Defect Detection by Combination of Threshold and Multistep Watershed Techniques

Springer Science and Business Media LLC - Tập 56 - Trang 80-91 - 2020
M. R. Mohebbifar1, K. Omarmeli2
1Department of Physics, Faculty of Science, Malayer University, Malayer, Iran
2Department of Physics, University of Tarbiat Modares, Tehran, Iran

Tóm tắt

In this work proposes a technique to detect some types of defects based on the radiography method. Inspection tests include two categories, destructive and nondestructive. One of the nondestructive tests is radiographic test that is used to detect internal defect. In addition, the image processing methods are used to improve defect detection in the radiographic images. The watershed technique is one of the segmentation methods that used to analyze images based on needed information. The proposed method in this paper is combination threshold and multistage watershed technique that applies to detect some of welding defects such as lack of fusion, wormholes, incomplete filled groove, and incomplete penetration. Otsu’s threshold leads to an increase in the contrast of the image and then multistep watershed transformation used to detect discontinuities and defect welding.

Tài liệu tham khảo

Development of Protocols for Corrosion and Deposits Evaluation in Pipes by Radiography, Vienna: IAEA, 2005.

Brown, B.H., Medical impedance tomography and process impedance tomography: a brief review, Meas. Sci. Technol., 2001, vol. 12, pp. 991–996.

Baumbach, H., Cioclov, D., Kraus, S., and Schmitz, V., Non-destructive testing and quality management technology, Law Insur., 1998, no. 3(3), p. 191–195.

da Silva, R.R., Pattern recognition of weld defects detected by radiographic test, NDT&E Int., 2004, vol. 37, no. 2, pp. 461–470.

Shaffek, H.I., Automation inspection of gas pipeline welding defects using an expert vision system, NDT&E Int., 2004, vol. 37, no. 2, pp. 301–307.

Ravanbod, H., Application of neuro fuzzy technique in pipeline ultrasonic non-destructive testing, NDT&E Int., 2005, vol. 3, no. 1, pp. 643–653.

Basak, D., Non-destructive evaluation of drive ropes: a case study, Nondestr. Test. Eval., 2005, vol. 20, no. 4, pp. 221–229.

McNab, D., An intelligent approach to inspection qualification, NDT&E Int., 2005, vol. 38, no. 2, pp. 97–105.

Alaknanda, Kumar, P., and Anand, R.S., Flaw detection in radiographic weld images using morphological approach, NDT&E Int., 2006, vol. 39, no. 1, pp. 29–33.

Mirapixe, J., Real-time arc welding defect detection technique by means of plasma spectrum optical analysis, 2007, NDT&E Int., vol. 39, no. 2, pp. 356–360.

Carvalho, A.A., MFL signal and artificial neural network applied to detection and classification of pipe weld defects, NDT&E Int., 2006, vol. 39, no. 8, pp. 661–667.

Cumming, S.R., Boyd, A.J., and Ferraro, C.C., Tensile strength pre-diction in concrete using nondestructive testing techniques, Res. Nondestr. Eval., 2006, vol. 17, no. 4, pp. 205–222.

Saguy, H., Flaw detection in metals by ACPD technique: theory and experiment, NDT&E Int., 2007, vol. 40, no. 2, pp. 505–509.

Ferraro, C.C., Boyd, A.J., and Hamilton, H.R., III, Detection and assessment of structural flaws in concrete bridges with NDT methods, Res. Nondestr. Eval., 2007, vol. 18, no. 3, pp. 179–192.

Duan Hu-Shi, Research on segmentation and distribution features of small defects, NDT&E Int., 2007, vol. 40, no. 1, pp. 397–404.

Ying Yin, Feature extraction and optimization of X-ray weld image classification, in 17th World Conf. Nondestr. Test., Shanghai, China, October 25–28, 2008.

Yan Wang, Detection of line weld defects based on multiple threshold and support vector machine, NDT&E Int., 2008, vol. 41, no. 1, pp. 517–524.

