Research Article

Human Emotion Classification Using Facial Expressions and CNN Models

by  Alishana Thorat, Kanishka Panpatil, Selvavani Mathavan, Sneha Kushwaha, Savita Sangam
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Issue 14
Published: June 2025
Authors: Alishana Thorat, Kanishka Panpatil, Selvavani Mathavan, Sneha Kushwaha, Savita Sangam
10.5120/ijca2025925115
PDF

Alishana Thorat, Kanishka Panpatil, Selvavani Mathavan, Sneha Kushwaha, Savita Sangam . Human Emotion Classification Using Facial Expressions and CNN Models. International Journal of Computer Applications. 187, 14 (June 2025), 22-26. DOI=10.5120/ijca2025925115

                        @article{ 10.5120/ijca2025925115,
                        author  = { Alishana Thorat,Kanishka Panpatil,Selvavani Mathavan,Sneha Kushwaha,Savita Sangam },
                        title   = { Human Emotion Classification Using Facial Expressions and CNN Models },
                        journal = { International Journal of Computer Applications },
                        year    = { 2025 },
                        volume  = { 187 },
                        number  = { 14 },
                        pages   = { 22-26 },
                        doi     = { 10.5120/ijca2025925115 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2025
                        %A Alishana Thorat
                        %A Kanishka Panpatil
                        %A Selvavani Mathavan
                        %A Sneha Kushwaha
                        %A Savita Sangam
                        %T Human Emotion Classification Using Facial Expressions and CNN Models%T 
                        %J International Journal of Computer Applications
                        %V 187
                        %N 14
                        %P 22-26
                        %R 10.5120/ijca2025925115
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

This project aims to teach machines how to recognize human emotions by analysing facial expressions. Using deep learning and the pre-trained VGG16 model, our system identifies six key emotions: happiness, sadness, anger, fear, surprise, and disgust. This system applies transfer learning, data augmentation, and class balancing to improve accuracy and performance. The result is a reliable emotion detection model that can support real-world applications like mental health monitoring, smart assistants, and interactive learning tools.

References
  • F Ghaffar, 'Facial Emotions Recognition using Convolutional Neural Net' arXiv preprint arXiv:2001.01456, Jan. 2020. [Online].
  • A. V Savchenko, 'Facial expression and attributes recognition based on multi-task learning of lightweight neural networks' arXiv preprint arXiv: 2103.17107, Mar.2021. [Online]
  • A Saroop, S. K. S Gupta, S. K. S Gupta, 'Facial Emotion Recognition: A multi-task approach using deep learning' arXiv preprint arXiv: 2110.15028, Oct 2021. [Online].
  • A. Chaudhari, A. Agrawal and S Joshi ‘ViTFER: Facial Emotion Recognition with Vision Transformers’, Journal of Imaging 5 (4) (2022) 80. [Online]
  • S Kaur and N Kulkarni, ‘FERFM: An Enhanced Facial Emotion Recognition System Using Fine Tuned MobileNetV2 Architecture’, IETE Journal of Research 10 (2023) 415-418. [Online]
  • R Zhang, ‘Facial emotion detection based on improved VGG-16’, Applied and Computational Engineering 2 (3) (2023) 45-50. [Online].
  • A R Angeline, A N Alice, ‘Multimodal Human Facial Emotion Recognition Using DenseNet-161 and Image Feature Stabilization Algorithm’ Traitement du Signal 39 (6) (2022)
  • S Nathani, ‘A Comparative Study of Transfer Learning for Emotion Recognition using CNN and Modified VGG16 Models’ arXiv preprint
  • El Boudouris, Y., & Bohi, A. (2025, January). EmoNeXt: An adapted ConvNeXt for facial emotion recognition. arXiv preprint arXiv:2501.08199. [Online]. Available: arXiv: 2501.08199.
  • Doe, J., & Smith, J. (2023, March). Deep emotion recognition: A comprehensive review of current approaches and future directions. Journal
  • Davis, E., & Johnson, M. (2024, June). Real-time facial emotion recognition using lightweight CNNs. Proceedings of the IEEE.
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Emotion detection facial expressions deep learning VGG16 transmission learning convolutional neural network (CNN) data augmentation class imbalance.

Powered by PhDFocusTM