SVM-based Multiview Face Recognition by Generalization of Discriminant Analysis

TL;DR

This paper presents a multiview face recognition method combining Gabor filters, canonical covariate analysis, and SVMs to handle non-linear variations due to pose, illumination, and expression, demonstrating high accuracy on the UMIST database.

Contribution

It introduces a novel approach integrating Gabor features, canonical covariate analysis, and SVMs for robust multiview face recognition, improving over existing methods.

Findings

High recognition accuracy on UMIST database

Effective reduction of high-dimensional features

Robustness to pose, illumination, and expression variations

Abstract

Identity verification of authentic persons by their multiview faces is a real valued problem in machine vision. Multiview faces are having difficulties due to non-linear representation in the feature space. This paper illustrates the usability of the generalization of LDA in the form of canonical covariate for face recognition to multiview faces. In the proposed work, the Gabor filter bank is used to extract facial features that characterized by spatial frequency, spatial locality and orientation. Gabor face representation captures substantial amount of variations of the face instances that often occurs due to illumination, pose and facial expression changes. Convolution of Gabor filter bank to face images of rotated profile views produce Gabor faces with high dimensional features vectors. Canonical covariate is then used to Gabor faces to reduce the high dimensional feature spaces into low dimensional subspaces. Finally, support vector machines are trained with canonical sub-spaces that contain reduced set of features and perform recognition task. The proposed system is evaluated with UMIST face database. The experiment results demonstrate the efficiency and robustness of the proposed system with high recognition rates.