Image processing method and system

Abstract

The present disclosure relates to an image processing method. The method may include: receiving an input image to be compressed; extracting features of the input image; encoding the extracted features of the input image into a latent feature, zinput, determining, from a background image database which contains one or more background images, a background image that has a latent feature, zbackground, best-matching with zinput; calculating a delta feature, Δz, which is the difference between zinput and zbackground, in accordance with the following formula: Δz=zinput−zbackground; and compressing Δz to obtain a bitstream, Ydifferences. The method may further include: sending Ydifferences and an identifier (IDentifier—ID) of zbackground to a server; retrieving zbackground based on the ID of zbackground; decompressing Ydifferences based on zbackground to retrieve Δz; calculating a reconstructed latent feature, zreconstructed, in accordance with the following formula: zreconstructed=Δz+zbackground; and decoding zreconstructed to obtain a reconstructed input image. An image processing system and a computer program are further disclosed.

Dependencies are inferred from the claim text.