Abstract
Image recognition, a subset of artificial intelligence, has been applied to various industries, including steel recycling, to enhance efficiency and accuracy in quality control processes. This review paper provides an overview of the current state of image recognition technology in steel recycling, including the types of images used, the algorithms employed, and the benefits and limitations of the technology. The paper also discusses potential future directions for image recognition in steel recycling, such as integrating machine learning and deep learning frameworks to improve accuracy and developing mobile applications for on-site quality control. Overall, image recognition technology has shown great potential in the steel recycling industry, and further research and development in this field could lead to significant improvements in efficiency and quality control. Experimental results show that the precision of steel scrap classification is 0.92, and the precision of steel scrap quality judgment is 0.87. The empirical findings indicate that this technique can swiftly and precisely detect the type of steel scrap and evaluate its quality, it can also identify the existence of dangerous goods. The model can directly help enterprises reduce costs and increase efficiency, is conducive to the full recovery of scrap steel, and positively affects environmental protection and enterprise profits.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call