Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper addresses facial emotion recognition by merging three datasets (CK+, FER+, KDEF) and employing data augmentation and random weighted sampling to mitigate class imbalance. The approach leverages deep convolutional networks for feature extraction and classification. The proposed method achieves 82% accuracy in recognizing seven basic emotions, demonstrating improved performance compared to training on individual datasets.
Training a single emotion recognition model on merged datasets with balanced sampling beats individual dataset training, achieving 82% accuracy.
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.