Share Email Print

Proceedings Paper

Context modeling for text/non-text separation in free-form online handwritten documents
Author(s): Adrien Delaye; Cheng-Lin Liu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Free-form online handwritten documents contain a high diversity of content, organized without constraints imposed to the user. The lack of prior knowledge about content and layout makes the modeling of contextual information of crucial importance for interpretation of such documents. In this work, we present a comprehensive investigation of the sources of contextual information that can benefit the task of discerning textual from non-textual strokes in handwritten online documents. An in-depth analysis of interactions between strokes is conducted through the design of various pairwise clique systems that are combined within a Conditional Random Field formulation of the stroke labeling problem. Our results demonstrate the benefits of combining complementary sources of context for improving the text/non-text recognition performance.

Paper Details

Date Published: 4 February 2013
PDF: 12 pages
Proc. SPIE 8658, Document Recognition and Retrieval XX, 86580C (4 February 2013); doi: 10.1117/12.2001973
Show Author Affiliations
Adrien Delaye, Institute of Automation (China)
Cheng-Lin Liu, Institute of Automation (China)

Published in SPIE Proceedings Vol. 8658:
Document Recognition and Retrieval XX
Richard Zanibbi; Bertrand Coüasnon, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?