File(s) under permanent embargo
Urdu Nastaliq recognition using convolutional–recursive deep learning
journal contribution
posted on 2017-06-21, 00:00 authored by S Naz, A I Umar, R Ahmad, I Siddiqi, S B Ahmed, Imran RazzakImran Razzak, F Shafait© 2017 Recent developments in recognition of cursive scripts rely on implicit feature extraction methods that provide better results as compared to traditional hand-crafted feature extraction approaches. We present a hybrid approach based on explicit feature extraction by combining convolutional and recursive neural networks for feature learning and classification of cursive Urdu Nastaliq script. The first layer extracts low-level translational invariant features using Convolutional Neural Networks (CNN) which are then forwarded to Multi-dimensional Long Short-Term Memory Neural Networks (MDLSTM) for contextual feature extraction and learning. Experiments are carried out on the publicly available Urdu Printed Text-line Image (UPTI) dataset using the proposed hierarchical combination of CNN and MDLSTM. A recognition rate of up to 98.12% for 44-classes is achieved outperforming the state-of-the-art results on the UPTI dataset.
History
Journal
NeurocomputingVolume
243Pagination
80 - 87Publisher
ElsevierLocation
Amsterdam, The NetherlandsPublisher DOI
ISSN
0925-2312eISSN
1872-8286Language
engPublication classification
C1.1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC