International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
Smart Emotion-Based Activity Recommendation System Using Convolutional Neural Network Sindhiya R1, Akash A2, Eswar M S3 1Assistant Professor, Dept. of Computer Science of Engineering, K.L.N. College of Engineering, Tamil Nadu, 2Student, Dept. of Computer Science of Engineering, K.L.N. College of Engineering, Tamil Nadu, India
3 Student, Dept. of Computer Science of Engineering, K.L.N. College of Engineering, Tamil Nadu, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Facial expressions play a crucial role in non-
be found in various domains such as autonomous vehicles, healthcare monitoring, entertainment, education, and security systems.
verbal communication and are an essential component of social interaction. Recognizing emotions through facial expressions has become a significant research area with applications in self-driving cars, entertainment, healthcare, and security systems. Emotion recognition systems (ERS) serve as a vital part of human–machine interaction, enabling computers to understand and respond to human feelings effectively. Recognizing emotions is a challenging task for machines due to variations in facial features, lighting conditions, and individual expressions. To address these challenges, the proposed Smart Emotion-Based Activity Recommendation System Using Convolutional Neural Network (CNN) employs deep learning for precise emotion classification. The system performs four main processes—face detection, preprocessing, feature extraction, and classification. A single CNN model is trained to detect emotions such as happiness, sadness, anger, fear, surprise, and neutral states from real-time camera feeds or uploaded images. Once the emotion is identified, Gemini AI provides personalized activity recommendations such as songs, movies, hobbies, or motivational quotes that align with the detected mood. This integration of CNN-based emotion detection and AI-driven activity suggestion enhances user engagement and promotes emotional well-being. The proposed system demonstrates high accuracy and reliability, making it suitable for real-world applications in mental health support, intelligent user interfaces, and adaptive entertainment systems.
Emotion recognition through facial expressions is a challenging task because human emotions vary depending on environmental factors, lighting, pose, and cultural differences. Traditional machine learning approaches rely on handcrafted feature extraction techniques, which often limit accuracy and adaptability. With the evolution of deep learning, Convolutional Neural Networks (CNNs) have proven highly effective for image-based emotion classification due to their ability to automatically learn spatial features from facial images. The proposed Smart Emotion-Based Activity Recommendation System uses a single CNN model for emotion recognition. The system captures facial expressions through a real-time camera feed or uploaded image, preprocesses the data, extracts features, and classifies the emotion into predefined categories such as happiness, sadness, anger, fear, surprise, and neutral. Once the emotion is identified, Gemini AI is used to recommend suitable activities such as songs, movies, hobbies, or motivational quotes to enhance the user’s emotional state. The combination of CNN-based emotion recognition and Gemini AI-driven recommendations creates a dynamic and interactive environment that supports mental well-being and personalized engagement. This research aims to contribute to the development of intelligent systems that understand human emotions and respond in a context-aware manner.
Key Words: Emotion Recognition, Convolutional Neural Network, Gemini AI, Activity Recommendation, RealTime Detection, Mental Health Support, HumanComputer Interaction.
1.2 OBJECTIVE AND SCOPE OF THE PROJECT
1.INTRODUCTION
The main objective of this project is to design and implement a Smart Emotion-Based Activity Recommendation System capable of detecting human emotions in real time and suggesting suitable activities to improve user engagement and mental well-being. The system utilizes a single Convolutional Neural Network (CNN) model for facial emotion recognition using live webcam feeds or uploaded images, accurately classifying emotions such as happiness, sadness, anger, fear, surprise, and neutral. Once the emotion is identified, Gemini AI is integrated to provide personalized
Facial expressions play a crucial role in non-verbal communication and form an important aspect of social interaction. The ability to recognize human emotions through facial cues has become an emerging research area in the field of computer vision and artificial intelligence. Emotion recognition systems (ERS) help machines understand human feelings and react accordingly, enabling a more natural and effective form of Human-Machine Interaction (HMI). Applications of emotion recognition can
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 433