Abstract art by shape classification

Yi-Zhe Song, David Pickup, Chuan Li, Paul Rosin, Peter Hall

Research output: Contribution to journalArticlepeer-review

14 Citations (SciVal)


This paper shows that classifying shapes is a tool useful in Non-Photorealistic rendering from photographs. Our classifier inputs regions from an image segmentation hierarchy and outputs the “best” fitting simple shape such as a circle, square or triangle. Other approaches to NPR have recognised the benefits of segmentation, but none have classified the shape of segments. By doing so, we can create artwork of a more abstract nature, emulating the style of modern artists such as Matisse and other artists who favoured shape simplification in their artwork. The classifier chooses the shape that “best” represents the region. Since the classifier is trained by a user, the ‘best shape’ has a subjective quality that can over-ride measurements such as minimum error and more importantly captures user preferences. Once trained, the system is fully automatic, although simple user interaction is also possible to allow for differences in individual tastes. A gallery of results shows how this classifier contributes to NPR from images by producing abstract artwork.
Original languageEnglish
Pages (from-to)1252-1263
Number of pages12
JournalIEEE Transactions on Visualization and Computer Graphics
Issue number8
Early online date14 Feb 2013
Publication statusPublished - Aug 2013

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Abstract art by shape classification'. Together they form a unique fingerprint.

Cite this