Multi-focus image fusion method based on memristor pulse coupling neural network

Abstract

The invention discloses a multi-focus image fusion method based on a memristor pulse coupling neural network. In an existing pulse coupled neural network (PCNN), a self-adaptive change method of a connection coefficient is completely based on computer analog simulation, so the timeliness of a PCNN model in the operation process is possibly low; meanwhile, a self-adaptive change equation of parameters (connection coefficients) is completely set manually, so the feasibility of parameter self-adaptive change in the actual operation process cannot be guaranteed. The method comprises the followingsteps: designing a self-adaptive memristor PCNN model based on a memristor cross array compact circuit structure; designing a flexible and universal mapping function (Mapping function); applying the self-adaptive memristor PCNN model to multi-focus image fusion, and acquiring a better multi-focus image fusion result by further improving the network structure (single channel to multiple channels) of the multi-focus image fusion model. The method not only provides a brand-new solution for inherent parameter estimation problems in numerous parameter-controlled neural network models, but also facilitates promotion of hardware implementation of the neural network.

Description

Technical field [0001] The present invention belongs to the technical field of multi-focus image fusion, and particularly relates to a multi-image focus fusion method based on a new memristive cross-array structure (including necessary peripheral circuits). Background technique [0002] Pulse coupled neural network (PCNN) is a simplified neural network model obtained by Eckhorn in 1990 based on experimental observations of the visual cortex of the cat’s brain. PCNN has many unique network characteristics, such as: pulse coupling characteristics, synchronous pulse delivery characteristics, nonlinear modulation characteristics, threshold dynamic change characteristics, etc. At the same time, PCNN itself can extract effective data and information from complex backgrounds without training. And the specific form and processing mechanism of the signal are more in line with the physiological basis of the Human Vision System (HVS). Therefore, PCNN is also known as the third-generation a...

AI Technical Summary

Problems solved by technology

However, in the current PCNN model, the adaptive change method of the connection coefficient is completely based on computer simulation, which may lead to low timeliness of the PCNN model during operation.

At the same time, the adaptive change equation of parameters (connection coefficients) is completely set artificially, which cannot guarantee the feasibility of parameter adaptive change in the actual operation process

Images