Learning from neighboring strokes: Combining appearance and context for multi-domain sketch recognition
Name
3885-learning-from-neighboring-strokes-combining-appearance-and-context-for-multi-domain-sketch-recognition.pdf
Description
Published version
Size
471.97 KB
Format
Adobe PDF
Checksum (MD5)
2ec33b8cfdc586b4d7941f24fff6e850
Author(s) •
Ouyang, Tom Yu
Davis, Randall
Date Issued
2009
Journal
Advances in Neural Information Processing Systems 22 (NIPS 2008)
Publisher
Neural Information Processing Systems Foundation, Inc.
Citation
Ouyand, Tom Y. and Randall Davis. "Learning from Neighboring Strokes: Combing Appearance and Context for Multi-Domain Sketch Recognition." Advances in Neural Information Processing Systems 22 (NIPS 2009), December 2008, Vancouver, B.C., Canada, edited by D. Koller, Neural Information Processing Systems Foundation, Inc., 2009.
Version
Final published version
Abstract
We propose a new sketch recognition framework that combines a rich representation of low level visual appearance with a graphical model for capturing high level relationships between symbols. This joint model of appearance and context allows our framework to be less sensitive to noise and drawing variations, improving accuracy and robustness. The result is a recognizer that is better able to handle the wide range of drawing styles found in messy freehand sketches. We evaluate our work on two real-world domains, molecular diagrams and electrical circuit diagrams, and show that our combined approach significantly improves recognition performance.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/3885-learning-from-neighboring-strokes-combining-appearance-and-context-for-multi-domain-sketch-recognition