Matching and Painting using Gestalt Models
Lead Research Organisation:
University of Bath
Department Name: Computer Science
Abstract
When an artist makes a drawing or painting of the real world in front of them, they constantly compare what they see to their art. They retouch their art, sometimes to make it more accurate, other times to bring out parts of the scene that interest them. The point is that making art involves seeing somethings as more important than others, and requires an ability to match artwork to the real world. If we replace the artist by a computer we should expect the same things to be true, but at the moment this is not the case. Our proposal is to match photographs and artwork so machines can make better - and new - art. Doing so offers more benefits than producing better artwork, it is a basic technique we can use to help machines identify important parts of a photograph, which helps computers see the world through human eyes just a little more.
Organisations
People |
ORCID iD |
Peter Hall (Principal Investigator) |
Publications
A Balikai
(2008)
Shapes fit for purpose
Hall P
(2013)
Simple art as abstractions of photographs
Song YZ
(2013)
Abstract art by shape classification.
in IEEE transactions on visualization and computer graphics
X Bai
(2007)
Learning object classes from structure
Xiao B
(2011)
Learning invariant structure for object identification by using graph methods
in Computer Vision and Image Understanding
Y Song
(2008)
Arty Shapes
Description | 1. It is possible to define Pr?gnanz in a computationally useful way.2. Shape is a determining factor in object recognition and in painting.3. Structure is a determining factor in object recognition and in painting.4. Aesthetic value judgments are not arbitrary. |
Exploitation Route | A computational definition of Pr?gnanz is of value to those who wish to analyse image parts into semantic objects. |
Sectors | Creative Economy Culture Heritage Museums and Collections |