Title: Parameter-free marginal fisher analysis based on L_2,1-norm regularisation for face recognition

Authors: Yu'e Lin; Zhiyuan Ren; Xingzhu Liang; Shunxiang Zhang

Addresses: College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China ' College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China ' College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China; Institute of Environment-friendly Materials and Occupational Health, Anhui University of Science and Technology, Wuhu, Anhui, China ' College of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China

Abstract: Marginal fisher analysis is an effective feature extraction algorithm for face recognition, but the algorithm is sensitive to the influence of the neighbourhood parameter setting, and does not have the function of feature selection. In order to solve the above problems, this paper proposes a parameter-free marginal discriminant analysis based on L_2,1-norm regularisation (PFMDA/L_2,1). The algorithm calculates the weights using the cosine distance between samples and dynamically determines neighbours of each data point so that it does not set any parameters. In order to enable both feature extraction and feature selection to proceed simultaneously, two optimisation models with the L_2,1-norm constraint are presented and then the complete solution for PFMDA/L_2,1 is given. The experimental results on the ORL, YaleB and AR face databases show that the proposed method is feasible and effective.

Keywords: marginal fisher analysis; MFA; feature extraction; feature selection; parameter-free; L_2,1-norm regularisation; cosine distance; face recognition; neighbourhood parameter setting; dynamically.

DOI: 10.1504/IJCSE.2023.129740

International Journal of Computational Science and Engineering, 2023 Vol.26 No.2, pp.210 - 219

Received: 26 Jul 2021
Accepted: 24 Nov 2021
Published online: 22 Mar 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article