A Compared Study Between Some Subspace Based Algorithms

TL;DR

This paper compares various subspace-based face recognition algorithms, introducing ECA (2DECA) based on Renyi entropy, and evaluates their recognition accuracy and efficiency.

Contribution

It proposes ECA (2DECA) derived from PCA and 2DPCA using Renyi entropy, and compares multiple algorithms' performance.

Findings

ECA (2DECA) shows improved feature extraction.

Recognition accuracy varies among algorithms.

Operational efficiency differs significantly.

Abstract

The technology of face recognition has made some progress in recent years. After studying the PCA, 2DPCA, R1-PCA, L1-PCA, KPCA and KECA algorithms, in this paper ECA (2DECA) is proposed by extracting features in PCA (2DPCA) based on Renyi entropy contribution. And then we conduct a study on the 2DL1-PCA and 2DR1-PCA algorithms. On the basis of the experiments, this paper compares the difference of the recognition accuracy and operational efficiency between the above algorithms.