[1]陆宝春,李建文,王婧,等.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,(06):797-800.
 LU Bao-chun,LI Jian-wen,WANG Jing,et al.Feature Difference Based Image Segmentation Algorithm for Fluorescent Magnetic Detection[J].Journal of Nanjing University of Science and Technology,2011,(06):797-800.
点击复制

基于特征差异性的荧光磁粉探伤图像分割算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2011年06期
页码:
797-800
栏目:
出版日期:
2011-12-31

文章信息/Info

Title:
Feature Difference Based Image Segmentation Algorithm for Fluorescent Magnetic Detection
作者:
陆宝春1李建文1王婧1冯毅1李纯健2
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
Author(s):
LU Bao-chun1LI Jian-wen1WANG Jing1FENG Yi1LI Chun-jian2
1. School of Mechanical Engineering,NUST,Nanjing 210094,China; 2. Shengjieda NDT Device Manufacturing Co. ,Ltd. ,Yancheng 224300,China
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
Keywords:
fluorescent magnetic detection image segmentation gradient method threshold method gray feature
分类号:
TG115. 28
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。
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. Gradient features are selected as main segmentation criteria,which makes up the poor generality of simple threshold method. The algorithm is debugged in the VC program integrated with OpenCV. The testing results show: the gradient differences between the target information and the false information are significant; after the false information with high-gradient is removed, the gradient features between the target information and the background information are significant, the target information is easy to be extracted by combining with threshold method.

参考文献/References:

[1] 中国机械工程学会无损检测学会. 磁粉探伤[M]. 北京: 机械工业出版社, 2005.
[2] 陆宝春,李建文,陈吉朋,等. 荧光磁粉探伤自动缺 陷识别方法研究[J]. 南京理工大学学报,2010, 34( 6) : 803-808.
[3] 张强,霍凯. 轴承荧光磁粉探伤自动识别技术的研 究[J]. 现代电子技术, 2009, 32( 7) : 107-110.
[4] Bruce F, Jeff S. Photoshop CS3 camera raw 完全剖析 [M]. 北京: 人民邮电出版社, 2009.
[5] Bakunov A S,Korolev A Y,Kudryavtsev D A, et al. A set of magnetic fluorescent-penetrant inspection[J]. Russian Journal of Nondestructive Testing,2005,41 ( 3) : 170-174.
[6] Rafael C G,Richard E W. Digital image processing [M]. London,England: Prentice Hall, 2006.
[7] 张玉珍,王建宇,戴跃伟. 基于自适应双阈值和主色 率的足球视频镜头的分割[J]. 南京理工大学学报, 2009, 33( 4) : 432-437.
[8] 李峰,徐诚,任国全,等. 基于数学形态学的铁谱磨 粒图像分割研究[J]. 南京理工大学学报,2005, 29( 1) : 70-72.
[9] 陆建峰,杨静宇,叶玉坤. 一个用于彩色肺癌细胞图 像的分割算法[J]. 南京理工大学学报,2000, 24( 6) : 481-485.
[10] Gray B,Adrian K. Learning OpenCV[M]. Frankfort, Germany: O’Reilly Media, Inc, 2009.

相似文献/References:

