Expression-Based Music Recommendation
Machine Learning
Android app that reads facial expression through the camera and recommends music matching the detected mood. Basis for a published paper.
Overview
An Android application integrating CNN-based facial expression recognition. It performs real-time emotion detection through the device camera and maps detected moods to music recommendations. The underlying model was published in IRJET in 2021.
Role
Built the Flutter application and integrated the CNN model, including the optimisation work for on-device inference.
The hard part
Running inference on-device in real time. The model had to be optimised for mobile deployment, trading accuracy against latency to stay responsive on commodity Android hardware.
Architecture
Flutter application with the expression recognition model running on-device. Detected emotion categories drive the recommendation step.
Stack
Flutter · CNN · Python · Computer Vision