Authors : Aadi Gupta

Volume/Issue : Volume 9 - 2024, Issue 11 - November

Google Scholar : https://tinyurl.com/37ze3ccz

Scribd : https://tinyurl.com/2s48dccw

DOI : https://doi.org/10.38124/ijisrt/IJISRT24NOV819

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The ability to 'read' human emotions is a crucial component of effective human-computer interaction. I believe my research introduced a cutting-edge image recognition model that accurately identifies facial expressions and corresponding emotional states. Leveraging deep learning techniques, specifically convolutional neural networks (CNNs), my model is trained on a comprehensive dataset containing a diverse range of facial expressions and emotional states. The dataset encompassed variations across different demographics, including age, ethnicity, and gender, to ensure the robustness and generalizability of the model. Here, the methodology involved preprocessing images to normalize lighting and facial orientation before feeding them into our multi-layered CNN architecture. We employed data augmentation strategies to enhance the model's ability to generalize from limited data. We evaluated the performance of the model through various metrics, including accuracy, precision, recall, and F1-score, using a separate validation dataset. Additionally, we analyzed the model's performance across different emotional categories, such as happiness, sadness, anger, and surprise. The research demonstrated the exceptional accuracy of our model in recognizing facial expressions and emotions, surpassing existing models in handling real-world scenarios. These findings contributed to the field by providing insights into the effectiveness of modern deep learning techniques for emotion recognition and offer potential applications in areas such as human-computer interaction, mental health monitoring, and user experience enhancement. Future research is needed that will focus on refining the model and exploring its integration into interactive systems.

Keywords : Image Recognition Model, Convolutional Neural Networks, F1-Score, Emotion Recognition.

References :

1. Kaggle. (2024). Facial Expression Challenge Dataset. Retrieved from https://www.kaggle.com/c/facial-expression-recognition-challenge
2. Ekman, P. (2013). Facial expressions and emotion. Guilford Publications.
3. Lyons, M., Ellis, D., Ambrožová, J., Zheng, Q., & Littlewort, G. (2010). Facial expression recognition: History, advances, and future challenges. International Journal of Computer Vision, 97(1), 16-35.
4. Yu, Z., Zhang, C., Yan, Y., Lei, Z., & Li, S. (2019). Deep learning for real-time facial expression recognition: A comprehensive survey. arXiv preprint arXiv:1904.08330.
5. Akter, T., Ali, M., Khan, M., Satu, M., Uddin, M., Alyami, S., … & Moni, M. (2021). Improved transfer-learning-based facial recognition framework to detect autistic children at an early stage. Brain Sciences, 11(6), 734. https://doi.org/10.3390/brainsci11060734
6. Alrimy, T. (2023). Facial expression recognition based on well-known convnet architectures. Journal of King Abdulaziz University-Computing and Information Technology Sciences, 12(1). https://doi.org/10.4197/comp.12-1.5
7. Dangi, D., Bhagat, A., & Dixit, D. (2022). Emerging applications of artificial intelligence, machine learning and data science. Computers Materials & Continua, 70(3), 5399-5419. https://doi.org/10.32604/cmc.2022.020431
8. Lin, Q., He, R., & Jiang, P. (2020). Feature guided cnn for baby’s facial expression recognition. Complexity, 2020, 1-10. https://doi.org/10.1155/2020/8855885
9. Sarma, P., Laskar, T., Gowda, D., & Ramesha, M. (2022). Human emotion recognition using deep learning with special emphasis on infant’s face. International Journal of Electrical and Electronics Research, 10(4), 1176-1183. https://doi.org/10.37391/ijeer.100466.
10. Talegaonkar, I., Joshi, K., Valunj, S., Kohok, R., & Kulkarni, A. (2019). Real time facial expression recognition using deep learning. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.3421486.
11. Triwijoyo, B., Adil, A., & Anggrawan, A. (2021). Convolutional neural network with batch normalization for classification of emotional expressions based on facial images. Matrik Jurnal Manajemen Teknik Informatika Dan Rekayasa Komputer, 21(1), 197-204. https://doi.org/10.30812/matrik.v21i1.1526.