Quantify spatial relations to discover handwritten graphical symbols

Jinpeng Li; Harold Mouchère; Christian Viard-Gaudin

doi:10.1117/12.910588

23 January 2012 Quantify spatial relations to discover handwritten graphical symbols

Jinpeng Li, Harold Mouchère, Christian Viard-Gaudin

Proceedings Volume 8297, Document Recognition and Retrieval XIX; 82970F (2012) https://doi.org/10.1117/12.910588
Event: IS&T/SPIE Electronic Imaging, 2012, Burlingame, California, United States

Abstract

To model a handwritten graphical language, spatial relations describe how the strokes are positioned in the 2-dimensional space. Most of existing handwriting recognition systems make use of some predefined spatial relations. However, considering a complex graphical language, it is hard to express manually all the spatial relations. Another possibility would be to use a clustering technique to discover the spatial relations. In this paper, we discuss how to create a relational graph between strokes (nodes) labeled with graphemes in a graphical language. Then we vectorize spatial relations (edges) for clustering and quantization. As the targeted application, we extract the repetitive sub-graphs (graphical symbols) composed of graphemes and learned spatial relations. On two handwriting databases, a simple mathematical expression database and a complex flowchart database, the unsupervised spatial relations outperform the predefined spatial relations. In addition, we visualize the frequent patterns on two text-lines containing Chinese characters.

Citation Download Citation

Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin "Quantify spatial relations to discover handwritten graphical symbols", Proc. SPIE 8297, Document Recognition and Retrieval XIX, 82970F (23 January 2012); https://doi.org/10.1117/12.910588

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available