• Version
• Download 20
• File Size 296.56 KB
• File Count 1
• Create Date 1 April 2025
• Last Updated 1 April 2025

RECOGNISING FACIAL EMOTIONS THROUGH ATTENTION MECHANISM AND SONG RECOMMENDATION

 

 

 

Authors:

Dr.P.Radha

Asst.Prof.,Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore. Email- radhap@skasc.ac.in

S.Hariharan

UG Student, Department of Computer Science, Sri Krishna Arts and Science College, Coimbatore. Email – s.hariharan250803@gmail.com

 

 

 

ABSTRACT

Facial Emotion Recognition (FER) plays a critical role in human-computer interaction, allowing systems to understand, interpret, and respond to human emotions effectively. However, traditional FER models face significant challenges, including variations in facial expressions, lighting conditions, occlusions, and head poses, which can reduce recognition accuracy. To address these issues, this paper proposes an advanced FER system that integrates an attention mechanism with deep learning models to enhance both accuracy and robustness. The attention mechanism dynamically prioritizes key facial features, ensuring the model focuses on the most relevant regions for emotion detection. Additionally, we incorporate a personalized song recommendation system, where the recognized emotions serve as input to suggest mood-based music, enhancing user experience. Our approach employs a hybrid deep learning model, combining convolutional neural networks (CNNs) and attention mechanisms for feature extraction, followed by a collaborative filtering-based recommendation system.  Experimental results demonstrate high accuracy in emotion recognition and strong user satisfaction in music recommendations. This work contributes to affective computing, with applications in mental health support, entertainment, and intelligent user interfaces.

Keywords - Facial Emotion Recognition, Attention Mechanism, Deep Learning, Song Recommendation, Affective Computing, Human-Computer Interaction.

Download