基于二维信息熵图像分割的缺陷识别方法

迟大钊; 刚铁

基于二维信息熵图像分割的缺陷识别方法

迟大钊,
刚铁

哈尔滨工业大学先进焊接与连接国家重点实验室, 哈尔滨 150001

基金项目: 国家自然科学基金资助项目（51375002，51005056）；黑龙江省博士后科研启动基金资助项目（LBH-Q13079）

计量
- 文章访问数: 417
- HTML全文浏览量: 6
- PDF下载量: 209
出版历程
- 收稿日期: 2016-06-03

Defect detection method based on 2D entropy image segmentation

State Key Laboratory of Advanced Welding and Joining, Harbin Institute of Technology, Harbin 150001, China

摘要

摘要: 为了提高无损检测的工作效率及可靠性，研究超声图像中缺陷目标的自动识别方法.根据超声D扫描图像的特征，在背景杂波抑制及噪声抑制的基础上，采用基于KSW二维信息熵的阈值分割方法对图像进行二值化处理.结果表明，由于不能兼顾图像各处的细节信息，基于二维信息熵的全局阈值图像二值化方法会产生欠分割.当图像尺寸较大时，全局阈值方法会丢失许多像元数目不多的集群，造成小目标的漏检.基于二维信息熵的局部阈值法充分考虑了图像的局部区域特征，能有效地识别图像中的缺陷目标，从而提高缺陷检出率.
- 超声检测 /
- 缺陷识别 /
- 二维信息熵 /
- 图像分割
Abstract: In order to improve the work efficiency of non-destructive testing (NDT) and the reliability of NDT results, an automatic method to detect defects in ultrasonic image was researched. According to the characterization of ultrasonic D-scan image, clutter wave suppression and de-noising were presented firstly. Then, the image is processedby binaryzation using KSW 2D entropy based image segmentation method. The results show that, the global threshold based segmentation method is somewhat ineffective for D-scan image because of under-segmentation. Especially when the image is bigger in size, small targets which are composed by a small amount of pixels are often undetected. Whereas, local threshold based image segmentation method is effective in recognizing small defects because it takes local image character into account.
- ultrasonic testing /
- defect detection /
- 2D entropy /
- image segmentation

HTML全文

参考文献(7)

[1]	梁硼, 魏艳红, 占小红. 基于B样条曲线的X射线图像焊缝缺陷分割与提取[J]. 焊接学报, 2012, 33(7):109-112. Liang Peng, Wei Yanhong, Zhan Xiaohong. Weld defect segmentation and extraction of X-ray image based on B-spline curve[J]. Transactions of the China Welding Institution, 2012, 33(7):109-112.
[2]	高炜欣, 胡玉衡, 穆向阳, 等. 基于聚类的埋弧焊X射线焊缝图像缺陷分割算法及缺陷模型[J]. 焊接学报, 2012, 33(4):37-41. Gao Weixin, Hu Yuheng, Mu Xiangyang, et al. Study on sub-arc X-ray welding image defect segmentation algorithm and defect model[J]. Transactions of the China Welding Institution, 2012, 33(4):37-41.
[3]	Kechida A, DraiR, Khelil M. 2D Gabor functions and FCMI algorithm for flaws detection in ultrasonic images[J]. Transactions on engineering, computing and technology, 2005, (9):1305-5313.
[4]	KapurJ N, Sahoo P K, Wong A K C. New method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing, 1985, 29(3):273-285.
[5]	MarianoR, Omar O, Marroquin J L. Entropy-controlled quadratic Markov measure field models for efficient image segmentation[J]. IEEE Transactions on Image Processing, 2007, 16(12):3047-3057.
[6]	迟大钊, 刚铁, 孙昌立. 基于自适应滤波的超声杂波抑制方法[J]. 焊接学报, 2015, 36(11):33-36. Chi Dazhao, Gang Tie, Sun Changli. An ultrasonic clutter suppression method using adaptive filter[J]. Transactions of the China Welding Institution, 2015, 36(11):33-36.
[7]	迟大钊, 刚铁, 姚英学. 基于非线性小波收缩的超声检测缺陷信号识别方法[J]. 机械工程学报, 2011, 47(18):1-6. Chi Dazhao, Gang Tie, Yao Yingxue. Non-linear wavelet shrinkage based method for defect detection in ultrasonic signal[J]. Journal of Mechanical Engineering, 2011, 47(18):1-6.

施引文献

资源附件(0)

计量

文章访问数: 417
HTML全文浏览量: 6
PDF下载量: 209
被引次数: 0

基于二维信息熵图像分割的缺陷识别方法

计量

出版历程

Defect detection method based on 2D entropy image segmentation

计量

出版历程

目录