Study of Defect Segmentation from a Mode Background Image

The difficulty of machine vision defect detection is how to extract the defect target from the background image, especially the defect target segmentation under the pattern background image. The pattern background image has more complex pattern, contour, color or texture information, while the defect target and the background area have the same color or grayscale, and it cannot be well segmented with the conventional gray threshold or the tone threshold. This paper focuses on the defect segmentation of pattern background image and discusses the defect segmentation of pattern background image in several cases. The key problem discussed in this paper is how to convert the defect of pattern background image into the contrast defect of non-pattern background image. In this paper, the method of removing transverse and longitudinal texture based on wavelet transform and slant texture based on discrete cosine transform is proposed, and the defect of pattern background image is converted into the contrast defect of non-pattern background image, so as to simplify the segmentation algorithm and improve the segmentation speed. Experiments show that the algorithm proposed in this paper has good segmentation effect for segmentation of defects in horizontal, vertical and oblique texture.