Image deduplication method, device, equipment and medium

Abstract

The application discloses a method, device, equipment and medium for image deduplication, and is used for improving the accuracy of image deduplication. The method comprises the following steps: determining a structural similarity matrix of two images; determining a mask matrix of a difference area of the two images; determining a first similarity index of the difference area and a second similarity index of a non-difference area of the two images based on the structural similarity matrix and the mask matrix; and determining whether to perform a deduplication operation on the two images based on the first similarity index and the second similarity index. In the embodiment of the application, when determining whether to perform a deduplication operation on the two images, the first similarity index of the difference area and the second similarity index of the non-difference area (i.e. the background area) of the two images are considered. Compared with only considering global features, local subtle changes between images are focused on, and the accuracy of image deduplication can be improved.

Images