| 细胞神经网络图像恢复新方法的研究 |
| |
| 引用本文： | 汪海明,赵建业,程承旗,余道衡. 细胞神经网络图像恢复新方法的研究[J]. 计算机工程与应用, 2003, 39(8): 4-6 |
| |
| 作者姓名： | 汪海明 赵建业 程承旗 余道衡 |
| |
| 作者单位： | 1. 北京大学电子学系视觉与听觉信息处理国家重点实验室,北京,100871
2. 北京大学遥感与地理信息系统研究所,北京,100871 |
| |
| 基金项目： | 国家863高技术研究发展计划项目资助课题(编号:2002AA783060) |
| |
| 摘 要： | 结合二维细胞自动机(CA)和细胞神经网络通用二进制神经元(CNN-UBN)设计了两种新的用于噪声图像恢复的细胞神经网络(CNN)。这两种网络的联合处理图像结果明显优于长度为3和5的普通中值滤波恢复方法,且具有速度快、结构简单、易于硬件集成等优点,是一种新颖实用的图像恢复算法。
|
| 关 键 词： | 细胞自动机 细胞神经网络 图像恢复 |
| 文章编号： | 1002-8331-(2003)08-0004-03 |
| 修稿时间： | 2002-11-01 |
A New Approach for Image Restoring Based on CNN |
| |
| Wang Haiming Zhao Jianye Cheng Chengqi Yu Daoheng. A New Approach for Image Restoring Based on CNN[J]. Computer Engineering and Applications, 2003, 39(8): 4-6 |
| |
| Authors: | Wang Haiming Zhao Jianye Cheng Chengqi Yu Daoheng |
| |
| Affiliation: | Wang Haiming 1 Zhao Jianye 1 Cheng Chengqi 2 Yu Daoheng 11 |
| |
| Abstract: | In this paper,two new kind of CNN are designed with two-dimensional Cellular Automata(CA)and CNN U-niversal Binary neuron(CNN-UBN),which can implement image restoring.The processing results of two algorithms are better than that of median filter whose length is3and5obviously.Furthermore,it has many advantages,such as,high-speed processing,simple structure and easy integration and so on.It is a novel and effective algorithm. |
| |
| Keywords: | Cellular Automata(CA) Cellular neural network(CNN) Image restoring |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
