Skip to main navigation Skip to search Skip to main content

Using the web to create dynamic dictionaries in handwritten out-of-vocabulary word recognition

  • CNRS LTCI
  • LIST-DTSI-SLA CEA
  • University of Balamand

Research output: Contribution to journal › Conference article › peer-review

10 Citations (Scopus)

Abstract

Handwriting recognition systems rely on predefined dictionaries obtained from training data. Small and static dictionaries are usually exploited to obtain high in-vocabulary (IV) accuracy at the expense of coverage. Thus the recognition of out-of-vocabulary (OOV) words cannot be handled efficiently. To improve OOV recognition while keeping IV dictionaries small, we introduce a multi-step approach that exploits Web resources. After an initial IV-OOV sequence classification, external resources are used to create OOV sequence-adapted dynamic dictionaries. A final Viterbi-based decoding is performed over the dynamic dictionary to determine the most probable word for the OOV sequence. We validate our approach with experiments conducted on RIMES, a publicly available database. Results show that improvements are obtained compared to standard handwriting recognition, performed with a static dictionary. Both domain adapted and generic dynamic dictionaries are studied and we show that domain adaptation is beneficial.

Original languageEnglish
Article number6628764
Pages (from-to)989-993
Number of pages5
JournalProceedings of the International Conference on Document Analysis and Recognition, ICDAR
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes
Event12th International Conference on Document Analysis and Recognition, ICDAR 2013 - Washington, DC, United States
Duration: 25 Aug 2013 → 28 Aug 2013

Keywords

  • Web resources
  • dynamic dictionaries
  • handwriting word recognition

Fingerprint

Dive into the research topics of 'Using the web to create dynamic dictionaries in handwritten out-of-vocabulary word recognition'. Together they form a unique fingerprint.

Cite this