首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络的纹理图象生成
引用本文:吴小培,周荷琴,冯焕清.基于神经网络的纹理图象生成[J].中国图象图形学报,2000,5(6):484-488.
作者姓名:吴小培  周荷琴  冯焕清
作者单位:中国科学技术大学电子科学与技术系!合肥230026
摘    要:提出了一种利用多层前馈神经网络生成纹理图象的新方法 .利用该方法可方便地生成图案丰富的纹理图象集 ,并且该纹理图象集中的任何一幅图象均唯一地对应一组神经网络的权值和阈值 ,因此不仅便于图象保存 ,还大大地节省了图象存储空间 .

关 键 词:神经网络  纹理图象  BP算法  图象处理  纹理综合
收稿时间:1/7/1999 12:00:00 AM
修稿时间:1999-01-07

The Texture Image Generation Based on Neural Network
WU Xiao-pei,ZHOU He-qin and FENG Huan-qing.The Texture Image Generation Based on Neural Network[J].Journal of Image and Graphics,2000,5(6):484-488.
Authors:WU Xiao-pei  ZHOU He-qin and FENG Huan-qing
Affiliation:Department of Electronic Science and Technology,USTC,Hefei 230026;Department of Electronic Science and Technology,USTC,Hefei 230026;Department of Electronic Science and Technology,USTC,Hefei 230026
Abstract:In this paper, a new method to generate the texture image by use of Multi layer feed forward neural network is presented. This method can be used conveniently to generate different kinds of texture image sets. Each image in texture image sets corresponds to a group of definite weights and thresholds of neural network. This characteristic of the method is very useful for image's saving and then a lot of storage space can be saved.
Keywords:Multilayer feed  forward neural network  Texture image  BP algorithm
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
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