Journal of the Korean institute of surface engineering (한국표면공학회지)

The Korean Institute of Surface Engineering (한국표면공학회)
권호 표지
DOI QR코드

DOI QR Code

Trends in image processing techniques applied to corrosion detection and analysis

부식 검출과 분석에 적용한 영상 처리 기술 동향

  • Beomsoo Kim (Department of Mechanical System Engineering, Gyeongsang National University) ;
  • Jaesung Kwon (Department of Mechanical System Engineering, Gyeongsang National University) ;
  • Jeonghyeon Yang (Department of Mechanical System Engineering, Gyeongsang National University)
  • 김범수 (경상국립대학교 기계시스템공학과) ;
  • 권재성 (경상국립대학교 기계시스템공학과) ;
  • 양정현 (경상국립대학교 기계시스템공학과)
  • Received : 2023.11.13
  • Accepted : 2023.12.01
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Corrosion detection and analysis is a very important topic in reducing costs and preventing disasters. Recently, image processing techniques have been widely applied to corrosion identification and analysis. In this work, we briefly introduces traditional image processing techniques and machine learning algorithms applied to detect or analyze corrosion in various fields. Recently, machine learning, especially CNN-based algorithms, have been widely applied to corrosion detection. Additionally, research on applying machine learning to region segmentation is very actively underway. The corrosion is reddish and brown in color and has a very irregular shape, so a combination of techniques that consider color and texture, various mathematical techniques, and machine learning algorithms are used to detect and analyze corrosion. We present examples of the application of traditional image processing techniques and machine learning to corrosion detection and analysis.

Keywords

References

  1. M. Komary, S. Komarizadehasl, N. Tooic, I. Segura, J.A. Lozano-Galant, J. Turmo, Low-cost technologies used in corrosion monitoring, Sensors, 23 (2023) 1309.
  2. A. R. M. Forkan, Y. B. Kang, P. P. Jayaraman, K. Liao, R. Kaul, G. Morgan, S. Sinha, Corrdetector: A framework for structural corrosion detection from drone images using ensemble deep learning, Expert Systems with Applications, 193 (2022) 116461.
  3. N. N. Almanza-Ortega, J. M. Flores-Vazquez, H. Martinez-Anorve, J. Perez-Ortega, J. C. Zavala-Diaz, A. Mexicano-Santoyo, J. C. Carmona-Fraustro, Corrosion analysis through an adaptive preprocessing strategy using the K-means algorithm, Procedia Computer Science, 219 (2023) 586-595.
  4. M. A. Jayaram, M. A, Computer vision applications in construction material and structural health monitoring: A scoping review, Materials Today: Proceedings (2023).
  5. M. S. B. Reddy, D. Ponnamma, K. K. Sadasivuni, S. Aich, S. Kailasa, H. Parangusan, R. Zarandah, Sensors in advancing the capabilities of corrosion detection: A review, Sensors and Actuators A: Physical, 332 (2021) 113086.
  6. H. Zhu, H. Luo, D. Ai, C. Wang, Mechanical impedance-based technique for steel structural corrosion damage detection, Measurement, 88 (2016) 353-359. https://doi.org/10.1016/j.measurement.2016.01.041
  7. S. Sharma, A. Mukherjee, Ultrasonic guided waves for monitoring corrosion in submerged plates, Struct Control Health Monit, 22 (2015) 19-35. https://doi.org/10.1002/stc.1657
  8. S. Doshvarpassand, C. Wu, X. Wang, X, An overview of corrosion defect characterization using active infrared thermography, Infrared Physics and Technology, 96 (2019) 366-389. https://doi.org/10.1016/j.infrared.2018.12.006
  9. M. Enikeev, I. Gubaydullin, M. Maleeva, Analysis of corrosion process development on metals by means of computer vision, Engineering Journal, 21 (2017) 183-192.
  10. H. S. Munawar, F. Ullah, D. Shahzad, A. Heravi, S. Qayyum, J. Akram, Civil infrastructure damage and corrosion detection: An application of machine learning, Buildings, 12 (2022) 156.
  11. Q. Chen, X. Wen, S. Lu, D. Sun, Corrosion detection for large steel structure base on uav integrated with image processing system, IOP Conference Series: Materials Science and Engineering, 608 (2019) 012020.
  12. M. Khayatazad, L. De Pue, W. De Waele, Detection of corrosion on steel structures using automated image processing, Developments in the Built Environment, 3 (2020) 100022.
