Face identification by means of a neural net classifier

TL;DR

This paper introduces a face identification method combining eigenfaces and neural networks, achieving higher recognition accuracy than classical approaches by effectively handling variations in facial appearance and lighting.

Contribution

The novel integration of eigenfaces with neural network classifiers improves face recognition accuracy under challenging conditions.

Findings

Recognition rate of over 87%

Outperforms classical Turk and Pentland method

Handles variations in expression, details, and lighting

Abstract

This paper describes a novel face identification method that combines the eigenfaces theory with the Neural Nets. We use the eigenfaces methodology in order to reduce the dimensionality of the input image, and a neural net classifier that performs the identification process. The method presented recognizes faces in the presence of variations in facial expression, facial details and lighting conditions. A recognition rate of more than 87% has been achieved, while the classical method of Turk and Pentland achieves a 75.5%.