Face Recognition Using Scattering Convolutional Network

TL;DR

This paper introduces a face recognition method using scattering transform features combined with PCA and SVM, achieving high accuracy despite variations in face images.

Contribution

The paper proposes a novel face recognition approach utilizing scattering transform features, enhancing invariance to pose and illumination changes.

Findings

High recognition accuracy on three face datasets

Effective feature extraction with scattering transform

Dimensionality reduction with PCA improves performance

Abstract

Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations. Here a new image representation, called scattering transform/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.