Disney researchers have developed computer models that learn an artist's drawing style, how they use strokes, and how they select features to highlight as they interpret a face into a portrait. The researchers say that a better understanding of this abstraction process can help in developing artificial drawing tools.
"There's something about an artist's interpretation of a subject that people find compelling," says Disney's Moshe Mahler. "We're trying to capture that--to create a computer model of it--in a way that no one has done before."
Their approach is built on a database representing abstractions of a set of artists. The database contains sketched portraits based on 24 photographs of male and female faces using a stylus pen that allows the researchers to record each stroke. Seven artists created four sketches of each photo, with decreasing time intervals allowed for each. The result was a dataset of 672 sketches at four abstraction levels. The dataset contains about 8,000 strokes for each artist, with each stroke categorized as shading strokes or contour strokes, with contour strokes subdivided into complex and simple strokes.
The researchers used the system to synthesize sketches based on new face photos, and found that their sketch-generation method produced multiple, distinct styles that are similar to hand-drawn sketches.
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA