Improved sparse PCA method for face and image recognition

TL;DR

This paper proposes an improved sparse PCA approach combined with nearest-neighbor and kernel ridge regression methods for face recognition, showing that certain combinations can outperform traditional PCA in accuracy and speed.

Contribution

It introduces a novel combination of sparse PCA with classification methods and compares the efficiency of FISTA and proximal gradient algorithms for sparse PCA computation.

Findings

FISTA-based sparse PCA is faster than proximal gradient-based sparse PCA.

Certain sparse PCA and classification method combinations improve face recognition accuracy.

Sparse PCA can sometimes outperform traditional PCA in recognition tasks.

Abstract

Face recognition is the very significant field in pattern recognition area. It has multiple applications in military and finance, to name a few. In this paper, the combination of the sparse PCA with the nearest-neighbor method (and with the kernel ridge regression method) will be proposed and will be applied to solve the face recognition problem. Experimental results illustrate that the accuracy of the combination of the sparse PCA method (using the proximal gradient method and the FISTA method) and one specific classification system may be lower than the accuracy of the combination of the PCA method and one specific classification system but sometimes the combination of the sparse PCA method (using the proximal gradient method or the FISTA method) and one specific classification system leads to better accuracy. Moreover, we recognize that the process computing the sparse PCA algorithm using the FISTA method is always faster than the process computing the sparse PCA algorithm using the proximal gradient method.