Gabor-like Image Filtering using a Neural Microcircuit

TL;DR

This paper introduces a neural microcircuit that employs Hebbian learning to perform Gabor-like image filtering, mimicking biological visual processing with a simple excitatory synapse structure.

Contribution

It presents a novel neural microcircuit design that approximates Gabor filtering using only excitatory synapses and Hebbian learning, advancing biologically inspired image processing methods.

Findings

Successfully approximates Gabor-like filtering

Uses only excitatory synapses for correlation

Capable of other image processing functions

Abstract

In this letter, we present an implementation of a neural microcircuit for image processing employing Hebbian-adaptive learning. The neuronal circuit utilizes only excitatory synapses to correlate action potentials, extracting the uncorrelated ones, which contain significant image information. This circuit is capable of approximating Gabor-like image filtering and other image processing functions