  13. X. Lv, F. Duan, J.J. Jiang, X. Fu, L. Gan, Deep metallic surface defect detection: The new benchmark and detection network, Sensors, 20 (2020) 1562.
  14. S. Doshvarpassand, C. Wu, X. Wang, An overview of corrosion defect characterization using active infrared thermography, Infrared Physics and Technology, 96 (2019) 366-389. https://doi.org/10.1016/j.infrared.2018.12.006
  15. S. K. Ahuja, M. K. Shukla, A survey of computer vision based corrosion detection approaches, ICTIS, 2 (2018) 55-63. https://doi.org/10.1007/978-3-319-63645-0_6
  16. H. Jia, G. Qiao, P. Han, Machine learning algorithms in the environmental corrosion evaluation of reinforced concrete structures-A review, Cement and Concrete Composites, (2022) 104725.
  17. M. M. H. Imran, S. Jamaludin, A. F. M. Ayob, A. A. I. Ali, S. Z. A. S. Ahmad, M. F. A. Akhbar, S. B. Mohamed, Application of artificial intelligence in marine corrosion prediction and detection, Journal of Marine Science and Engineering, 11 (2023) 256.
  18. Z. Lin, W. Zhang, J. Li, J. Yang, B. Han, P. Xie, Application of artificial intelligence (AI) in the area of corrosion protection, Anti-Corrosion Methods and Materials, 70 (2023) 243-251.
  19. P. H. Chen, L. M. Chang, Artificial intelligence application to bridge painting assessment, Automation in Construction, 12 (2003) 431-445. https://doi.org/10.1016/S0926-5805(03)00016-5
  20. Z. Bahrami, R. Zhang, R. Rayhana, T. Wang, Z. Liu, Optimized deep neural network architectures with anchor box optimization for shipping container corrosion inspection, IEEE Symposium Series on Computational IntelligenceComput Intell, (2020) 1328-1333.
  21. F. N. Medeiros, G. L. Ramalho, M. P. Bento, L. C. Medeiros, On the evaluation of texture and color features for nondestructive corrosion detection, EURASIP Journal on Advances in Signal Processing, (2010) 1-7.
  22. D. Vriesman, A. B. Junior, A. Zimmer, A. L. Koerich, Texture CNN for thermoelectric metal pipe image classification, International Conference on Tools for Artificial Intelligence, (2019) 569-574.
  23. D. Haitz, P. Hubner, M. Ulrich, S. Landgraf, B. Jutzi, Semantic segmentation with small training datasets: a case study for corrosion detection on the surface of industrial objects, Image Processing Forum, (2022) 73-85.
  24. J. A. I. Diaz, M. I. Ligeralde, J. A. C. Jose, A. A. Bandala, Rust detection using image processing via Matlab, TENCON 2017 - 2017 IEEE Region 10 Conference, (2017) 1327-1331.
  25. D. Haitz, P. Hubner, M. Ulrich, B. Jutzi, A comparison of learning-based approaches for the corrosion detection on barrels in industrial applications, tm - Technisches Messen, (2023).
  26. M. Khayatazad, M. Honhon, W. De Waele, Detection of corrosion on steel structures using an artificial neural network, Struct. Infrastruct. Eng., 19 (2023) 1860-1871.
  27. W. A. Mustafa, M. M. M Abdul Kader, A review of histogram equalization techniques in image enhancement application, Journal of Physics: Conference Series, 1019 (2018) 012026.
  28. A. K. Aijazi, L. Malaterre, M. L. Tazir, L. Trassoudaine, P. Checchin, Detecting and analyzing corrosion spots on the hull of large marine vessels using colored 3D lidar point clouds, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 3 (2016) 153-160. https://doi.org/10.5194/isprsannals-III-3-153-2016
  29. H. K. Shen, P. H. Chen, L. M. Chang, Automated steel bridge coating rust defect recognition method based on color and texture feature, Automation in Construction, 31 (2013) 338-356. https://doi.org/10.1016/j.autcon.2012.11.003
  30. V. Bondada, D. K. Pratihar, C. S. Kumar, Detection and quantitative assessment of corrosion on pipelines through image analysis, Procedia Computer Science, 133 (2018) 804-811. https://doi.org/10.1016/j.procs.2018.07.115
  31. R. Sun, T. Lei, Q. Chen, Z. Wang, X. Du, W. Zhao, A. K. Nandi, Survey of image edge detection, Front Signal Process, 2, (2022) 826967.
