Abstract | ||
---|---|---|
In this paper we present a recognizer of sketched symbols based on Latent-Dynamic Conditional Random Fields (LDCRF), a discriminative model for sequence classification. The LDCRF model classifies unsegmented sequences of strokes into domain symbols by taking into account contextual and temporal information. In particular, LDCRFs learn the extrinsic dynamics among strokes by modeling a continuous stream of symbol labels, and learn internal stroke sub-structure by using intermediate hidden states. The performance of our work is evaluated in the electric circuit domain. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICPR.2010.275 | ICPR |
Keywords | Field | DocType |
sketched symbol recognition,latent-dynamic conditional random fields,domain symbol,discriminative model,internal stroke sub-structure,electric circuit domain,latent-dynamic conditional model,extrinsic dynamic,continuous stream,ldcrf model,intermediate hidden state,account contextual,discriminative models,unified modeling language,probability,mathematical model,feature extraction,resistors,conditional random field,electrical circuit,handwriting recognition | Conditional random field,Symbol recognition,Unified Modeling Language,Pattern recognition,Computer science,Symbol,Handwriting recognition,Feature extraction,Speech recognition,Artificial intelligence,Discriminative model | Conference |
Citations | PageRank | References |
1 | 0.35 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vincenzo Deufemia | 1 | 449 | 40.96 |
Michele Risi | 2 | 403 | 40.98 |
Genoveffa Tortora | 3 | 1477 | 151.59 |