Research On Infrared Residue Detection System Based On Quadratic Threshold Segmentation

Steel industry is an integral part of the steel-making process, as the existence of the steel slag will affect the purity of the steel, we need real-time detect the ratio of steel slag in liquid steel, that is slag carry-over detection. In a lot of slag detection methods, infrared detection method has been more and more widely used because of its small influence on the surrounding environment, simple operation, easy maintenance, low operating cost and so on. However, in china, especially some medium-sized steel mills the infrared detection method has not been well applied because of the harsh environment and production costs and other reasons. Therefore, we hope to design a slag detection system with low cost, good adaptability to complex environment, real-time and accuracy.In this paper, firstly, during the study of the infrared radiation theory, the principle of infrared slag detection is discussed, and the suitable infrared detector is selected. Then the program in the framework of C++MFC to collect the slag carry-out video in real time is written. At last the knowledge of image preprocessing and image segmentation is studied systematically, an improved slag extraction method is proposed on the basis of comparing the advantages and disadvantages of the existing slag detection method. Firstly, the contrast enhancement and median filter are used to preprocess the slag carry-over image, then two threshold segmentation method is used for the image to extract the steel slag. Through experiments, it is found that the method can accurately extract the steel slag in complex background. In order to further improve the accuracy of the steel slag extraction, a threshold determination method based on the combination of global and local thresholds is proposed.experiments show that the proposed method can accurately separate the steel slag in molten steel, and the method can meet the needs of steel slag detection in different situations because of the coefficient can be adjusted.