Brain-inspired algorithms for processing of visual data

TL;DR

This paper reviews brain-inspired computational models for visual data processing, highlighting neural mechanisms and their implementation in convolutional networks to improve stability and performance.

Contribution

It provides a comprehensive analysis of neuro-scientific findings applied to image processing and explores the connection between visual cortex organization and convolutional network structures.

Findings

Neural inhibition mechanisms enhance stability in visual processing.

Hierarchical organization of the visual system informs ConvNet design.

Inhibition mechanisms are implemented in image operators and ConvNets.

Abstract

The study of the visual system of the brain has attracted the attention and interest of many neuro-scientists, that derived computational models of some types of neuron that compose it. These findings inspired researchers in image processing and computer vision to deploy such models to solve problems of visual data processing. In this paper, we review approaches for image processing and computer vision, the design of which is based on neuro-scientific findings about the functions of some neurons in the visual cortex. Furthermore, we analyze the connection between the hierarchical organization of the visual system of the brain and the structure of Convolutional Networks (ConvNets). We pay particular attention to the mechanisms of inhibition of the responses of some neurons, which provide the visual system with improved stability to changing input stimuli, and discuss their implementation in image processing operators and in ConvNets.