FACIAL EMOTION RECOGNITION USING SHALLOW CONVOLUTIONAL NEURAL NETWORK AND IMPROVED FER-2013 DATASET

Abdurahmon Kurbanov

Authors

Kurbanov Abdurahmon Alishboyevich Jizzakh branch of National University of Uzbekistan named after Mirzo Ulugbek

Keywords:

CNN, FER-2013, Machine learning, Deep learning, model, CNN architecture, OpenCV

Abstract

It is very easy and simple for a person to sense his inner feelings by looking at his face. That is, in the process of evaluating the emotional state of the person standing in front of him, the human brain sees the facial structure of the other person and can quickly analyze it. However, the ability of a computer to understand and respond to human emotions is considered one of the most difficult problems in the fields of modern computer vision and deep learning. Despite the fact that many studies have been carried out on the evaluation of the emotional state of a person, the proposed solutions are not effective enough. Several convolutional neural network models developed in this field can also solve the problem in a rather narrow scope. In this article, we proposed a shallow convolutional neural network and an augmented and improved fer-20103 dataset in order to speed up the training process and improve previous results. The proposed architecture was tested and analyzed on an updated dataset.

References

A. Mollahosseini, B. H. (2019). AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild. IEEE Transactions on Affective Computing, vol. 10, 18-31.

Ahmed, N. a. (2023). A systematic survey on multimodal emotion recognition using learning algorithms. Intell. Syst. Appl. 17, 200171.

Arafin, S. a. (2024). Enhancing the ability to recognize facial expressions in young children: A method using few-shot learning and cross-dataset validation. 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), (pp. 640-645).

Chouhayebi H, M. M. (2024). Human Emotion Recognition Based on Spatio-Temporal Facial Features Using HOG-HOF and VGG-LSTM. Computers, 101.

Ekman, P. a. (1978). Facial action coding systems. Consulting Psychologists Press.

Khaireddin, Y. a. (2021). Facial emotion recognition: State of the art performance on FER2013. arXiv preprint arXiv:2105.03588.

Kurbanov A. A. (2024). Inson tanasi harakatlarini tahlil qilishda zamonaviy modellar va algoritmlarni qo ‘llashni o ‘rganish. Al-Farg’oniy avlodlari, 169-175.

Kurbanov A. A. (2024). Inson yuz tasviridan hissiyotlarni aniqlash uchun geomertik xususiyatlarini va tashqi ko ‘rinishga asoslangan xususiyatlarini ajratib olish. Al-Farg’oniy avlodlari, 61-67.

Kurbanov, A. (2024). Chuqur o‘rganishga asoslangan yuz tahlili: xususiyatlarni ajratib olish va his-tuyg‘ularni tushunish. Международный Журнал Теоретических и Прикладных Вопросов Цифровых Технологий, 68-76.

Lucey, P. e. (2010). The extended cohn-kanade dataset (ck+): A complete dataset for action unit and emotion-specified expression. IEEE.

Mao, A. M. (2023). Cross-entropy loss functions: Theoretical analysis and applications. International conference on Machine learning, (pp. 23803-23828).

Minaee, S. a. (2021). Deep-emotion: Facial expression recognition using attentional convolutional network. Sensors, 30-46.

Nojavanasghari, B. B. (2016). Emoreact: a multimodal approach and dataset for recognizing emotional responses in children. Proceedings of the 18th acm international conference on multimodal interaction, 137-144.

Oguine, O. C. (2022). Hybrid facial expression recognition (FER2013) model for real-time emotion classification and prediction. arXiv preprint arXiv:2206.09509.

P. Lucey, J. F. (2010). The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression,. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, San Francisco, CA, USA, 94-101.

Ruan, H. T. (2022). Efficient sub-pixel convolutional neural network for terahertz image super-resolution. Optics letters, 3115-3118.

Tutuianu, G. I. (2024). Benchmarking deep facial expression recognition: An extensive protocol with balanced dataset in the wild. Engineering Applications of Artificial Intelligence.

Zahara, L. M. (2020). The facial emotion recognition (FER-2013) dataset for prediction system of micro-expressions face using the convolutional neural network (CNN) algorithm based Raspberry Pi. Fifth international conference on informatics and computing (ICIC) (pp. 1-9). IEEE.