  32. C. Rother, V. Kolmogorov, A. Blake, "GrabCut" interactive foreground extraction using iterated graph cuts, ACM Transactions on Graphics, 23 (2004) 309- 314. https://doi.org/10.1145/1015706.1015720
  33. N. D. Hoang, V. D. Tran, Image processing-based detection of pipe corrosion using texture analysis and metaheuristic-optimized machine learning approach, Computational Intelligence and Neuroscience, 8097213 (2019) 1-13.
  34. S. Beucher, F. Meyer, The morphological approach to segmentation: the watershed transformation, Mathematical Morphology in Image Processing, 34 (1993) 49.
  35. M. M. H. Imran, S. Jamaludin, A. F. M. Ayob, A. A. I. M Ali, S. Z. A.S . Ahmad, M. F. A. Akhbar, S. B Mohamed, Application of artificial intelligence in marine corrosion prediction and detection, Journal of Marine Science and Engineering, 11 (2023) 256.
  36. S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz, D. Terzopoulos, Image segmentation using deep learning: A survey, IEEE Trans Pattern Anal Mach Intell, 44 (2021) 3523-3542.
  37. K. P. Sinaga, M. S. Yang, Unsupervised K-means clustering algorithm, IEEE access, 8 (2020) 80716-80727. https://doi.org/10.1109/ACCESS.2020.2988796
  38. B. Kim, J. Kwon, S. Choi, J. Noh, K. Lee, J. Yang. Corrosion Image Monitoring of steel plate by using k-means clustering, Journal of the Korean Society of Surface Science and Engineering, 54 (2021) 278-284.
  39. K. Khan, S. U. Rehman, K. Aziz, S. Fong, S. Sarasvady, DBSCAN: Past, present and future, The International Conference on The Applications of Digital Information and Web Technologies, (2014) 232-238.
  40. B. Kim, Y. Kim, K. Lee, J. Yang, Corrosion image analysis on galvanized steel by using superpixel DBSCAN clustering algorithm, Journal of the Korean Society of Surface Science and Engineering, 55 (2022) 164-172.
  41. M. Trujillo, M. Sadki, Fuzzy C-means classification for corrosion evolution of steel images, In Image Processing: Algorithms and Systems III, 5298, (2004) 318-327.
  42. B. E. Boser, I. M. Guyon, V. N. Vapnik, A training algorithm for optimal margin classifiers, Proceedings of the fifth annual workshop on Computational learning theory, (1992) 144-152.
  43. P. H. Chen, H. K. Shen, C. Y. Lei, L. M. Chang, Support-vector-machine-based method for automated steel bridge rust assessment, Automation in Construction, 23 (2012) 9-19. https://doi.org/10.1016/j.autcon.2011.12.001
  44. L. B. Soares, P. J. Evald, E. A. D. Evangelista, P. L. J. Drews-Jr, S. S. D. C. Botelho, R. I. Machado, An autonomous inspection method for pitting detection using deep learning, 2023 INDIN - 21st IEEE International Conference on Industrial Informatics, (2023) 1-6.
  45. G. Sanchez, W. Aperador, A. Ceron, Corrosion grade classification: a machine learning approach, Indian Institute of Chemical Engineers, 62 (2020) 277-286. https://doi.org/10.1080/00194506.2019.1675539
  46. N. A. Ibraheem, M. M. Hasan, R. Z. Khan, P. K. Mishra, Understanding color models: a review, ARPN Journal of science and technology, 2 (2012) 265-275.
  47. E. Chavolla, D. Zaldivar, E. Cuevas, M. A. Perez, Color spaces advantages and disadvantages in image color clustering segmentation, Advances in soft computing and machine learning in image processing, (2018) 3-22.
  48. L. Petricca, T. Moss, G. Figueroa, S. Broen, Corrosion detection using AI: a comparison of standard computer vision techniques and deep learning model, International Conference on Computer Science, Engineering and Information Technology, (2016) 91-99.
  49. M. W. Schwarz, W. B. Cowan, J. C. Beatty, An experimental comparison of RGB, YIQ, LAB, HSV, and opponent color models, ACM Transactions on Graphics, 6 (1987) 123-158. https://doi.org/10.1145/31336.31338
  50. K. Leon, D. Mery, F. Pedreschi, J. Leon, Color measurement in L*a*b* units from RGB digital images, Food Research International, 39 (2006) 1084-1091.
