Real-Time Emotion Detection and Recommendation System

Emotion recognition plays a crucial role in enhancing human–computer interaction by enabling systems to understand and respond to user emotions effectively. This paper presents a real-time facial emotion detection and intelligent recommendation system using deep learning techniques. The proposed system utilizes a Convolutional Neural Network (CNN) trained on grayscale facial images to classify emotions into four categories: Angry, Happy, Neutral, and Sad. The model is trained on a balanced dataset to ensure unbiased learning across all classes. Extensive preprocessing and data handling techniques are applied to improve model generalization. The system captures real-time video input, detects facial features, and predicts emotions dynamically, followed by generating appropriate recommendations based on the detected emotional state. Experimental results demonstrate a significant improvement in model performance, achieving an accuracy of 75%, compared to an earlier baseline of 68%, highlighting the effectiveness of the proposed approach. The system is efficient, scalable, and suitable for real-world applications such as mental health monitoring, personalized user interaction, and smart assistive systems