Pairwise dependency-based robust ensemble pruning for facial expression recognition

Xing Chen

doi:10.1007/s11042-023-16756-1

Pairwise dependency-based robust ensemble pruning for facial expression recognition

2023-09-27

0

PRE

AI

DOI：10.1007/s11042-023-16756-1

原文链接

原文求助

摘要

En 中文

Facial expression recognition is crucial in analyzing an individual's emotional state. Ensemble pruning becomes essential to enhance the effectiveness of this recognition by selecting appropriate classifiers from a pool of base classifiers. However, outliers and noise within the classifiers can adversely affect the final recognition results and the generalization performance of the selected subset of classifiers. Additionally, effectively combining accuracy and low redundancy of base classifiers remains a challenging problem that requires further investigation. In this paper, we propose a novel algorithm called Pairwise Dependency-based Robust Ensemble Pruning (PDREP) to address these issues. The PDREP algorithm treats the predicted results of classifiers for sample instances as features of the classifier and evaluates their dependencies between pairs of classifiers using mutual information. By incorporating this dependency measure into the regression-based objective equation, we can assess the redundancy of a subset of base classifiers and prune redundant classifiers. We use the l(2,1-)norm in PDREP's objective equation to perform robust classifier pruning while considering the base classifiers' dependencies and accuracy. Furthermore, we introduce weight control parameters to balance accuracy and dependencies, facilitating the elimination of ineffective and redundant classifiers. The results show significant improvements when evaluating the proposed method's recognition accuracy on five public face sentiment datasets (FER2013, JAFFE, CK+, RaFD, and KDEF). Specifically, the proposed method achieves 3.15%, 9.39%, 1.72%, 3.70%, and 4.70% higher accuracy than integrating all base classifiers, respectively. Extensive experiments conducted on five facial expression datasets demonstrate that the proposed method consistently outperforms existing state-of-the-art ensemble pruning algorithms in most cases.

Keyword:

Facial expression recognition

Classifier ensemble pruning

Classifier dependency

1-norm

Pairwise dependency-based robust ensemble pruning for facial expression recognition

摘要

期刊

机构

引用论文