Constellation Models for Sketch Recognition

Simple item page
dc.contributor.authorSharon, Danaen_US
dc.contributor.authorPanne, Michiel van deen_US
dc.contributor.editorThomas Stahovich and Mario Costa Sousaen_US
dc.date.accessioned2014-01-27T19:17:06Z
dc.date.available2014-01-27T19:17:06Z
dc.date.issued2006en_US
dc.description.abstractSketch-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.en_US
dc.description.seriesinformationEurographics Workshop on Sketch-Based Interfaces and Modelingen_US
dc.identifier.isbn3-905673-39-8en_US
dc.identifier.issn1812-3503en_US
dc.identifier.urihttps://doi.org/10.2312/SBM/SBM06/019-026en_US
dc.publisherThe Eurographics Associationen_US
dc.titleConstellation Models for Sketch Recognitionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
019-026.pdf
Size:
343.48 KB
Format:
Adobe Portable Document Format
Download
Collections
SBM06: Sketch Based Interfaces and Modeling 2006