Alaknanda, Kumar, P., and Anand, R.S., Flaw detection in radiographic weld images using morphological watershed segmentation techniques, NDT&E Int., 2009, vol. 42, no. 1, pp. 2–8.

Vilar, R. and Zapata, J., An automatic system of classification of weld defects in radiographic images, NDT&E Int., 2009, vol. 42, no. 5, pp. 467–476.

Nanditha, N.M. and Manoharan, N., Comparative study on the suitability of feature extraction techniques for tungsten inclusion and hotspot detection from weld thermographs for online weld monitoring, Int. J. Eng. Mater. Sci., 2010, vol. 17, pp. 20–26.

Zapata, R.V.J., An automatic system of classification of weld defects in radiographic images, NDT&E Int., 2009, vol. 42, no. 5, pp. 467–476.

Valavanis, I. and Kosmopoulos, D., Multiclass defect detection and classification in weld radiographic images using geometric and texture features, Expert Syst. Appl., 2010, vol. 37, no. 12, pp. 7606–7614.

Rathod, V.R. and Anand, R.S., A Comparative Evaluation of Different Segmentation Techniques to Detect Flaws in Weldments Radiographically, Roorkee, India: Dep. Electr. Eng., Indian Inst. Technol., 2011.

Rathod, V.R. and Anand, R.S., A Comparative Study of Different Segmentation Techniques for Detection of Flaws in NDEWeld Images, Roorkee, India: Dep. Electr. Eng., Indian Inst. Technol., 2012.

Otsu, N., A threshold selection method from gray level histograms, in IEEE Trans. Syst. Man Cybern.SMC-9, 1979, pp. 62–66.

Velasco, F.R.D., Thresholding using the Isodata clustering algorithm, in IEEE Trans. Syst. Man Cybern.SMC-10, 1980, pp. 771–774.

Maldonado-Bascón, S., Acevedo-Rodríguez, J., Arroyo, S.L., Fernández-Caballero, A., and López-Ferreras, F., “An optimization on pictogram identification for the road-sign recognition task using SVMs, in Comput.Vision Image Understanding, 2010, pp.373–383.

Roerdink, J.B.T.M. and Meijster, A., The watershed transform: definitions, algorithms and parallelisation, Fundamenta Informaticae, 2000, vol. 41, pp. 187–228.

Bienick, A. and Moga, A., An efficient watershed algorithm based on connected components, Pattern Recogn., 2000, vol. 33, no. 3, pp. 907–916.

Bleau, A. and Leon, L.J., Watershed-based segmentation and region-merging, Comput. Vision Image Understanding, 2000, vol. 77, pp. 317–370.

Gonzalez, R.C. and Woods, R.E., Digital Image Processing. Instructor’s Manual Version 3.0, 2008, 3rd ed.

Marr, D. and Hilseth, E.C., Theory of edge detection, Proc. R. Soc. London, 1980, vol., B270, pp. 187–217.

Henstock, P.V. and Chelberg, D.M., Automatic gradient threshold determination for edge detection, IEEE Trans. Image Process., 1996, vol. 5, no. 5, pp. 784–787.

Canny, J., A computational approach to edge detection, IEEE Trans. Pattern Anal. Mach. Intell., 1986, vol. 8, no. 6.

Alaknanda, Kumar, P., and Anand, R.S., Comparative evaluation of edge detection techniques for feature extraction in ultrasound NDT images, in Proc. Int. Conf. ICSCI-2004, NISTET, Hyderabad, India, February 12–15, 2004, pp. 337–341.

Henstock, P.V. and Chelberg, D.M., Automatic gradient threshold determination for edge detection, IEEE Trans. Image Process., 1996, vol. 5, no. 5, pp. 784–787.

Gonzalez, R.C., Woods, R.E., and Eddins, S.L., Digital Image Processing Using MATLAB, 2009, 2nd ed.

MATLAB Software, Database Toolbox™, User’s Guide, R2011b.

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Tập 56

80-91

Thông tin tác giả