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{196492,
        author = {T. PAVAN KUMAR and P. DINESH KUMAR and Dr T. Surendra Natha Reddy},
        title = {A SUSTAINABLE AND SCALABLE AI MODEL FOR FACIAL EMOTION DETECTION IN ANDROID APPLICATIONS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {4796-4801},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196492},
        abstract = {The emotion detection is the key requirement in the field of human-computer interaction. There has been considerable interest in the application areas of mental health, smart educational environments, and user experience. However, the traditional process of emotion detection is time-consuming, wherein the task is carried out manually, through surveys, or rule-based techniques that are not efficient. Therefore, to overcome these problems, the current project aims to develop FACE FEEL AI, which is an emotion classification system for the Android platform, employing image learning models to perform facial emotion detection. The proposed system allows a user to recognise emotions in the facial image taken by the mobile camera or choose from the album. A machine learning model trained by Teachable Machine is embedded in the Android App in order to classify emotions such as happiness, sadness, anger, surprise, and neutrality. In this system, the input image is pre-processed for emotion recognition in the mobile environment. FACE FEEL AI is intended to be lightweight, fast, and friendly to use so as to run with ease in real-time without requiring any specialised hardware or any controlled environment. The application will offer immediate results of emotion recognition through an interactive interface. This increases accuracy, consistency, and accessibility as opposed to human intervention, which is analysed through automation in the proposed system. The tool provides a realistic and efficient approach towards the problem of detecting emotions. The tool would greatly benefit areas such as the provision of mental health assistance, smart learning platforms, and intelligent human computer interaction systems.},
        keywords = {Emotion Classification, Facial Emotion Recognition, Android Application, Image Learning Models, Teachable Machine, Real-Time Emotion Detection, Camera and Gallery Images.},
        month = {April},
        }