Facial Expression Recognition Using Sparse Complex Matrix Factorization with Ridge Term Regularization

Putri, Diyah Utami Kusumaning and Musdholifah, Aina and Makhrus, Faizal and Duong, Viet Hang and Phuong, Le Thi and Chen, Bo Wei and Wang, Jia Ching (2021) Facial Expression Recognition Using Sparse Complex Matrix Factorization with Ridge Term Regularization. In: 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE), 12-15 October 2021, Kyoto, Japan.

Full text not available from this repository. (Request a copy)

Abstract

This work proposes a novel method of matrix factorization on the complex domain to obtain both extracted features and coefficient matrix with high recognition results in facial expression recognition. The real data matrix is transformed into a complex number based on the Euler representation of complex numbers. Sparse regularization in dimensionality reduction using ridge term (L2-norm) is applied into this study. Basic complex matrix factorization (CMF) is modified into sparse complex matrix factorization using ridge term (SCMF-L2) which adding sparse L2-norm constraint in the coefficient. The gradient descent method is used to solve optimization problems. Experiments on facial expression recognition scenario reveal that the proposed methods provide better recognition results that prevalent NMF and CMF methods. © 2021 IEEE.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Cited by: 2
Uncontrolled Keywords: Face recognition; Gradient methods; Matrix algebra; Complex matrix factorization; Complex matrixes; Complex number; Facial expression recognition; Features extraction; L2-norm; Matrix factorizations; Nonnegative matrix factorization; Novel methods; Regularisation; Non-negative matrix factorization
Subjects: Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Mathematics and Natural Sciences > Computer Science & Electronics Department
Depositing User: Sri JUNANDI
Date Deposited: 10 Oct 2024 03:25
Last Modified: 10 Oct 2024 03:25
URI: https://ir.lib.ugm.ac.id/id/eprint/8648

Actions (login required)

View Item
View Item