Magneto-optical imaging nondestructive testing of welding defects based on image fusion

Improving the visual effect of welding defect detection is a key research area of magneto-optical imaging nondestructive testing technology. Finite element analysis and magneto-optical image simulation are used to analyze the characteristics of magneto-optical imaging detection under rotating excitation. Through the stripe analysis of simulated magneto-optical images, it is found that the multi-frame magneto-optical images at defects have low discrete degree of gray value. Therefore, an image fusion method based on pixel standard deviation is proposed for the welding defect detection of magneto-optical imaging. Fast guide filtering is applied to the magneto-optical images of welding defects under rotating excitation. Pixel standard deviation is used to fuse multi-frame magneto-optical images, and image enhancement and rendering are used to improve the visual effect of welding defect detection. The experimental results show that the fast guided filter can improve the speed of image preprocessing and ensure good image smoothing effect. Compared with other image fusion algorithms, the proposed method can significantly improve the image quality of magneto-optical imaging detection, and does not require screening of magneto-optical images. This method has the advantages of tolerating frame drops in acquisition and excellent generalization performance, enabling fast and efficient nondestructive testing of welding defects.