Lens surface defect detection method, equipment and medium

The embodiment of the invention discloses a lens surface defect detection method. The method comprises the following steps: acquiring a multi-angle image of a to-be-detected lens; wherein the multi-angle image at least comprises a first angle image corresponding to a side image and a second angle image corresponding to a front image; based on a preset contour recognition algorithm and a template library corresponding to an application scene of the to-be-detected lens, performing matching recognition on the first angle image to obtain lens basic information of the to-be-detected lens; processing the second angle image to determine a detection area corresponding to the to-be-detected lens, and performing proportion division on the detection area according to the current detection precision to obtain detection sub-areas; and performing pixel point traversal on each detection sub-region to obtain a defect identification result of each detection sub-region, and splicing each detection sub-region to identify the le