Quantifying Visual Similarity for Artistic Styles

Determining the style or artistic movement to which a painter corresponds is a challenging and complicated problem because there are many factors that influence a painting, and these factors are of a qualitative nature, not a quantitative one. This work presents a methodology focused on the quantification of paintings via machine learning methods; we also perform a comparison between computer vision and machine learning techniques in order to understand the particularities and the functionalities of different methods.