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{199259,
        author = {Mangalapally Sai Sri harsha and A.Hansika Reddy and B. Abhilash Reddy, and D. Pranav Aditya and Ms.V.Bhavya},
        title = {REAL-TIME EMOTION DETECTION USING RESIDUAL MASKING NETWORK},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12373-12378},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199259},
        abstract = {Human emotions are important for how we communicate and make decisions. The ability of machines to understand emotions in real time is becoming very important in areas like healthcare, education, and how people interact with computers. This paper introduces a real- time emotion detection system that uses a Residual Masking Network (RMN). It combines deep learning with attention mechanisms to make the system more accurate and efficient. The system takes live video input, detects facial features, and categorizes emotions into types such as happiness, sadness, anger, fear, surprise, and neutrality. Unlike older systems, this model uses residual learning to overcome some training issues and masking techniques to focus on important parts of the face. The system is designed for real-time performance with low delay and ensures privacy through secure data handling.
The experimental results show that this approach has higher accuracy, better performance under different conditions, and efficient real-time processing. This system offers a scalable and reliable solution for emotion recognition tasks.},
        keywords = {},
        month = {April},
        }