Sciweavers

ICPR
2008
IEEE

A symbol graph based handwritten math expression recognition

13 years 10 months ago
A symbol graph based handwritten math expression recognition
In online handwritten math expression recognition, one-pass dynamic programming can produce highquality symbol graphs in addition to best symbol sequence hypotheses [3], especially after discriminative training and trigram graph rescoring [2]. Impact of symbol graphs on whole expression recognition, however, has not been referred to yet, since the interface of structure analysis module does not work well with symbol graphs on the basis of typical tree search [4]. In this paper, we propose a method to convert symbol graph to segment graph to make the tree search efficient and effective, i.e., search of best segmentations in symbol graph without pruning becomes possible. With trigram rescoring, the overall expression recognition accuracy has been improved by 10% relative in comparison with the baseline.
Yu Shi, Frank K. Soong
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICPR
Authors Yu Shi, Frank K. Soong
Comments (0)