[1]赵君爱,贾民平.工件表面微小缺陷的检测与识别方法[J].东南大学学报(自然科学版),2014,44(4):735-739.[doi:10.3969/j.issn.1001-0505.2014.04.010]
 Zhao Junai,Jia Minping.Detection and recognition method of small defects in workpiece surface[J].Journal of Southeast University (Natural Science Edition),2014,44(4):735-739.[doi:10.3969/j.issn.1001-0505.2014.04.010]
点击复制

工件表面微小缺陷的检测与识别方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
44
期数:
2014年第4期
页码:
735-739
栏目:
计算机科学与工程
出版日期:
2014-07-16

文章信息/Info

Title:
Detection and recognition method of small defects in workpiece surface
作者:
赵君爱12贾民平1
1东南大学机械工程学院, 南京 211189; 2江苏农林职业技术学院机电工程系, 句容 212400
Author(s):
Zhao Junai12 Jia Minping1
1School of Mechanical Engineering, Southeast University, Nanjing 211189, China
2Department of Mechanical and Electrical Engineering, Jiangsu Polytechnic College of Agriculture and Forestry, Jurong 212400, China
关键词:
中值滤波 微小缺陷分割 缺陷检测 特征提取
Keywords:
median filter small defect segmentation defect detection feature extraction
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2014.04.010
摘要:
针对微小缺陷在复杂背景图像情形下分割难的问题,提出了一种基于像元搜索算法的微小缺陷检测方法.首先采用直方图均衡化提升背景与缺陷目标的对比度,在分析噪声分布特点的基础上,利用基于中值和均值滤波的改进滤波算法对图像进行去噪等前期预处理;然后根据背景灰度分布,在目标分割过程中采用分块、按方差大小排除背景图像块、初定目标和剔除伪目标的缺陷像元搜索算法;最后采用矩形度和区域占空比进行缺陷特征提取.结果表明,对于背景不均匀、目标与背景区分不明显这类复杂背景图像,所提出算法相对于传统的Otsu等算法能够更好地分割出弱小缺陷目标,提高了检测缺陷的准确性.
Abstract:
In order to solve the difficulty of segmenting the small defects from images with a complex background, a new detection method based on the pixel search is proposed. Firstly, histogram equalization is used to enhance the contrast between the target and the background, and an improved filtering algorithm based on median and mean filtering is applied to denoising according to the characteristics of the noise distribution. Then, according to the background gray distribution, a new segment technique based on the pixel search is proposed, which includes four steps: division of the image, exclusion of the background blocks based on the variance, determination of the preliminary defects target and elimination of the fake targets. Finally, the rectangularity and the regional duty ratio are used to extract the defect features. The experimental results show that compared with the traditional Otsu algorithm, this segmenting algorithm can more successfully separate the small defects target from images with complicated background and overlap regions between the target and background, which can improve the accuracy of defect detection.

参考文献/References:

[1] Xia Yong, Feng Dagan, Wang Tianjiao. Image segmentation by clustering of spatial patterns[J]. Pattern Recognition Letters,2007,28(12):1548-1555.
[2] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation[J]. Journal of Electronic Imaging,2004, 13(1):146-165.
[3] 汪国有,邹玉兰, 凌勇.基于显著性Otsu局部递归分割算法[J].华中科技大学学报,2002,30(9):57-59.
  Wang Guoyou, Zou Yulan, Ling Yong. An algorithm for salience-based local recursive Otsu segmentation[J]. Jornal of Huazhong University of Science and Technology, 2002, 30(9): 57-59.(in Chinese)
[4] 何志勇,孙立宁,芮延年.一种微小表面缺陷的机器视觉检测方法[J]. 应用科学学报,2012,30(5):532-538.
  He Zhiyong, Sun Lining, Rui Yannian. Detection of small surface defects based on machine vision[J]. Journal of Application Science, 2012, 30(5):532-538.(in Chinese)
[5] Singh K M. Fuzzy rule based on median filter for gray-scale images[J]. Journal of Information Hiding and Multimedia Signal Processing, 2011, 2(2):108-122.
[6] Wang Z, Zhang D. Progressive switching median filter for the removal of impulse noise from highly corrupted images[J]. IEEE Trans Circuits Sys, 1999, 46(1):78-80.
[7] Li Chunming, Kao Chiu-Yen, Gore John C, et al. Implicit active contours driven by local binary fitting energy[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Minneapolis,USA,2007:1-7.
[8] 樊冬进,孙冰,封举富.基于方差及方差梯度的指纹图像自适应分割算法[J].计算机辅助设计与图形学学报,2008,20(6):742-747.
  Fan Dongjin, Sun Bing, Feng Jufu. Adaptive segmentation based on variance and its gradient[J]. Journal of Computer-Aided Design & Computer Graphics, 2008, 20(6):742-747.(in Chinese)
[9] 刘运龙,薛雨丽,袁素真,等.基于局部均值的红外小目标检测算法[J].红外与激光工程, 2013,42(3):816-825.
  Liu Yunlong, Xue Yuli, Yuan Suzhen, et al. Infrared small targets detection using local mean[J]. Infrared and Laser Engineering, 2013, 42(3):816-825.(in Chinese)
[10] 韩芳芳. 表面缺陷视觉在线检测关键技术研究[D].天津:天津大学精密仪器与光电子工程学院, 2011.

备注/Memo

备注/Memo:
收稿日期: 2013-11-20.
作者简介: 赵君爱(1980—),女,博士生,讲师;贾民平(联系人),男,博士,教授,博士生导师,mpjia@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(51075070).
引用本文: 赵君爱,贾民平.工件表面微小缺陷的检测与识别方法[J].东南大学学报:自然科学版,2014,44(4):735-739. [doi:10.3969/j.issn.1001-0505.2014.04.010]
更新日期/Last Update: 2014-07-20