基于神经网络的纹理图象生成

吴小培; 周荷琴; 冯焕清

doi:10.11834/jig.20000608

学术论文与技术报告 | 浏览量 : 0 下载量: 140 CSCD: 0

PDF
导出
分享
收藏
专辑

基于神经网络的纹理图象生成
The Texture Image Generation Based on Neural Network
2000年5卷第6期页码：484
纸质出版：2000
DOI： 10.11834/jig.20000608
稿件说明：

移动端阅览

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. DOI： 10.11834/jig.20000608.

The Texture Image Generation Based on Neural Network[J]. Journal of Image and Graphics, 2000, 5(6): 484. DOI： 10.11834/jig.20000608.

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.

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.