Image Coding and Pooling with a Bio-inspired Reaction-Diffusion Algorithm

Abstract

Abstract This paper proposes a reaction-diffusion algorithm designed for image encoding, pooling and decoding with a FitzHugh-Nagumo model. The model simulates biological nonlinear response on external stimuli applied to nerve axon. A system of discretely coupled elements governed by the FitzHugh-Nagumo model has the nature of organizing stationary pulses, depending on their initial conditions and coupling strength. The proposed algorithm utilizes the system, and encodes a gray level image into a halftone image with the nature organizing stationary pulses (image encoding); the encoded halftone image is pooled in the system without external stimuli (image pooling). In the image encoding, we need to add Gaussian noise to the gray level image for randomly distributing pulses, which represent gray levels in a local area. By providing the encoded halftone image for the initial condition of the same reaction-diffusion algorithm, we obtain a gray level image approximating to the original one (image decoding).