Facial Emotion Recognition (FER) is a pivotal component of Affective Computing, enabling machines to interpret human psychological states. Traditional FER systems often operate in isolation, lacking real-time interactive feedback or user engagement mechanisms. In this paper, we propose "Bio Vision," an end-to-end real-time emotion detection system integrated with a gamified and interactive web interface. The proposed system utilizes a Convolutional Neural Network (CNN) trained on facial expression datasets to classify seven universal emotions: Angry, Disgust, Fear, Happy, Neutral, Sad, and Surprise. Faces are continuously detected using Haar Cascade Classifiers via OpenCV, and predictions are served through a lightweight Flask API. The frontend architecture employs dynamic data visualization, bilingual voice feedback (English and Hindi), and emotion-responsive gamification, where game mechanics adapt dynamically to the user's emotional state. Experimental results indicate robust real-time performance with minimal latency, demonstrating the system's viability for applications in mental health monitoring, human-computer interaction, and digital well-being.
Facial Emotion Recognition, Convolutional Neural Networks (CNN), Affective Computing, Gamification, Human-Computer Interaction (HCI), Computer Vision, OpenCV.
IRE Journals:
Avnish Kumar, Keshav Kumar, Tajendra Riya, Prof. (Dr.) Sanjay Pachauri "BioVision: A Secure and Accurate AI Framework for Visual Facial Expression Analysis" Iconic Research And Engineering Journals Volume 9 Issue 10 2026 Page 1440-1445 https://doi.org/10.64388/IREV9I10-1716225
IEEE:
Avnish Kumar, Keshav Kumar, Tajendra Riya, Prof. (Dr.) Sanjay Pachauri
"BioVision: A Secure and Accurate AI Framework for Visual Facial Expression Analysis" Iconic Research And Engineering Journals, 9(10) https://doi.org/10.64388/IREV9I10-1716225