Nauman Riaz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Nauman Riaz has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Adnan Ul-Hasan
National University of Sciences and Technology (NUST)
2 shared publications Arooba Maqsood
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST), Islamabad, Pakistan
2 shared publicationsFaisal Shafait
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST), Islamabad, Pakistan
2 shared publicationsHaziq Arbab
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST), Islamabad, Pakistan
2 shared publicationsAdnan Ul-Hasan
National University of Sciences and Technology
1 shared publication- Arooba Maqsood
National University of Sciences and Technology (NUST)
1 shared publication
Latest Publications
- 19 August 2023
- Published by Springer Nature
- p. 116-130
A Unified Architecture for Urdu Printed and Handwritten Text Recognition
- 19 August 2023
- Published by Springer Nature
- p. 116-130
A Unified Architecture for Urdu Printed and Handwritten Text Recognition
- 23 September 2022
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (4) , 373-384
Conv-transformer architecture for unconstrained off-line Urdu handwriting recognition
- 23 September 2022
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (4) , 373-384
Conv-transformer architecture for unconstrained off-line Urdu handwriting recognition
- Open Access
- 4 April 2022
- Published by Springer Nature in Research Square
Conv-Transformer Architecture for Unconstrained Off-LineUrdu Handwriting Recognition
Unconstrained off-line handwriting text recognition in general and for Arabic-like scripts in particular is a challenging task and is still an active researcharea. Transformer based models for English handwriting recognition have recently shown promising results.In this paper, we have explored the use of transformerarchitecture for Urdu handwriting recognition. The useof a Convolution Neural Network before a vanilla fullTransformer and using Urdu printed text-lines alongwith handwritten text lines during the training are thehighlights of the proposed work. The Convolution Layers act to reduce the spatial resolutions and compensate for the n2 complexity of transformer multi-head attention layers. Moreover, the printed text images inthe training phase help the model in learning a greaternumber of ligatures (a prominent feature of Arabiclike scripts) and a better language model. Our modelachieved state-of-the-art accuracy (CER of 5.31%) onpublicly available NUST-UHWR dataset [1].
- 4 April 2022
- Published by Springer Nature in Research Square
Open AccessConv-Transformer Architecture for Unconstrained Off-LineUrdu Handwriting Recognition
Unconstrained off-line handwriting text recognition in general and for Arabic-like scripts in particular is a challenging task and is still an active researcharea. Transformer based models for English handwriting recognition have recently shown promising results.In this paper, we have explored the use of transformerarchitecture for Urdu handwriting recognition. The useof a Convolution Neural Network before a vanilla fullTransformer and using Urdu printed text-lines alongwith handwritten text lines during the training are thehighlights of the proposed work. The Convolution Layers act to reduce the spatial resolutions and compensate for the n2 complexity of transformer multi-head attention layers. Moreover, the printed text images inthe training phase help the model in learning a greaternumber of ligatures (a prominent feature of Arabiclike scripts) and a better language model. Our modelachieved state-of-the-art accuracy (CER of 5.31%) onpublicly available NUST-UHWR dataset [1].