Deep Learning-Based Automatic Recognition of Segregation in Continuous Casting Slabs

Central segregation, a typical internal defect in continuous casting slabs, significantly deteriorates the mechanical properties of steel products. However, traditional manual defect evaluation methods rely heavily on experience, are highly subjective and inefficient, making it difficult to meet the quality assessment requirements of today’s high-end steel materials. In this study, an approach which combines an unsupervised image enhancement algorithm and Otsu algorithm analysis was proposed to achieve automatic recognition and quantitative features extracting of central segregation in continuous casting slabs. The challenges posed by insufficient brightness and low contrast in central segregation images were addressed using unsupervised image enhancement algorithms. Following this enhancement, batch objective quantification of the segregation images was conducted through Otsu processing. Comparative experimental results showed that the enhanced images yielded an average Dice Similarity Coefficient of 0.965 for segregation recognition, representing a 38% improvement over unprocessed images, with consistent accuracy gains across complex segregation scenarios. This intelligent detection method eliminates the need for manually labeling a training set, substantially improves the consistency of segregation quantification and reduces the time cost significantly. Consequently, multiple parameters can be employed to quantify segregation characteristics, offering a more comprehensive and precise approach than current simplified rating methods. This advancement holds promise for enhancing quality control in steel processing and advancing Artificial Intelligence-driven technological progress within the metallurgical sector.