| 基于特征差异性的荧光磁粉探伤图像分割算法 |
| |
| 引用本文： | 陆宝春,李建文,王婧,冯毅,李纯健.基于特征差异性的荧光磁粉探伤图像分割算法[J].南京理工大学学报(自然科学版),2011,35(6). |
| |
| 作者姓名： | 陆宝春 李建文 王婧 冯毅 李纯健 |
| |
| 作者单位： | 1. 南京理工大学机械工程学院,江苏南京,210094
2. 盛捷达探伤设备制造有限公司,江苏盐城,224300 |
| |
| 基金项目： | 国家科技型中小企业技术创新基金(09C26213203712); 国家大学生创新性实验计划(101022802) |
| |
| 摘 要： | 为实现目标信息与伪信息的有效分割,提出一种融合了梯度法与阈值法的荧光磁粉探伤图像分割算法.以荧光磁粉图像中目标信息与伪信息的梯度特征差异为主要判据,设计了图像分割算法.滤除与目标信息的灰度特征最接近的伪信息,结合阈值法提取目标信息.主要选取梯度特征为分割判据,有效弥补了纯阈值法通用性差的缺陷.在集成了OpenCV的VC环境下进行了算法调试实验,结果显示:目标信息与伪信息的梯度特征差异显著,去除高梯度值的伪信息后,目标信息与背景信息的灰度特征差异明显,结合阈值法可以实现准确提取.
|
| 关 键 词： | 荧光磁粉探伤 图像分割 梯度特征差异法 阈值法 灰度特征 |
Feature Difference Based Image Segmentation Algorithm for Fluorescent Magnetic Detection |
| |
| LU Bao-chun
,
LI Jian-wen
,
WANG Jing
,
FENG Yi
,
LI Chun-jian.Feature Difference Based Image Segmentation Algorithm for Fluorescent Magnetic Detection[J].Journal of Nanjing University of Science and Technology(Nature Science),2011,35(6). |
| |
| Authors: | LU Bao-chun LI Jian-wen WANG Jing FENG Yi LI Chun-jian |
| |
| Affiliation: | LU Bao-chun1,LI Jian-wen1,WANG Jing1,FENG Yi1,LI Chun-jian2(1.School of Mechanical Engineering,NUST,Nanjing 210094,China,2.Shengjieda NDT Device Manufacturing Co.,Ltd.,Yancheng 224300,China) |
| |
| Abstract: | To segment false information and target information efficiently,a new image segmentation algorithm for fluorescent magnetic detection is proposed based on gradient method and threshold method.The image segmentation algorithm is designed by taking the gradient differences between target information and false information as the main criterion.The information most close to the target information on gray feature is filtered out,and the target information is extracted by combining with the threshold method.Gradi... |
| |
| Keywords: | fluorescent magnetic detection image segmentation gradient method threshold method gray feature |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
