您的位置:首页  > 论文页面

结合形态学和SOM神经网络的煤岩图像裂缝检测

发表时间:2014-08-31  浏览量:1738  下载量:428
全部作者: 凡宝荣,张伟,李朝锋,琚宜文
作者单位: 江南大学物联网工程学院;中国科学院大学地球科学学院,计算地球动力学重点实验室
摘 要: 为准确检测出煤岩图像的裂缝边缘,提出一种结合多结构元形态学边缘检测和自组织映射(self-organizing map,SOM)神经网络分类的煤岩图像裂缝检测方法。首先,用多结构元形态学边缘检测算法提取出煤岩图像的所有边缘;然后,计算出边缘的特征参数作为SOM神经网络的输入参数;最后,利用SOM神经网络分类算法,将裂缝边缘和非裂缝边缘区分开,最终得到煤岩图像的裂缝检测图像。实验证明,该算法可以有效地提取出图像中的煤岩裂缝边缘信息。
关 键 词: 计算机应用;裂缝检测;数学形态学;自组织映射分类
Title: Fracture detection of coal rock image based on morphology and SOM neural network
Author: FAN Baorong, ZHANG Wei, LI Chaofeng, JU Yiwen
Organization: School of Internet of Things Engineering, Jiangnan University; Key Laboratory of Computational Geodynamics, College of Earth Science, University of Chinese Academy of Sciences
Abstract: In order to detect the fracture of the coal rock image, a method of combing multi-structure elements morphology with self-organizing map (SOM) neural network clustering is presented in this paper. Firstly, multi-structure elements morphology is used to detect the edges of the coal rock image, and then the feature parameters of edges are calculated as the inputs of SOM neural network. Finally, the fracture edges and the non-fracture edges are classified by the SOM neural network clustering algorithm, and the fracture edges of image are gained. Experimental results show that this new method can effectively detect and extract the fracture information of coal rock image.
Key words: computer application; fracture detection; mathematical morphology; self-organizing map clustering
发表期数: 2014年8月第16期
引用格式: 凡宝荣,张伟,李朝锋,等. 结合形态学和SOM神经网络的煤岩图像裂缝检测[J]. 中国科技论文在线精品论文,2014,7(16):1657-1663.
 
0 评论数 0
暂无评论
友情链接