  51. R. C. Gonzales, P. Wintz, Digital image processing, Addison-Wesley Longman Publishing Co., Inc., (1987).
  52. G. N. Chaple, R. D. Daruwala, M. S. Gofane, Comparisions of Robert, Prewitt, Sobel operator based edge detection methods for real time uses on FPGA, ICTSD-2015, (2015) 1-4.
  53. J. Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 6 (1986) 679-698. https://doi.org/10.1109/TPAMI.1986.4767851
  54. S. R. Gunn, On the discrete representation of the Laplacian of Gaussian, Pattern Recognit, 32 (1999) 1463-1472.
  55. V. Torre, T. A. Poggio, On edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2 (1986) 147-163. https://doi.org/10.1109/TPAMI.1986.4767769
  56. R. K.Ranjan, T. Gylati, Condition assessment of metallic objects using edge detection, International Journal of Advanced Research in Computer Science and Software Engineering, 4 (2014) 253-258.
  57. B. Kim, Y. Kim, J. Yang, Detection of corrosion on steel plate by using Image Segmentation Method, Journal of the Korean Society of Surface Science and Engineering, 54 (2021) 84-89.
  58. R. Vorobel, I. Ivasenko, O. Berehulyak, T. Mandzii, Segmentation of rust defects on painted steel surfaces by intelligent image analysis, Automation in Construction, 123, (2021) 103515.
  59. B. Yin, N. Josselyn, T. Considine, J. Kelley, B. Rinderspacher, R. Jensen, W. Rundensteiner, Corrosion image data set for automating scientific assessment of materials, BMVC, (2021) 1-15.
  60. D. A. Yeshanew, M. G. Jiru, G. M. S. Ahmed, I.A. Badruddin, M.E.M Soudagar, S. Kamangar, M. A. Tolcha, Corrosion charac-terization at surface and subsurface of iron-based buried water pipelines, Materials, 14 (2021) 5877.
  61. A. Carlos, Mendiola-Santibanez, F. Paredes-Orta, D. Jorge, I.R. Terol-Villalobos, Method for grain size determination in carbon steels based on the ultimate opening, Measurement, 133 (2019) 193-207. https://doi.org/10.1016/j.measurement.2018.09.068
  62. H. Gao, W. C. Siu, C. H. Hou, Improved techniques for automatic image segmentation, IEEE Transactions on Circuits and Systems for Video Technology, 11 (2001) 1273-1280. https://doi.org/10.1109/76.974681
  63. X. J. XWang, X. J. Sun, C. Song, H. Chen, S. Tong, W. Han, F. Pan, Grain size-dependent mechanical properties of a high-manganese austenitic steel, Acta Materialia, 32 (2019) 746-754.
  64. G. Ji, Y. Zhu, Y. Zhang, The corroded defect rating system of coating material based on computer vision, Transactions on edutainment VIII, (2012) 210-220.
  65. F. N. Medeiros, G. L. Ramalho, M. P. Bento, L.C. Medeiros, On the evaluation of texture and color features for nondestructive corrosion detection, EURASIP Journal on Advances in Signal Processing, (2010) 1-7.
  66. B. Ghojogh, F. Karray, M. Crowley, Fisher and kernel Fisher discriminant analysis: Tutorial, arXiv:1906.09436, (2019).
  67. P. S. Addison, The illustrated wavelet transform handbook: introductory theory and applications in science, engineering, medicine and finance, CRC press, (2017).
  68. T. A. Alkanhal, Image processing techniques applied for pitting corrosion analysis, IJRET, (2014) 385-391.
  69. S. A. Idris, F. A. Jafar, Image enhancement based on software filter optimization for corrosion inspection, International Conference on Advanced Intelligent Systems for Sustainable Development, (2014) 345-350.
  70. S. Ghanta, T. Karp, S. Lee, Wavelet domain detection of rust in steel bridge images, ICASSP, (2011) 1033-1036.
  71. G. R. Yang, X. J. Wang, Artificial neural networks for neuroscientists: a primer, Neuron, 107 (2020) 1048-1070. https://doi.org/10.1016/j.neuron.2020.09.005
  72. M. Ahmed, R. Seraj, S. M. S. Islam, The k-means algorithm: A comprehensive survey and performance evaluation, Electronics, 9 (2020) 1295.