[1]李敏,罗洪艳,郑小林,等.一种改进的最大类间方差图像分割法[J].南京理工大学学报(自然科学版),2012,36(02):332.
 LI Min,LUO Hong-yan,ZHENG Xiao-lin,et al.Image Segmentation Based on Improved Otsu Algorithm[J].Journal of Nanjing University of Science and Technology,2012,36(06):332.
[2]李 峰*,徐 诚,任国全,等.基于数学形态学的铁谱磨粒图像分割研究[J].南京理工大学学报(自然科学版),2005,(01):70.
 LI Feng,XU Cheng,REN Guo-quan,et al.Image Segmentation of Ferrography Wear Particles Based On Mathematical Morphology[J].Journal of Nanjing University of Science and Technology,2005,(06):70.
[3]娄震,胡钟山,杨静宇.支票自动处理系统中的图像处理及识别[J].南京理工大学学报(自然科学版),1999,(03):85.
 LouZhen HuZhongshan YangJingyu.Applications of Image Processing and Recognition Technology in an Automatic Bankcheck Processing System[J].Journal of Nanjing University of Science and Technology,1999,(06):85.
[4]石澄贤,等.Snakes外力场的改进及其左心室MRI的精确分割[J].南京理工大学学报(自然科学版),2006,(01):76.
 SHI Cheng-xian,WANG Ping- an,et al.Improved External Force Field for Snakes and Accurate Segmentation of Left Ventricle MRI[J].Journal of Nanjing University of Science and Technology,2006,(06):76.
[5]陈沅涛,徐蔚鸿,吴佳英,等.基于增量学习向量SVM方法的图像分割应用[J].南京理工大学学报(自然科学版),2014,38(01):6.
 Chen Yuantao,Xu Weihong,Wu Jiaying,et al.Image segmentation application based on incremental learning vector SVM algorithm[J].Journal of Nanjing University of Science and Technology,2014,38(06):6.
[6]廖传柱,张 旦,江铭炎.基于ABC-PCNN模型的图像分割[J].南京理工大学学报(自然科学版),2014,38(04):558.
 Liao Chuanzhu,Zhang Dan,Jiang Mingyan.Image segmentation based on ABC-PCNN model[J].Journal of Nanjing University of Science and Technology,2014,38(06):558.
[7]郭东岩,赵春霞,李军侠,等.结合图像显著与灰度不一致性的目标自动提取[J].南京理工大学学报(自然科学版),2014,38(05):701.
 Guo Dongyan,Zhao Chunxia,Li Junxia,et al.Image saliency and intensity inhomogeneity based automatic object extraction[J].Journal of Nanjing University of Science and Technology,2014,38(06):701.
[8]王 鑫,胡洋洋,杨慧中.基于迭代腐蚀的粘连细胞图像分割研究[J].南京理工大学学报(自然科学版),2016,40(03):285.[doi:10.14177/j.cnki.32-1397n.2016.40.03.006]
 Wang Xin,Hu Yangyang,Yang Huizhong.Segmentation of adherent cell image based on iterative erosion[J].Journal of Nanjing University of Science and Technology,2016,40(06):285.[doi:10.14177/j.cnki.32-1397n.2016.40.03.006]
[9]许 芹,唐敦兵,蔡祺祥.改进的快速模糊C均值聚类图像分割算法[J].南京理工大学学报(自然科学版),2016,40(03):309.[doi:10.14177/j.cnki.32-1397n.2016.40.03.010]
 Xu Qin,Tang Dunbing,Cai Qixiang.Improved fast fuzzy C-means clustering algorithm for image segmentation[J].Journal of Nanjing University of Science and Technology,2016,40(06):309.[doi:10.14177/j.cnki.32-1397n.2016.40.03.010]
[10]刘晓曼,刘永民.基于分块K-SVD字典学习的彩色图像去噪[J].南京理工大学学报(自然科学版),2016,40(05):607.[doi:10.14177/j.cnki.32-1397n.2016.40.05.017]
 Liu Xiaoman,Liu Yongmin.Color image denoising with block K-SVD dictionary learning[J].Journal of Nanjing University of Science and Technology,2016,40(06):607.[doi:10.14177/j.cnki.32-1397n.2016.40.05.017]
[11]陆宝春,李建文,陈吉朋,等.荧光磁粉探伤自动缺陷识别方法研究[J].南京理工大学学报(自然科学版),2010,(06):803.
 LU Bao-chun,LI Jian-wen,CHEN Ji-peng,et al.Automatic Flaw Recognition Method of Fluorescent Magnetic Detection[J].Journal of Nanjing University of Science and Technology,2010,(06):803.

备注/Memo

备注/Memo:
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) 作者简介: 陆宝春( 1965-) ,男,教授,博士生导师,主要研究方向: 制造系统检测控制、诊断与维护,E-mail: lbcnust@ sina. com。
更新日期/Last Update: 2012-10-25