Exploring 'Artist Image' Using Content-Based Analysis Of Promotional Photos
Jānis Lībeks, Douglas Turnbull · University of Michigan Library Repository · 2010
We are interested in automatically calculating music similarity based on the visual appearance of artists.By collecting a large set of promotional photographs featuring artists and using a state-of-the-art image annotation system, we show that we can successfully annotate artists with a large set of (genre) tags.This suggests that we can learn some notion of artist similarity based on visual appearance.Such a similarity measure provides us with a novel query-by-image retrieval paradigm for music discovery.