Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{151743,
        author = {Pradnya D. Sutar and Pallavi S. Chandanshive and Pushpa D. Kale and Aarti H. Chavan and Uttam Y.siddha},
        title = {Design and development of automatic surface defect detection in hot rolled steel strip},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {8},
        number = {1},
        pages = {701-704},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=151743},
        abstract = {In the steel industry Automatic detection of steel surface defects is very important for product quality control. However, the traditional method cannot be well applied in the production line, because of slow running speed and its low accuracy. The current, popular algorithm (based on deep learning) also has the problem of low accuracy, and there is still a lot of room for improvement. This paper proposes a method combining improved  and enhanced faster region convolutional neural networks (faster R-CNN) to improve the accuracy reduce the average running time . Firstly, the image input into the improved  model, which add the deformable revolution network (DCN) and improved cutout to classify the sample with defects and without defects. If the probability of having a defect is less , the algorithm directly outputs the sample without defects. Otherwise, the samples are further input into the improved faster CNN . The output is the  classification and location of the defect in the sample or without defect in the sample. By analyzing the data set which is obtained in the real factory environment, the accuracy of this method can reach 98%. At the same time, the average running time is faster than other models.Here, the NEU database, used for improve efficiency of model,which having six kinds of typical surface defects of hot-rolled steel strip. The results show that in all kinds of defects in database, the proposed model can perform defect segmentation ,in this  process there is no need of skilled learning with no labeling and small training procedure so it is easy to give required application. also, this defect detection shall improve the reliability and productivity of steel  strip's production process.},
        keywords = {steel surface defect detection; Convocutional neural network,python deep learning ,classification},
        month = {},
        }