Visual Harmonies: Investigating the Impact of Album Cover Image Features on Music Genre Image Classification for Top Spotify Artists in the USA

McGrane, Cian (2024) Visual Harmonies: Investigating the Impact of Album Cover Image Features on Music Genre Image Classification for Top Spotify Artists in the USA. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This research explores the potential of image classification models to identify music genres from album cover features, using data from the most popular Spotify artists in the United States. This research compares the efficacy of the k-nearest neighbour (KNN) and support vector machines (SVM) models in classifying genres based on two types of features: most dominant colour (MDC) and pixel intensity histograms (PIH). Data was sourced from a Kaggle dataset containing artist information and the Spotify API for gathering album cover images. The MDC features were extracted using k-means clustering, while PIH features were derived from pixel intensity distributions. Both features were transformed into 3x3 RGB images to standardise the input for the models. The KNN model achieved an overall accuracy of 63% with MDC features and 62% with PIH features, while the SVM ensemble model, combining MDC and PIH features, demonstrated superior performance with 75% accuracy, Key findings reveal that image features can effectively distinguish music genres, offering a novel approach to music classification. Future work will focus on refining feature extraction techniques and exploring the potential for commercial applications in music recommendation systems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Zahoor, Sheresh UNSPECIFIED
Uncontrolled Keywords:	Image classification; feature extraction; music; album artwork; KNN; SVM
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 Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jun 2025 13:44
Last Modified:	18 Jun 2025 13:44
URI:	https://norma.ncirl.ie/id/eprint/7919

Actions (login required)

View Item