2011
DOI: 10.1145/2030365.2030369
|View full text |Cite
|
Sign up to set email alerts
|

Recognizing sketched multistroke primitives

Abstract: Sketch recognition attempts to interpret the hand-sketched markings made by users on an electronic medium. Through recognition, sketches and diagrams can be interpreted and sent to simulators or other meaningful analyzers. Primitives are the basic building block shapes used by high-level visual grammars to describe the symbols of a given sketch domain. However, one limitation of these primitive recognizers is that they often only support basic shapes drawn with a single stroke. Furthermore, recognizers that do… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
23
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 41 publications
(23 citation statements)
references
References 43 publications
0
23
0
Order By: Relevance
“…Stroke-based methods treat each sketch as a sequence of time-stamped strokes, each containing a series of sample points in space. While some works share similarities to our domain [17,33,34,42,52], stroke-based methods are ill-suited for our recognition framework, which is designed to work on rasterized images. Still, there are interesting parallels; for instance, [34] uses a graph representation to combine low-level primitives into highlevel shapes using geometrical rules.…”
Section: Sketch Recognitionmentioning
confidence: 99%
See 1 more Smart Citation
“…Stroke-based methods treat each sketch as a sequence of time-stamped strokes, each containing a series of sample points in space. While some works share similarities to our domain [17,33,34,42,52], stroke-based methods are ill-suited for our recognition framework, which is designed to work on rasterized images. Still, there are interesting parallels; for instance, [34] uses a graph representation to combine low-level primitives into highlevel shapes using geometrical rules.…”
Section: Sketch Recognitionmentioning
confidence: 99%
“…While some works share similarities to our domain [17,33,34,42,52], stroke-based methods are ill-suited for our recognition framework, which is designed to work on rasterized images. Still, there are interesting parallels; for instance, [34] uses a graph representation to combine low-level primitives into highlevel shapes using geometrical rules. We also implement graphs in our recognition pipeline, but instead connect low-level joints to form high-level mechanisms based (partially) on mechanical feasibility rules.…”
Section: Sketch Recognitionmentioning
confidence: 99%
“…Various heuristics can be used to guide search such as probabilities produced by Baysian networks ]. Ouyang and Davis [2009] and Hammond and Paulson [2011] also make use of heuristic guided search.…”
Section: Related Workmentioning
confidence: 99%
“…This strategy is distinct from other grouping strategies as it reduces the problem to classification, whereas most other _____________________________ * phillipsteven4@gmail.com + rachel.blagojevic@auckland.ac.nz † beryl@cs.auckland.ac.nz strategies [Shilman et al 2004;Ouyang et al 2009;Hammond et al 2011] perform a complex search to find the groups.…”
Section: Introductionmentioning
confidence: 99%
“…To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. State-of-the-art gesture recognition techniques, such as Hidden Markov Models [19], feature-based statistical classifiers [17,22], or mixture of classifiers [12], typically require significant technical knowledge to understand and develop them for new platforms, or knowledge from other fields such as graph theory [11]. Therefore, our growing body of work has been tackling this problem by proposing low-cost, easy to understand and implement, yet high performing, gesture recognition approaches [2,3,23].…”
Section: Introductionmentioning
confidence: 99%