Paper Info
Title
Sketch2Tag: automatic hand-drawn sketch recognition
Abstract
In this work, we introduce the Sketch2Tag system for hand-drawn sketch recognition. Due to large variations presented in hand-drawn sketches, most of existing work was limited to a particular domain or limited predefined classes. Different from existing work, Sketch2Tag is a general sketch recognition system, towards recognizing any semantically meaningful object that a child can recognize. This system enables a user to draw a sketch on the query panel, and then provides real-time recognition results. To increase the recognition coverage, a web-scale clipart image collection is leveraged as the knowledge base of the recognition system. Better understanding a user's drawing will be of great value to a variety of applications, such as, improving the sketch-based image search by combining the recognition results as textual queries.
Year
DOI
Venue
2012
10.1145/2393347.2396429
ACM Multimedia 2001
Keywords
Field
DocType
hand-drawn sketch,sketch-based image search,recognition coverage,automatic hand-drawn sketch recognition,limited predefined class,general sketch recognition system,recognition system,sketch2tag system,real-time recognition result,hand-drawn sketch recognition,recognition result,sketch recognition
Computer vision,3D single-object recognition,Sketch-based modeling,Recognition system,Computer science,Sketch recognition,Artificial intelligence,Knowledge base,Sketch
Conference
Citations 
PageRank 
References 
2
0.36
4
Authors
4
Name
Order
Citations
PageRank
Zhenbang Sun1432.22
Changhu Wang2129670.36
Liqing Zhang32713181.40
Lei Zhang4175489.83