Please use this identifier to cite or link to this item:
Title: Handwriting-OOV word-recognition using web resources
Authors: Oprean, Cristina
Mokbel, Chafic 
Likforman-Sulem, Laurence
Popescu, Adrian
Affiliations: Department of Electrical Engineering 
Issue Date: 2014
Part of: La Voisier journal
Volume: 17
Issue: 3
Start page: 77
End page: 96
Handwriting recognition systems rely on predefined dictionaries. Small and static dictionaries are often exploited to obtain high in-vocabulary (IV) accuracy at the expense of coverage. Thus the recognition of out-of-vocabulary (OOV) words is not handled efficiently. To improve OOV recognition while keeping IV dictionaries small, we introduce a multi-step approach that exploits web resources. After an IV-OOV classification, Wikipedia is used to create OOV sequence-adapted dynamic dictionaries. A second decoding is done the dynamic dictionary to determine the most probable word for the OOV sequence. We validate our approach with experiments conducted on the RIMES dataset using a BLSTM recognizer. Results show that improvements are obtained compared to handwriting recognition with static dictionary.
Type: Journal Article
Appears in Collections:Department of Electrical Engineering

Show full item record

Record view(s)

checked on May 8, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.