Design and Development of a System for Corrosion Detection Using Image Segmentation Technique


Praful Sonarkar
Gaurav Patil
Pranav Chalasani


Corrosion, the natural and irreversible process that converts refined metal into a more chemically stable form such as oxide, hydroxide, carbonate. Ultimately the purity of metal goes down and it will cause failure in Welding,bindings in an industry. Accidents due to mechanical loss of metallic bridges, cars, aircraft, etc may cause damage to not only metal but the human digestive tract, eyes, skin,respiratory tract. The manual checking on these metals for corrosion detection is time-consuming. Hence this study builds the Design and Development of a system for Corrosion detection using the image segmentation algorithm U-Net. Dataset creation is first and foremost, a crucial step whenever we go for applying machine learning for any new task. During this experiment, the dataset was generated by capturing images from surrounding various devices and combining datasets from various online sources consisting of rusted metal. This approach obtains a good predictive result with an intersection over union score of 0.6160, and a Jaccard loss of 1.1356 for rust detection. In this paper, we proposed the automated technique by which we can be able to detect rust on metal.


How to Cite
Praful Sonarkar, Gaurav Patil, & Pranav Chalasani. (2022). Design and Development of a System for Corrosion Detection Using Image Segmentation Technique. International Journal of Next-Generation Computing, 13(5).


  1. Agarwala, V., Reed, P., and Ahmad, S. 2000. Corrosion detection and monitoring - a review.
  2. Alzubaidi, L., Zhang, J., Humaidi, A., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamar´ıa, J., Fadhel, M., Al-Amidie, M., and Farhan, L. 2021. Review of deeplearning: concepts, cnn architectures, challenges, applications, future directions. Journalof Big Data 8. DOI:
  3. B, S., Pranav, K., Raj, K., and C V, J. 2014. Rust prevention in structural establishments using cathodic protection technique driven by an mppt based solar charge controller.
  4. Bhanu, B. and Lee, S. 1994. Image segmentation Techniques. 15–24. DOI:
  5. Czichos, H., Saito, T., and Smith, L. 2011. Springer Handbook of Metrology and Testing.Vol. 2. DOI:
  6. Deng, J., Xuan, X., Wang, W., Li, Z., Yao, H., and Wang, Z. 2020. A review of research
  7. on object detection based on deep learning. Journal of Physics: Conference Series 1684,012028.
  8. Kumar, A., Zhang, J., and Lyu, H. 2020. Object detection in real time based on improved single shot multi-box detector algorithm. EURASIP Journal on Wireless Communications and Networking 2020 DOI:
  9. Le Dinh, D., Son, N., and Hassan, M. 2020. Deep learning in semantic segmentation of rust in images.
  10. Lesto, A., Kusumo, P., Kristanto, D., and Prasetia, A. 2022. Corrosion management technology for analyzing and solving of corrosion problems in geothermal field.
  11. Li, Y. and Zhang, Y. 2020. Application research of computer vision technology in automation.374–377. DOI:
  12. Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., and Pietik¨ainen,M. 2020. Deep learning for generic object detection: A survey. International Journal of Computer Vision 128. DOI:
  13. Petrovic, Z. 2016. Catastrophes caused by corrosion. Vojnotehnicki glasnik 64, 1048–1064. DOI:
  14. Sharma, A., Singh, P., and Khurana, P. 2016. Analytical review on object segmentation and recognition. 524–530. DOI:
  15. Srivastava, A., Ji, G., and Singh, R. 2021. Application of deep-learning architecture for image analysis based corrosion detection. 1–5. DOI:
  16. Veleva, L., Mexico, Y., and Kane, R. 2003. Atmospheric Corrosion.
  17. Wang, L., MA, X.-h., and Ye, Y. 2020. Computer vision-based road crack detection using an improved i-unet convolutional networks. 539–543. DOI: