23 January 2012 Quantify spatial relations to discover handwritten graphical symbols
Author Affiliations +
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.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jinpeng Li, Jinpeng Li, Harold Mouchère, Harold Mouchère, Christian Viard-Gaudin, Christian Viard-Gaudin, "Quantify spatial relations to discover handwritten graphical symbols", Proc. SPIE 8297, Document Recognition and Retrieval XIX, 82970F (23 January 2012); doi: 10.1117/12.910588; https://doi.org/10.1117/12.910588


Evaluating the multi-scale iCID metric
Proceedings of SPIE (February 07 2015)
Automatic human hallmark recognition based on visual words
Proceedings of SPIE (August 30 2018)
Color space quantization for inspection of textured objects
Proceedings of SPIE (September 15 1999)
Putting the media into hypermedia
Proceedings of SPIE (March 13 1995)

Back to Top