Facial Emotion Recognition Based on Resnet-18 Model

Hamed M suliman

المؤلفون

Hamed M suliman High Institute of Science and Technology Misrata Libya

الكلمات المفتاحية:

Face emotion recog-nition، accuracy، training

الملخص

This paper introduces an efficient computational method capable of real-time facial expression analysis, extracting features and classifying seven distinct emotional states from static images. To bridge the gap between traditional recognition and robust automated analysis, we propose an optimized deep learning framework based on the ResNet18 architecture. The model employs a hybrid transfer learning approach and enhances generalization through strategic data augmentation. Furthermore, the architecture leverages the skip connections inherent in ResNet to maintain feature integrity. Trained on the CK+ dataset, the model achieved a state-of-the-art accuracy of 98.4%.

المراجع

-Tatikonda Lakshman, 2. S. (2022). FACIAL EMOTION DETECTION AND RECOGNITION. (pp. Issue 11 | ISSN: 2456-3315). IJRTI | Volume 7.

-A.Saravanan, G. P. (2020). Facial Emotion Recognition using Convolutional Neural Networks. Cornell university.

-Bin Li1, #. R. (2021). Facial expression recognition via ResNet-18. International Conference on Multimedia Technology and Enhanced Learning. Springer.

-H. Zhang, M. A. (2019). A Face Emotion Recognition Method Using Convolutional Neural Network and Image Edge Computing. (p. Volume 7). IEEE Access.

-Mehendale, N. (2020). Facial emotion recognition using convolutional neural networks. Springer Nature Switzerland.

-Mohammad A. Haghpanah, E. S. (22 March 2022). Real-Time Facial Expression Recognition using. International Conference on Machine Vision and Image. Ahvaz, Iran, Islamic Republic of: ieeexplore.ieee.org.

-Noha A. El Hag1 · Walid El Shafai2, 3. ·. S. (9/9/2025). Enhanced Facial Emotion Recognition and Age. Int J Comput Intell Syst.

-P. Tarnowski, M. A. (2017). Emotion recognition using facial expressions. International Conference on Computational Science, ICCS (pp. 12-14). Elsevier.

-W. Mellouka, w. H. (2020). Facial emotion recognition using deep learning: review and insights. The 2nd International Workshop on the future of Internet of Every thing (FIoE) (pp. 689-694). Elsevier.