Advanced

Transferring Characteristic Proportions to Modify the Artistic Style of Cartoons

Buchanan, Philip and Doggett, Michael LU (2012) Computer Graphics International, 2012
Abstract (Swedish)
Abstract in Undetermined

This paper presents a new automatic algorithm for extracting properties of an individual artist’s style and applying those properties to other drawings. The algorithm can be used to ensure consistent artistic style across a project by automatically transferring a selected style to hand drawn images. We present an algorithm that uses multiple stages; subdivision of an image into selected geons, extraction of corresponding datasets from additional images, analysis and characterisation of the artist’s style and finally transferring the artist’s style to target images. When transferring the artist’s style we use a complexity sensitive scaling algorithm to avoid artefacts. We apply this algorithm to line... (More)
Abstract in Undetermined

This paper presents a new automatic algorithm for extracting properties of an individual artist’s style and applying those properties to other drawings. The algorithm can be used to ensure consistent artistic style across a project by automatically transferring a selected style to hand drawn images. We present an algorithm that uses multiple stages; subdivision of an image into selected geons, extraction of corresponding datasets from additional images, analysis and characterisation of the artist’s style and finally transferring the artist’s style to target images. When transferring the artist’s style we use a complexity sensitive scaling algorithm to avoid artefacts. We apply this algorithm to line drawn cartoons and demonstrate that artistic style can be transferred between cartoon objects. Our results show that analysis of object proportions can be used practically to ensure consistency for objects with the same Geon structure but drawn by different artists. (Less)
Abstract
This paper presents a new automatic algorithm
for extracting properties of an individual artist’s
style and applying those properties to other drawings.
The algorithm can be used to ensure consistent artistic
style across a project by automatically transferring
a selected style to hand drawn images. We present an
algorithm that uses multiple stages; subdivision of an
image into selected geons, extraction of corresponding
datasets from additional images, analysis and characterisation
of the artist’s style and finally transferring
the artist’s style to target images. When transferring
the artist’s style we use a complexity sensitive scaling
algorithm to avoid artefacts. We apply this... (More)
This paper presents a new automatic algorithm
for extracting properties of an individual artist’s
style and applying those properties to other drawings.
The algorithm can be used to ensure consistent artistic
style across a project by automatically transferring
a selected style to hand drawn images. We present an
algorithm that uses multiple stages; subdivision of an
image into selected geons, extraction of corresponding
datasets from additional images, analysis and characterisation
of the artist’s style and finally transferring
the artist’s style to target images. When transferring
the artist’s style we use a complexity sensitive scaling
algorithm to avoid artefacts. We apply this algorithm
to line drawn cartoons and demonstrate that artistic
style can be transferred between cartoon objects. Our
results show that analysis of object proportions can be
used practically to ensure consistency for objects with
the same Geon structure but drawn by di↵erent artists. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to conference
publication status
unpublished
subject
pages
10 pages
conference name
Computer Graphics International, 2012
language
English
LU publication?
yes
id
a6b301d9-9555-4d3c-a32c-552792dfa0cf (old id 2796962)
alternative location
http://fileadmin.cs.lth.se/graphics/research/papers/2012/cst/cst.pdf
date added to LUP
2012-06-27 09:46:17
date last changed
2016-11-30 09:45:05
@misc{a6b301d9-9555-4d3c-a32c-552792dfa0cf,
  abstract     = {This paper presents a new automatic algorithm<br/>for extracting properties of an individual artist’s<br/>style and applying those properties to other drawings.<br/>The algorithm can be used to ensure consistent artistic<br/>style across a project by automatically transferring<br/>a selected style to hand drawn images. We present an<br/>algorithm that uses multiple stages; subdivision of an<br/>image into selected geons, extraction of corresponding<br/>datasets from additional images, analysis and characterisation<br/>of the artist’s style and finally transferring<br/>the artist’s style to target images. When transferring<br/>the artist’s style we use a complexity sensitive scaling<br/>algorithm to avoid artefacts. We apply this algorithm<br/>to line drawn cartoons and demonstrate that artistic<br/>style can be transferred between cartoon objects. Our<br/>results show that analysis of object proportions can be<br/>used practically to ensure consistency for objects with<br/>the same Geon structure but drawn by di↵erent artists.},
  author       = {Buchanan, Philip and Doggett, Michael},
  language     = {eng},
  pages        = {10},
  title        = {Transferring Characteristic Proportions to Modify the Artistic Style of Cartoons},
  year         = {2012},
}