Improving Facial Emotion Recognition through Dataset Merging and Balanced Training Strategies

TL;DR

This paper presents a deep learning approach for facial emotion recognition that merges multiple datasets and employs augmentation and sampling strategies to address data imbalance, achieving 82% accuracy.

Contribution

The study introduces a combined dataset and novel training strategies to enhance the robustness and accuracy of facial emotion recognition models.

Findings

Achieved 82% accuracy in recognizing seven basic emotions.

Effectively mitigated data imbalance with augmentation and sampling.

Demonstrated improved generalization over previous methods.

Abstract

In this paper, a deep learning framework is proposed for automatic facial emotion based on deep convolutional networks. In order to increase the generalization ability and the robustness of the method, the dataset size is increased by merging three publicly available facial emotion datasets: CK+, FER+ and KDEF. Despite the increase in dataset size, the minority classes still suffer from insufficient number of training samples, leading to data imbalance. The data imbalance problem is minimized by online and offline augmentation techniques and random weighted sampling. Experimental results demonstrate that the proposed method can recognize the seven basic emotions with 82% accuracy. The results demonstrate the effectiveness of the proposed approach in tackling the challenges of data imbalance and improving classification performance in facial emotion recognition.