Pit Defect Detection on Steel Shell End Face based on Machine Vision

An algorithm based on ellipse fitting and distance threshold is proposed to detect the pit defect of steel shell. According to the obvious change of the gray value of the pit defect, the method uses the gradient algorithm to highlight the pit defect, and extracts the non-edge defect and the ring affected by the gray value of the edge defect by the OTSU method. Then, ellipse fitting is performed on the extracted inner circle curve, and the nearest distance from the point on the inner circle curve to the fitting ellipse is calculated. Finally, based on the
$3\sigma$
principle, the upper and lower distance threshold is set to detect the defect. Experimental results show that this method has high accuracy and detection efficiency for pit defects. Compared with other testing methods, it can better adapt to the actual production requirements.