  Associative  性能  验证  结果  处理实验  识别  自联想记忆  鲁棒性  结合  混合型  随机噪声  混合噪声  能力  腐蚀  形态联想
文章编号:1006-9348(2007)07-0156-04
修稿时间:2006-06-02

Application of Scale-space Associative Memories in Grayscale Image
RAN Tian-bao,WU Xi-sheng.Application of Scale-space Associative Memories in Grayscale Image[J].Computer Simulation,2007,24(7):156-159.
Authors:RAN Tian-bao  WU Xi-sheng
Affiliation:School of Information Engineering, Southern Yangtze University, Wuxi Jiangsu 214122, China
Abstract:Morphological Associative Memories(MAM) has outstanding capability against dilative or erosive noise,but its ability against general noise is poor.But in practice,random noise is always composed both of dilative and erosive noise.The combination of scale space and Morphological Associative Memories offers a new version of MAM with outstanding capability against dilative or erosive noise,besides its robustness against random noise.Recognition and associative memories tests on grayscale images with random noise have produced desirable results and proved its excellent performance.
Keywords:Scale space  Associative memories  Dilative memory matrix  Erosive memory matrix  Grayscale image
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号