What Auto Completion Tells Us About Sketch Recognition

Simple item page
dc.contributor.authorAltiok, Ozan Canen_US
dc.contributor.authorYesilbek, Kemal Tugrulen_US
dc.contributor.authorSezgin, Tevfik Metinen_US
dc.contributor.editorErgun Akleman, Lyn Bartram, Anıl Çamcı, Angus Forbes, Penousal Machadoen_US
dc.date.accessioned2016-07-18T16:42:35Z
dc.date.available2016-07-18T16:42:35Z
dc.date.issued2016
dc.description.abstractAuto completion is generally considered to be a difficult problem in sketch recognition as it requires a decision to be made with fewer strokes. Therefore, it is generally assumed that the classification of fully completed object sketches should yield higher accuracy rates. In this paper, we report results from a comprehensive study demonstrating that the first few strokes of an object are more important than the lastly drawn ones. Once the first few critical strokes of a symbol are observed, recognition accuracies reach a plateau and may even decline. This indicates that less is more in sketch recognition. Our results are supported by carefully designed computational experiments using Tirkaz et. al.'s sketch auto completion framework on the dataset of everyday object sketches collected by Eitz et. al..en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationExpressive 2016 - Posters, Artworks, and Bridging Papers
dc.identifier.doi10.2312/exp.20161254
dc.identifier.isbn978-3-03868-021-5
dc.identifier.pages1-2
dc.identifier.urihttps://doi.org/10.2312/exp.20161254
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/exp20161254
dc.publisherThe Eurographics Associationen_US
dc.subjectI.5.0 [Pattern Recognition]
dc.subjectGeneral
dc.subjectH.5.2 [Information Interfaces and Presentation]
dc.subjectUser Interfaces
dc.subjectInput devices and strategies
dc.titleWhat Auto Completion Tells Us About Sketch Recognitionen_US
Files
Collections
Expressive 2016 - Posters, Artworks, and Bridging Papers