Filters








8 Hits in 1.9 sec

Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks

Adnan Ul-Hasan, Saad Bin Ahmed, Faisal Rashid, Faisal Shafait, Thomas M. Breuel
2013 2013 12th International Conference on Document Analysis and Recognition  
In this work, we have presented the results of applying RNN to printed Urdu text in Nastaleeq script.  ...  Bidirectional Long Short Term Memory (BLSTM) architecture with Connectionist Temporal Classification (CTC) output layer was employed to recognize printed Urdu text.  ...  In this paper, we demonstrate the application of 1D bidirectional LSTM networks to the printed Urdu Nastaleeq recognition. 1D BLSTMs are different than 2D or multidimensional BLSTMs in how input sequence  ... 
doi:10.1109/icdar.2013.212 dblp:conf/icdar/Ul-HasanARSB13 fatcat:dxbu2g2udrb5vnsodibzma5sky

MMU-OCR-21: Towards End-to-End Urdu Text Recognition Using Deep Learning

Tayyab Nasir, Muhammad Kamran Malik, Khurram Shahzad
2021 IEEE Access  
That is, for any LSTM cell at timestamp t, the context from cells 1 to t-1 are carried out to this cell. Thus, Bidirectional LSTM is introduced here.  ...  To that end, we have developed a printed Urdu text corpus along with the corresponding OCR benchmark.  ... 
doi:10.1109/access.2021.3110787 fatcat:ztxzqok6mncvtattpf7dyzbnvy

A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks [article]

Anupama Ray, Sai Rajeswar, Santanu Chaudhury
2015 arXiv   pre-print
Deep LSTM is an ideal candidate for text recognition.  ...  This paper proposes a hybrid text recognizer using a deep recurrent neural network with multiple layers of abstraction and long range context along with a language model to verify the performance of the  ...  This framework is very “Offline printed urdu nastaleeq script recognition with bidirectional lstm effective in case of insertion and deletion errors introduced networks  ... 
arXiv:1502.07540v1 fatcat:lmptvd5wxfcmhddkhh5bkn44ue

CALText: Contextual Attention Localization for Offline Handwritten Text [article]

Tayaba Anjum, Nazar Khan
2021 arXiv   pre-print
Recognition of Arabic-like scripts such as Persian and Urdu is more challenging than Latin-based scripts.  ...  Not much research exists for offline handwritten Urdu script which is the 10th most spoken language in the world.  ...  and 87.6% accuracy for Urdu Nastaleeq style.  ... 
arXiv:2111.03952v1 fatcat:6fdcbrwpv5gchmxak7en6r77ri

Urdu Handwritten Text Recognition: A Survey

Mujtaba Husnain, Shahzad Mumtaz, Mickael Coustaty, Muzzamil Luqman, Jean-Marc Ogier, Saad Malik
2020 IET Image Processing  
In this study, the authors presented a comprehensive survey for a number of offline and online handwritten text recognition systems for Urdu script written in Nastaliq font style from 2004 to 2019.  ...  Work on the problem of handwritten text recognition in Urdu script has been an active research area. A significant progress is made in this interesting and challenging field in the last few years.  ...  of both the printed and handwritten Urdu Nastaleeq text based on ligature information.  ... 
doi:10.1049/iet-ipr.2019.0401 fatcat:vm6xhbrulvhrnj6eglcydaxwwe

A BLSTM Network for Printed Bengali OCR System with High Accuracy [article]

Debabrata Paul, Bidyut Baran Chaudhuri
2019 arXiv   pre-print
A good Indic multi script OCR system is also developed by Google.  ...  This paper presents a printed Bengali and English text OCR system developed by us using a single hidden BLSTM-CTC architecture having 128 units.  ...  We also plan to include Assamese script in our system. Moreover, we intend to enhance our system to recognize the Bengali text printed in obsolete Lino-Monotype fonts.  ... 
arXiv:1908.08674v1 fatcat:oi3tkwqndbgmzewpjufvu42rri

Amharic OCR: An End-to-End Learning

Birhanu Belay, Tewodros Habtegebrial, Million Meshesha, Marcus Liwicki, Gebeyehu Belay, Didier Stricker
2020 Applied Sciences  
In this paper, we introduce an end-to-end Amharic text-line image recognition approach based on recurrent neural networks.  ...  This script uses 34 consonant characters with the seven vowel variants of each (called basic characters) and other labialized characters derived by adding diacritical marks and/or removing parts of the  ...  recognition [29] , Urdu Nastaleeq script recognition using bidirectional LSTM [30] , segmentation-free Chinese handwritten text recognition [31] , a hybrid Convolutional Long-Term Memory Network(CLSTM  ... 
doi:10.3390/app10031117 fatcat:4gtjsm5gcjggtlvfsymqurapgm

Offline Hand Written Urdu Word Spotting using Random Data Generation

Faiq Faizan Farooqui, Muhammad Hassan, Muhammad Shahzad Younis, Muhammad Kashif Siddhu
2020 IEEE Access  
The system achieved a promising recognition rate of 98.96% due to the sample generation using Cycle-GANs. INDEX TERMS Word spotting, HOG features, hand written text, LSTM, GANs.  ...  For the word spotting process, Histogram of Oriented Gradients (HOG) features are extracted from ligature images and then used to train a Long Short-Term Memory (LSTM) network for the classification task  ...  This provides a better recognition rate when trained on LSTM network.  ... 
doi:10.1109/access.2020.3010166 fatcat:ybwmfq7dfnecvkiz7czszbnd5y