Automatic Detection of Slag Eye Area Based on a Hue-Saturation-Value Image Segmentation Algorithm

Inert gas bubbling is widely applied in the ladle refining of molten steel to ensure homogeneity and to promote chemical reactions between the slag and the metal phases. Monitoring the slag behavior is important for controlling the steel quality. In the present study, an image segmentation algorithm based on the hue-saturation-value color space has been proposed to realize the automatic detection and calculation of the slag eye area. Laboratory experiments show that the developed method was stable and yielded accurate results, which could be applied to automatic industrial image detection. In addition, the proposed methodology is promising in other fields, such as the evaluation of particle diameter for the identification of aggregate size, detection of material cracks, and measurement of the lining thickness of a furnace.