Knowledge Discovery of Artistic Influences: A Metric Learning Approach.
Babak Saleh, Kanako Abe, Ahmed Elgammal · 2014
We approach the challenging problem of discovering in-fluences between painters based on their fine-art paint-ings. In this work, we focus on comparing paintings of two painters in terms of visual similarity. This compari-son is fully automatic and based on computer vision ap-proaches and machine learning. We investigated differ-ent visual features and similarity measurements based on two different metric learning algorithm to find the most appropriate ones that follow artistic motifs. We evaluated our approach by comparing its result with ground truth annotation for a large collection of fine-art paintings.