LGLG-WPCA: An Effective Texture-based Method for Face Recognition

TL;DR

This paper introduces LGLG-WPCA, a novel face recognition method leveraging Gabor wavelet domain Gaussian features and WPCA, demonstrating robustness under challenging conditions and improved accuracy when combined with deep learning features.

Contribution

The paper presents a new texture-based face recognition technique using Gaussian feature embedding and WPCA, with a key-point version and combined deep learning features for enhanced accuracy.

Findings

Effective in adverse conditions like pose, aging, illumination

Outperforms state-of-the-art methods on FERET database

Combining with DCNN features yields highest recognition accuracy

Abstract

In this paper, we proposed an effective face feature extraction method by Learning Gabor Log-Euclidean Gaussian with Whitening Principal Component Analysis (WPCA), called LGLG-WPCA. The proposed method learns face features from the embedded multivariate Gaussian in Gabor wavelet domain; it has the robust performance to adverse conditions such as varying poses, skin aging and uneven illumination. Because the space of Gaussian is a Riemannian manifold and it is difficult to incorporate learning mechanism in the model. To address this issue, we use L2EMG to map the multidimensional Gaussian model to the linear space, and then use WPCA to learn face features. We also implemented the key-point-based version of LGLG-WPCA, called LGLG(KP)-WPCA. Experiments show the proposed methods are effective and promising for face texture feature extraction and the combination of the feature of the proposed methods and the features of Deep Convolutional Network (DCNN) achieved the best recognition accuracies on FERET database compared to the state-of-the-art methods. In the next version of this paper, we will test the performance of the proposed methods on the large-varying pose databases.