4 February 2013 Context modeling for text/non-text separation in free-form online handwritten documents
Author Affiliations +
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.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Adrien Delaye, Cheng-Lin Liu, "Context modeling for text/non-text separation in free-form online handwritten documents", Proc. SPIE 8658, Document Recognition and Retrieval XX, 86580C (4 February 2013); doi: 10.1117/12.2001973; https://doi.org/10.1117/12.2001973
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Data warehouse model design technology analysis and research
Proceedings of SPIE (January 13 2012)
ESP: An Expert System For Computer Performance Management
Proceedings of SPIE (March 26 1986)
GIS-based approaches for planning support
Proceedings of SPIE (November 05 2008)
A cyber-event correlation framework and metrics
Proceedings of SPIE (August 08 2003)
The role of the unified modeling language and the extensible...
Proceedings of SPIE (September 04 2003)

Back to Top