Constellation Models for Sketch Recognition

Sharon, Dana; Panne, Michiel van de

Constellation Models for Sketch Recognition

Files

019-026.pdf (343.48 KB)

Date

2006

Authors

Sharon, Dana
Panne, Michiel van de

Publisher

The Eurographics Association

Abstract

Sketch-based modeling shares many of the difficulties of the branch of computer vision that deals with single image interpretation. Most obviously, they must both identify the parts observed in a given 2D drawing or image.We draw on constellation models first proposed in the computer vision literature to develop probabilistic models for object sketches, based on multiple example drawings. These models are then applied to estimate the most-likely labels for a new sketch. A multi-pass branch-and-bound algorithm allows well-formed sketches to be quickly labelled, while still supporting the recognition of more ambiguous sketches. Results are presented for five classes of objects.

        @inproceedings{:10.2312/SBM/SBM06/019-026
,
booktitle = {Eurographics Workshop on Sketch-Based Interfaces and Modeling
},
editor = {Thomas Stahovich and Mario Costa Sousa
},
title = {{Constellation Models for Sketch Recognition
}},
author = {Sharon, Dana and 
Panne, Michiel van de
},
year = {2006
},
publisher = {The Eurographics Association
},
ISSN = {1812-3503
},
ISBN = {3-905673-39-8
},
DOI = {/10.2312/SBM/SBM06/019-026
}
}