Conditional Random Fields for Online Handwriting Recognition

Trinh-Minh-Tri Do 1 Thierry Artières 1
1 MALIRE - Machine Learning and Information Retrieval
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : In this work, we present a conditional model for online handwriting recognition. Our approach is based on Conditional Random Fields (CRFs), a probabilistic discriminant model that has been generally used up to now in particular settings, for labeling and parsing of sequential data such as text documents and biological sequences. We propose to adapt these models in order to build systems for handwriting recognition. We propose a few systems whose architecture allows dealing with multimodal classes and exploiting segmental features that are much adapted to signal data like online handwriting.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00104207
Contributor : Anne Jaigu <>
Submitted on : Friday, October 6, 2006 - 9:46:55 AM
Last modification on : Thursday, September 19, 2019 - 11:04:02 AM
Long-term archiving on: Tuesday, April 6, 2010 - 6:41:31 PM

Identifiers

  • HAL Id : inria-00104207, version 1

Citation

Trinh-Minh-Tri Do, Thierry Artières. Conditional Random Fields for Online Handwriting Recognition. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule, France. ⟨inria-00104207⟩

Share

Metrics

Record views

423

Files downloads

232