Image processing method and system, encoder, and computer readable storage medium

An encoder, comprising:

• an information-to-be-compressed determination module configured to for a feature matrix of each channel of an image output from an intermediate layer of a neural network, determine one or more rows having same feature values and one or more columns having same feature values at edges of the feature matrix as one or more rows to be compressed and one or more columns to be compressed, wherein the intermediate layer is a layer between an input layer and an output layer;
• a reserved value determination module configured to, for the feature matrix of the each channel, delete the feature values of the one or more rows to be compressed and the one or more columns to be compressed, and reserve remaining feature values as reserved values of the feature matrix of the each channel;
• an edge value compression module configured to, for the feature matrix of the each channel, compress the feature values of the one or more rows to be compressed and the one or more columns to be compressed to obtain one or more edge values of the feature matrix of the each channel;
• and
• an encoding module configured to, encode the reserved values and the one or more edge values of the feature matrix of the each channel, as well as a number of the one or more rows to be compressed and a number of the one or more columns to be compressed, and send a result of the encoding to a decoder for restoring the feature matrix of the each channel by the decoder.