Music Recommendation System Based On The Analysis Of The Images

Rajdev, Ramam (2024) Music Recommendation System Based On The Analysis Of The Images. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (977kB) | Preview
Preview	PDF (Configuration Manual) Download (755kB) | Preview

Abstract

Music recommendation system plays a significant role in the improvement of the user experience through recommender systems by enabling the listener to discover new artists/genre of music that they have an affinity towards. They are also helpful in the development of the music industry since they contribute to boosting activity, encouraging the subscription to streaming services, and introducing diverse music to the wide audience. The proposed music recommendation system in this research combines deep learning techniques and image analysis in order to provide improved user experience based on the books’ recommendation and the corresponding music dependent on the derived emotional image sentiment. It uses Convolutional Neural Networks (CNNs) to identify emotion from image; models used include Visual Geometry Group 16 (VGG16), Visual Geometry Group 19 (VGG19), CNN & Residual Neural Network 50V2 (ResNet50V2). The highest selected performance accuracy was recorded in the scenario with the ResNet50V2 model at about 73%. While using the VGG19 model, the test set accuracy was about 63%; however, in the case of the custom CNN, the test set accuracy result was significant low of 2% and using VGG16 model similar to the custom CNN model, the test set accuracy was 0%. The identified emotions are matched with the moods and music tracks are suggested from a pool of songs which are maintained from a dataset. This approach does not follow the usual recommendation systems that do not incorporate a user’s immediate emotional status in making recommendations, but rather provides a user-oriented approach.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Tomer, Vikas UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Music Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	25 Aug 2025 10:19
Last Modified:	25 Aug 2025 10:19
URI:	https://norma.ncirl.ie/id/eprint/8614

Actions (login required)

View Item