Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171904,
        author = {Shishir Ganesh Shetty and Suhas R Bhat and P V Manjunath and Shivananda V Seeri},
        title = {Facial Emotion Detection Using CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {1432-1436},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171904},
        abstract = {The growing need for real-time emotion analysis has significantly driven advancements in facial emotion recognition (FER) systems. This study explores the use of convolutional neural networks (CNNs) to design a robust FER model utilizing the EfficientNet-B0 architecture. To address challenges such as class imbalance, lighting variability, and occlusions, techniques like Weighted Random Sampler, focal loss, and data augmentation are employed. The system achieves notable accuracy in recognizing emotions such as happiness, sadness, anger, and neutrality. A user-friendly interface, created using Streamlit, enhances accessibility and usability for applications ranging from mental health monitoring to education and customer service. Real-time optimization allows the system to function on resource-constrained devices, bridging the gap between cutting-edge deep learning technology and practical usability. This research highlights how FER systems can improve human-computer interactions and serve as invaluable tools across a variety of industries.},
        keywords = {Facial Emotion Recognition, EfficientNet-B0, Real-Time Detection, Deep Learning, Emotion Analysis.},
        month = {January},
        }