Measuring the influence of painters through artwork facial features

• Bruna Dalmoro PUCRS
• Charles Monteiro PUCRS
• Soraia Raupp Musse PUCRS

Resumo

Computational aesthetics is a subfield of computer vision that seeks to understand the human aesthetic perception of images and image sequences. The main objective is to create systems that allow different aesthetic decisions, trying to approximate the judgment of a human being about the images. In this work, we explore the problem of identifying influence among artists based on visual features detected in their artworks. In particular, we are interested in investigating the similarity of faces in paintings to design the artists’ influence. In our methodology, we propose four groups of features to characterize the faces, and we show that the similarity of faces to finding artists’ influence, shows promising results when compared to the recently proposed methods.

Palavras-chave: Visualization, Computer vision, Feature extraction, Image sequences, Faces, Facial features, Painting