引用本文: | 瞿继双,王正志,王超.一种新的模糊多层自组织神经网络图像目标检测方法[J].国防科技大学学报,2002,24(6):46-51.[点击复制] |
QU Jishuang,WANG Zhengzhi,WANG Chao.A Novel Target Detection Approach in Images by Fuzzy Multilayer Self-organizing Neural Netwok[J].Journal of National University of Defense Technology,2002,24(6):46-51[点击复制] |
|
|
|
本文已被:浏览 5571次 下载 4504次 |
一种新的模糊多层自组织神经网络图像目标检测方法 |
瞿继双1,2, 王正志1, 王超2 |
(1.国防科技大学 机电工程与自动化学院,湖南 长沙 410073;2.中国科学院遥感应用研究所,北京 100101)
|
摘要: |
神经网络方法和模糊集理论用于图像处理和目标检测时各有优势,文中提出了一种将神经网络和模糊集理论集成的混合方法,即模糊多层自组织神经网络法。该方法将模糊测度作为神经网络的目标函数,网络包括多层结构,任一层中的一个神经元对应图像中的一个像素,该神经元只与前一层的对应元素及其邻域元素连接。针对遥感图像的实验处理过程证明该方法能够有效地进行目标检测和提取,并且具有良好的噪声免疫力。 |
关键词: 多层感知器 目标函数 模糊测度 自组织 |
DOI: |
投稿日期:2002-06-03 |
基金项目:中科院知识创新工程资助项目;“十五”国家高技术研究发展计划资助(863-701) |
|
A Novel Target Detection Approach in Images by Fuzzy Multilayer Self-organizing Neural Netwok |
QU Jishuang1,2, WANG Zhengzhi1, WANG Chao2 |
(1.College of Mechatronics Engineering and Automation,National Univ. of Defense Technology, Changsha 410073, China;2.Institute of Remote Sensing Application,CAS,Beijing 100101,China)
|
Abstract: |
There are respective advantages for image processing and target detection by neural network methods of fuzzy set theory methods.The paper proposes a hybrid approach by combining the two type methods,namely,Fuzzy Multilayer Self-Organizing Map(FMSOM),which utilizes fuzziness measure as objective function of neural network.The network comprises multilayer structure,every neuron in each layer corresponds to pixel of image,which just connects with the corresponding neurons in prior layer and its neighbors.Experiments using remote sensing images as input are executed and the results verify the approach is valid for target detection and extraction,simultaneously,possesses good noise immunity. |
Keywords: multilayer perceptron objective function fuzziness measure self-organizing |
|
|
|
|
|