Die cutting product surface defect detection method based on deep learning

The invention discloses a die-cutting product surface defect detection method based on deep learning. The method comprises the following steps: acquiring a die-cutting product surface image; inputting the surface image of the die-cutting product into the surface feature extraction network model to obtain surface features of the die-cutting product; and inputting the surface features of the die-cut product to the surface defect detection network model for surface defect detection, and outputting a surface defect detection result. According to the invention, deep learning related technologies are applied to die-cutting product surface defect detection, a general target detection algorithm is analyzed and improved, and an improved surface defect detection network model and a surface feature extraction network model for die-cutting product surface defect detection are provided. According to the die-cutting product surface defect detection method, the die-cutting product is subjected to surface defect detection ac