Method and system for image compressing and coding with deep learning

Abstract

An image processing system () and methods therein for compressing and coding an image and for optimizing its parameters are disclosed. The embodiments herein provide an improved system and simplified method with deterministic uniform quantization with integer levels based on Softmax function for image compression and coding. The embodiments herein produce exact discrete probability mass function for latent variables to be coded from side information. The embodiments herein enable training of the image processing system to minimize the bit rate through backpropagation at the same time. Moreover, the embodiments herein create the possibility to encode region of interest (ROI) areas during coding.