Journals / Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi / 2026 / Cilt: 39 Sayı: 1

Improving Facial Expression Detection Using Convolutional Neural Networks and Analysis of Education Efficiency

Evrişimli Sinir Ağları Kullanılarak Duygu Durum Tespitinin İyileştirilmesi ve Eğitim Verimliliğinin Analizi

Berkay Çakmak(ERCİYES ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)
İbrahim Develi(ERCİYES ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)0000-0001-5878-677X
Pages
37–43
Publication Date
2023-05-02
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Thanks to the presented report, the emotional states of the listeners are analyzed according to time, thereby increasing the educational efficiency.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this paper, a convolutional neural network model (CNN) with higher accuracy than other models in the literature is proposed to detect facial emotional expressions.
📊
Key Findings & Data:To train the convolutional neural network model, the FER2013 dataset consisting of 30,000 images and human faces in seven emotion categories was used.
💡
Conclusion & Impact:Thanks to the presented report, the emotional states of the listeners are analyzed according to time, thereby increasing the educational efficiency.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Evrişimli Sinir Ağları · Yüz duygu ifadeleri tanımlama · FER2013 veri seti

Abstract

In this paper, a convolutional neural network model (CNN) with higher accuracy than other models in the literature is proposed to detect facial emotional expressions. To train the convolutional neural network model, the FER2013 dataset consisting of 30,000 images and human faces in seven emotion categories was used. The training accuracy of the model was 97.83% and the test accuracy was 83.52%. In training and presentations made over the Internet; The emotional states of the listeners are detected in real time with the developed CNN model, and an algorithm has been developed that allows the emotional intensity of the participants to be reported to the presenter on a time basis during the training and at the end of the training with the designed algorithm. Thanks to the presented report, the emotional states of the listeners are analyzed according to time, thereby increasing the educational efficiency.

Özet

Bu çalışmada, yüzdeki duygu ifadelerini tespit etmek için literatürdeki diğer modellerden daha yüksek doğruluk oranına sahip bir evrişimli sinir ağı modeli (CNN) önerilmiştir. Evrişimli sinir ağı modelini eğitmek için yedi duygu kategorisinde insan yüzleri içeren ve 30.000 imge’den oluşan FER2013 veri seti kullanılmıştır. Modelin eğitim doğruluğu %97,83 ve test doğruluğu %83,52 olarak elde edilmiştir. İnternet üzerinden yapılan eğitim ve sunumlarda; dinleyicilerin duygu durumları, geliştirilen CNN modeli ile gerçek zamanlı olarak tespit edilmekte ve tasarlanan algoritma ile eğitim süresince ve eğitimin sonunda katılımcıların duygu yoğunlukları sunucuya zaman bazlı olarak rapor halinde sunulmasını sağlayan bir algoritma geliştirilmiştir. Sunulan rapor sayesinde dinleyicilerin zamana göre duygu durumları analiz edilerek eğitim verimliliği artırılmaktadır.

🔖

Cite This Article

Çakmak, B., Develi, İ. (2023). Improving Facial Expression Detection Using Convolutional Neural Networks and Analysis of Education Efficiency. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, Cilt: 39 Sayı: 1, 37–43. https://ajindex.com/articles/928256

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  1. Mellouk, W., Wahida H. 2020.Facial emotion recognition using deep learning: review and insights. Procedia Computer Science 175 (2020): 689-694.
  2. Ekman, P., Wallace V. F. 1971. Constants across cultures in the face and emotion. Journal of Personality and Social Psychology 17.2 (1971): 124.
  3. Ko, B. C. 2018. A brief review of facial emotion recognition based on visual information. Sensors 18.2 (2018): 401.
  4. Altekin, F., Demir, H. 2021. Emotion Detection from Facial Expression Using Different Feature Descriptor Methods with Convolutional Neural Networks. European Journal of Engineering and Applied Sciences 4.1 (2021): 14-17.
  5. Cakmak, B., Develi, I. 2023. Convolutional Neural Network-Based Classification of Facial Emotional Expressions and Computational Complexity Analysis. International Conference on Frontiers in Academic Research. Vol. 1. (2023) 168-173.
  6. Mehendale, N. 2020. Facial emotion recognition using convolutional neural networks (FERC). SN Applied Sciences 2.3 (2020): 1-8.
  7. Kim, J., Hwan, A. P., Dong, S. H. 2021. The extensive usage of the facial image threshing machine for facial emotion recognition performance. Sensors 21.6 (2021): 2026.
  8. Tümen, V., Söylemez, Ö. F., Ergen, B. 2017. Facial emotion recognition on a dataset using convolutional neural network. 2017 International Artificial Intelligence and Data Processing Symposium (IDAP). IEEE, (2017).
  9. Zahara, L., et al. 2020. The facial emotion recognition (FER-2013) dataset for prediction system of microexpressions face using the convolutional neural network (CNN) algorithm based Raspberry Pi. 2020 Fifth international conference on informatics and computing (ICIC). IEEE, (2020).
  10. Lasri, I., Solh, A. R., El Belkacemi, M. 2019. Facial emotion recognition of students using convolutional neural network. 2019 third international conference on intelligent computing in data sciences (ICDS). IEEE, (2019).
  11. Georgescu, M. I., Ionescu, R. T., Popescu, M. 2019. Local learning with deep and handcrafted features for facial expression recognition. IEEE Access 7 (2019): 64827-64836.
  12. Connie, T., et al. 2017. Facial expression recognition using a hybrid CNN–SIFT aggregator. International Workshop on Multi-disciplinary Trends in Artificial Intelligence. Springer, Cham, (2017).
  13. Wang, W., et al. 2020. Emotion recognition of students based on facial expressions in online education based on the perspective of computer simulation. Complexity (2020).
  14. Viola, P., Jones M. 2001. Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR (2001). Vol. 1. IEEE, 2001.