Detection Method of Protruding Defects of Parts Based on Improved Threshold Segmentation

Abstract

Aiming at a series of problems that the traditional threshold segmentation method has low detection accuracy in detecting part bulge defects, a part bulge defect detection method based on improved threshold segmentation is proposed in this paper. Firstly, the parts to be tested are obtained, and then the image is filtered and denoised. Because the traditional median filter has some limitations, a fast weighted median filtering algorithm is proposed. Then the image is enhanced, and the method based on Laplace operator is used to enhance the image. Then Otsu threshold segmentation and iterative threshold segmentation are used respectively. It is found that there are still many non convex defects, which have a great impact on the detection accuracy. Therefore, an improved iterative threshold segmentation is proposed. The difference operation is carried out between the standard part and the part to be tested, and the above three methods are compared. The results indicate that the better iterative threshold segmentation method can effectively test the convex fault of the compent.