Face recognition: a convolutional neural-network approach

TLDR

The study develops a hybrid neural‑network for human face recognition that outperforms existing methods. The system uses local image sampling, a self‑organizing map for dimensionality reduction and invariance, and a convolutional neural network that extracts hierarchical features, evaluated on a 400‑image database of 40 individuals, with alternative configurations using the Karhunen‑Loeve transform and a multilayer perceptron for comparison. The hybrid network achieves superior recognition performance compared to other methods.

Abstract

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.