A similarity measure for illustration style
- 27 July 2014
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 33 (4), 1-9
- https://doi.org/10.1145/2601097.2601131
Abstract
This paper presents a method for measuring the similarity in style between two pieces of vector art, independent of content. Similarity is measured by the differences between four types of features: color, shading, texture, and stroke. Feature weightings are learned from crowdsourced experiments. This perceptual similarity enables style-based search. Using our style-based search feature, we demonstrate an application that allows users to create stylistically-coherent clip art mash-ups.Keywords
Funding Information
- Gobierno de Aragón
- Seventh Framework Programme (251415, 288914)
- Ministerio de Economía y Competitividad (TIN2010-21543)
- Adobe Systems
This publication has 27 references indexed in Scilit:
- Curve Style Analysis in a Set of ShapesComputer Graphics Forum, 2013
- Impressionism, expressionism, surrealismACM Transactions on Applied Perception, 2010
- Redundancy, diversity and interdependent document relevanceACM SIGIR Forum, 2009
- Sketch2PhotoACM Transactions on Graphics, 2009
- Image retrievalACM Computing Surveys, 2008
- Lessons from the Netflix prize challengeACM SIGKDD Explorations Newsletter, 2007
- Photo clip artACM Transactions on Graphics, 2007
- Defining Pictorial Style: Lessons from Linguistics and Computer GraphicsAxiomathes, 2005
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Algorithm 778: L-BFGS-BACM Transactions on Mathematical Software, 1997