  73. K. S. Liao, Y. T. Lee, Detection of rust defects on steel bridge coatings via digital image recognition, Automation in Construction, 71 (2016) 294-306. https://doi.org/10.1016/j.autcon.2016.08.008
  74. A. A. Bushra, G. Yi, Comparative analysis review of pioneering DBSCAN and successive density-based clustering algorithms, IEEE Access, 9 (2021) 87918-87935. https://doi.org/10.1109/ACCESS.2021.3089036
  75. L. Sun, Y. Li, X. Li, C. Liu, Corrosion defect segmentation method based on superpixel feature cascade, Ain Shams Eng., (2023) 102425.clustering algorithm, IEEE Access, 8 (2020) 80716-80727. https://doi.org/10.1109/ACCESS.2020.2988796
  76. S. Ghosh, S. K. Dubey, Comparative analysis of k-means and fuzzy c-means algorithms, International Journal of Advanced Computer Science and Applications, 4 (2013)35-39. https://doi.org/10.14569/IJACSA.2013.040406
  77. V. Mosorov, L. Tomczak, Image texture defect detection method using fuzzy C-means clustering for visual inspection systems, Arabian Journal for Science and Engineering, 39, (2014) 3013-3022. https://doi.org/10.1007/s13369-013-0920-7
  78. C. Cortes, V. Vapnik, Support-vector networks, Machine learning, 20 (1995) 273-297.
  79. N. D. Hoang, Image processing-based pitting corrosion detection using metaheuristic optimized multilevel image thresholding and machine-learning approaches, Mathematical Problems in Engineering, (2020) 1-19.
  80. S. Hakimian, S. Pourrahimi, A. H. Bouzid, L.A. Hof, Application of machine learning for the classification of corrosion behavior in different environments for material selection of stainless steels, Computational Materials Science, 228, (2023) 112352.
  81. Z. Li, F. Liu, W. Yang, S. Peng, J. Zhou, A survey of convolutional neural networks: analysis, applications, and prospects, IEEE Transactions on Neural Networks and Learning Systems, (2021). 6999-7019.
  82. W. Nash, T. Drummond, N. Birbilis, A review of deep learning in the study of materials degradation, npj Materials Degradation, 2 (2018) 37.
  83. L. B. Coelho, D. Zhang, Y. Van Ingelgem, D. Steckelmacher, A. Nowe, H. Terryn, Reviewing machine learning of corrosion prediction in a data-oriented perspective, npj Materials Degradation, 6 (2022) 8.
  84. A. Srivastava, G. Ji, R. K. Singh, Application of deep-learning architecture for image analysis based corrosion detection, In 2021 STCR (2021) 1-5.
  85. D. L. Naik, H. U. Sajid, R. Kiran, G. Chen, Detection of corrosion-indicating oxidation product colors in steel bridges under varying illuminations, shadows, and wetting conditions, Metals, 10 (2020) 1439.
  86. W. Nash, L. Zheng, N. Birbilis, Deep learning corrosion detection with confidence, npj Materials Degradation, 6(1), (2022) 26.
  87. R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, (2014) 580-587.
  88. J. R. Uijlings, K. E. Van De Sande, T. Gevers, A.W. Smeulders, Selective search for object recognition, International Journal of Computer Vision, 104, (2013) 154-171. https://doi.org/10.1007/s11263-013-0620-5
  89. R. Girshick, Fast r-cnn, Proceedings of the IEEE International Conference on Computer Vision, (2015) 1440-1448.
  90. S. Ren, K. He, R. Girshick, J. Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems, 28 (2015) 1-9.
  91. I. Katsamenis, E. Protopapadakis, A. Doulamis, N. Doulamis, A. Voulodimos, Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation, Advances in Computer Vision and Pattern Recognition, (2020) 160-169.
  92. S. Xie, Z. Tu, Holistically-nested edge detection, Proceedings of the IEEE International Conference on Computer Vision, (2015) 1395-1403.
  93. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556, (2014).
  94. "scikit-learn", scikit-learn, last modified Nov 27. 2023, accessed Nov 29. 2023, http://scikit-learn.org.
  95. "github", github, last modified Dec 12. 2023, accessed Dec 13. 2023, https://github.com/anirbankonar123.
  96. H. Huang, H. Zhou, X. Yang, L. Zhang, L. Qi, A. Y. Zang, Faster R-CNN for marine organisms detection and recognition using data augmentation, Neurocomputing, 337 (2019) 372-384. https://doi.org/10.1016/j.neucom.2019.01.084