The invention discloses a surface defect judgment method based on visual saliency. The method comprises the following steps: firstly, acquiring a surface image sample of a to-be-detected product and calculating a visual saliency map by a saliency map model; secondly, performing threshold segmentation on a salient image; thirdly, calculating the characteristic value of the saliency map; finally, selecting a characteristic value threshold and judging whether a defect exists in the image or not. According to the method, an algorithm is simple and practical, the accuracy is high, and the influence of surface folds on defect detection is eliminated.