Abstract: Provided is a method for detecting a surface defect of a copper-clad laminate based on multi-scale gridding. The method includes: S1, collecting a photographed image of the copper-clad laminate through a line-scan camera; S2, segmenting out a copper-clad region and a non-copper-clad region, and rotating the copper-clad region upright; S3, dividing the copper-clad region of the image of the copper-clad laminate, and performing a pyramid operation on a divided original grid image; S4, determining averages of pixel values at all levels; S5, fusing the average at all levels to obtain a final background average; and S6, searching for a final defect according to a difference between a background and a foreground.

Abstract: Provided is a method for detecting a surface defect of a copper-clad laminate based on multi-scale gridding. The method includes: S1, collecting a photographed image of the copper-clad laminate through a line-scan camera; S2, segmenting out a copper-clad region and a non-copper-clad region, and rotating the copper-clad region upright; S3, dividing the copper-clad region of the image of the copper-clad laminate, and performing a pyramid operation on a divided original grid image; S4, determining averages of pixel values at all levels; S5, fusing the average at all levels to obtain a final background average; and S6, searching for a final defect according to a difference between a background and a foreground.