Fault Detection in Steel Surfaces Using Deep Learning Approaches


Shubham Joshi
Aditi Mukte
Snehal Jaiswal
Khushboo Khurana


There is sustainable growth in the industries in various developing nations. Quality maintenance of the product under development is an essential part of the product development process. Product quality affects the performance of the product. Various kinds of issues in the manufacturing can impact negatively on the product. Therefore, it is needed to make sure that the manufactured products are fault-free by establishing and employing such softwares that will ultimately bring some ease in the fault detection process. This paper aims to diagnose faults on steel surfaces by using convolutional neural networks and classification by making use of 5 different types of classifiers. They are Support Vector machines, Naive Bayes Classifier, Decision Tree, K-nearest Neighbors, and Random Forest. We have used 4 different types of models namely, Alexnet, InceptionV3, Resnet and VGG16. The testing accuracy was found to be maximum for the VGG16 model which was recorded to be 75.02%. Among the classifiers, the best accuracy was found out with Random Forest and Decision Tree classifiers to be 74.9% and 74.3% respectively. The defects are classified among the 4 categories of defects and are highlighted using image segmentation.


Author Biographies

Shubham Joshi, Shri Ramdeobaba College Of Engineering and Management,Nagpur

Shubham Joshi is a student of Shri Ramdeobaba College of Engineering and Management, and is currently pursuing his bachelor’s degree in Computer Science and Engineering. He is fascinated by Technology and the leverage that Technology is bringing to humans’ lives. He is passionate to become a part of the community which is at the producing end of the technology products and services. His research and technical interests include Deep Learning, Machine Learning, Cloud Computing and Data Science. He is Web dev Lead at Google Developers Student Club, RCOEM. He was one of the winner
at TATA Imagination Challenge organised by TATA group.
E-mail: [email protected].

Aditi Mukte, Shri Ramdeobaba College Of Engineering and Management,Nagpur

Aditi Mukte is currently pursuing graduation in Computer Science and Engineering branch from Shri Ramdeobaba College of Engineering and Management. She passed her 10th standard in 2017 from R.S. Mundle English School and Junior College with 97.8%. She also completed her 12 th standard in 2019 from Dr. Ambedkar College, Nagpur and secured 81.69She has interest in research field. Along with these, she has won Smart India Hackathon(SIH) organized by Ministry Of India, in Aug, 2022.
E-mail: [email protected].

Snehal Jaiswal, Shri Ramdeobaba College Of Engineering and Management,Nagpur

Snehal Jaiswal is currently in final year of B.E. in computer science and engineering from shri ramdeobaba College of engineering(RCOEM) and management, nagpur. She completed here standard 12th in 2019 from St. Paul’s Junior College in the field of science. She came merit in standard 10th in 2017 from St. Xavier’s High School, nagpur. She is a focused, creative and cooperative person. She is involved in various extracurricular activities.
E-mail: jaiswalsa2 @rknec.edu.

Khushboo Khurana, Shri Ramdeobaba College Of Engineering and Management,Nagpur

Khushboo Khurana is currently pursuing her Ph.D. from Visvesvaraya National Institute of Technology (VNIT), Nagpur and is working as an Assistant professor in Department of Computer Science and Engineering, Shri Ramdeobaba College of Engineering and Management, Nagpur. She completed her B.E (Computer Science and Engineering) in 2010 and M.Tech. (Computer Science and Engineering) in 2013, from Shri Ramdeobaba College of Engineering and Management, Nagpur. She is a gold medalist in her M.Tech. Her research interests include image processing, video processing and Deep Learning.
E-mail: [email protected].
How to Cite
Shubham Joshi, Aditi Mukte, Snehal Jaiswal, & Khushboo Khurana. (2023). Fault Detection in Steel Surfaces Using Deep Learning Approaches. International Journal of Next-Generation Computing, 14(1). https://doi.org/10.47164/ijngc.v14i1.1020


  1. Adhao, R. B., Pachghare, V. K., Khadse, V. M., et al. 2021. Hybrid intrusion detection system. International Journal of Next-Generation Computing 12, 5. DOI: https://doi.org/10.47164/ijngc.v12i5.439
  2. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255. DOI: https://doi.org/10.1109/CVPR.2009.5206848
  3. Du, P., Samat, A., Waske, B., Liu, S., and Li, Z. 2015. Random forest and rotation forest for fully polarized sar image classification using polarimetric and spatial features. ISPRS Journal of Photogrammetry and Remote Sensing 105, 38–53. DOI: https://doi.org/10.1016/j.isprsjprs.2015.03.002
  4. Fadli, V. F. and Herlistiono, I. O. 2020. Steel surface defect detection using deep learning. Int. J. Innov. Sci. Res. Technol 5, 244–250. DOI: https://doi.org/10.38124/IJISRT20JUL240
  5. Han, X., Zhong, Y., Cao, L., and Zhang, L. 2017. Pre-trained alexnet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification. Remote Sensing 9, 8, 848. DOI: https://doi.org/10.3390/rs9080848
  6. Kaur, T. and Gandhi, T. K. 2019. Automated brain image classification based on vgg-16 and transfer learning. In 2019 International Conference on Information Technology (ICIT). IEEE, 94–98. DOI: https://doi.org/10.1109/ICIT48102.2019.00023
  7. Li, J., Su, Z., Geng, J., and Yin, Y. 2018. Real-time detection of steel strip surface defects based on improved yolo detection network. IFAC-PapersOnLine 51, 21, 76–81. DOI: https://doi.org/10.1016/j.ifacol.2018.09.412
  8. Li, X., Wang, L., and Sung, E. 2004. Multilabel svm active learning for image classification. In 2004 International Conference on Image Processing, 2004. ICIP’04. Vol. 4. IEEE, 2207– 2210.
  9. McCann, S. and Lowe, D. G. 2012. Local naive bayes nearest neighbor for image classification. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3650–3656. DOI: https://doi.org/10.1109/CVPR.2012.6248111
  10. McNeely-White, D., Beveridge, J. R., and Draper, B. A. 2020. Inception and resnet features are (almost) equivalent. Cognitive Systems Research 59, 312–318. DOI: https://doi.org/10.1016/j.cogsys.2019.10.004
  11. Mishra, S. P., Sarkar, U., Taraphder, S., Datta, S., Swain, D., Saikhom, R., Panda, S., and Laishram, M. 2017. Multivariate statistical data analysis-principal component analysis (pca). International Journal of Livestock Research 7, 5, 60–78. DOI: https://doi.org/10.5455/ijlr.20170415115235
  12. Shao, X., Wang, Q., Yang, W., Chen, Y., Xie, Y., Shen, Y., and Wang, Z. 2021. Multi- scale feature pyramid network: A heavily occluded pedestrian detection network based on resnet. Sensors 21, 5, 1820. DOI: https://doi.org/10.3390/s21051820
  13. Song, F., Guo, Z., and Mei, D. 2010. Feature selection using principal component analysis. In 2010 international conference on system science, engineering design and manufacturing informatization. Vol. 1. IEEE, 27–30. DOI: https://doi.org/10.1109/ICSEM.2010.14
  14. Vailaya, A., Jain, A., and Zhang, H. J. 1998. On image classification: City images vs. landscapes. Pattern recognition 31, 12, 1921–1935. DOI: https://doi.org/10.1016/S0031-3203(98)00079-X
  15. Wen, L., Li, X., and Gao, L. 2020. A transfer convolutional neural network for fault diagnosis based on resnet-50. Neural Computing and Applications 32, 10, 6111–6124. DOI: https://doi.org/10.1007/s00521-019-04097-w