Intelligent detection method for surface defects of power adapter

The invention relates to the technical field of image defect detection, in particular to an intelligent detection method for surface defects of a power adapter. The method comprises the following steps: acquiring a grayscale image of the surface of the power adapter, and performing saliency detection to obtain suspected scratch pixel points; carrying out Gaussian pyramid layering processing to obtain scale images under different scales; determining an abnormal degree according to the gray value difference and the LBP value difference; to-be-analyzed pixel points are obtained through screening; determining an abnormal area according to the abnormal degree; determining the scratch probability of the abnormal region according to the gradient of the edge pixel points of the abnormal region, the distribution of the edge pixel points and the abnormal degree of the edge pixel points, and screening the abnormal region according to the scratch probability to obtain a scratch region; and performing defect detection on