The NoN Approach to Autonomic Face Recognition

TL;DR

This paper introduces a biologically inspired NoN model for autonomic face recognition, utilizing distributed networks that mimic cerebral cortex structures, achieving high recognition accuracy on benchmark data.

Contribution

It presents a novel NoN-based face recognition method that models cortical structures and demonstrates high accuracy on benchmark datasets.

Findings

Maximum recognition accuracy of 98.5%

Average recognition accuracy of 97.4%

Effective modeling of cortical information processing

Abstract

A method of autonomic face recognition based on the biologically plausible network of networks (NoN) model of information processing is presented. The NoN model is based on locally parallel and globally coordinated transformations in which the neurons or computational units form distributed networks, which themselves link to form larger networks. This models the structures in the cerebral cortex described by Mountcastle and the architecture based on that proposed for information processing by Sutton. In the proposed implementation, face images are processed by a nested family of locally operating networks along with a hierarchically superior network that classifies the information from each of the local networks. The results of the experiments yielded a maximum of 98.5% recognition accuracy and an average of 97.4% recognition accuracy on a benchmark database.