Lossy image compression using a modular structured neural network

被引:4
|
作者
Watanabe, E [1 ]
Mori, K [1 ]
机构
[1] Konan Univ, Fac Sci & Engn, Dept Informat Sci & Syst Engn, Kobe, Hyogo 6588501, Japan
关键词
D O I
10.1109/NNSP.2001.943144
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A lossy compression method for gray images is proposed on the basis of a modular structured neural network. This modular structured neural network consists of multiple neural networks with different block sizes (the numbers of input units) for the region segmentation. By the region segmentation procedure, each neural network is assigned to each region such as the edge or the flat region. From simulation results it is shown that the proposed compression method gives better compression performance compared with the conventional compression method using a single neural network.
引用
收藏
页码:403 / 412
页数:10
相关论文
共 50 条