Research
Improving Facial Emotion Recognition through Dataset Merging and Balanced Training Strategies
arXiv:2604.20307v1 Announce Type: new Abstract: In this paper, a deep learning framework is proposed for automatic facial emotion based on deep convolutional networks. In order to increase the general
arXiv:2604.20307v1 Announce Type: new 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.
Related
- Chaotic CNN for Limited Data Image Classification
- Chaos-Enhanced Prototypical Networks for Few-Shot Medical Image Classification
- Robust Diabetic Retinopathy Grading Using Dual-Resolution Attention-Based Deep Learning with Ordinal Regression
- A Resource-Efficient Hybrid CNN-LSTM network for image-based bean leaf disease classification
Source: arXiv cs.CV | 2026-04-23