• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2020, Volume: 13, Issue: 17, Pages: 1746-1754

Original Article

Handwritten Urdu character recognition via images using different machine learning and deep learning techniques

Received Date:02 April 2020, Accepted Date:08 May 2020, Published Date:12 June 2020


Objectives: This research presents a model for Urdu Handwritten Character Recognition via images using various Machine Learning and Deep Learning Techniques. The main objective of this research is to provide comparative study on Urdu Handwritten Characters from images dataset. Methods/Statistical analysis: In this research paper, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) algorithm, Multi-Layer Perceptron (MLP), Concurrent Neural Network (CNN), Recurrent Neural Network (RNN) and Random Forest Algorithm (RF) have been implemented in order to evaluate most suitable technique for Urdu Handwritten Characters Recognition via images. Findings: Ample amount of research work has been carried out on English Language but it is clearly shown through the conducted literature review that very lesser amount of work has been done on Urdu Handwritten Characters Recognition using images. Furthermore, It has been analyzed from this research that CNN models are most efficient compared to RF, SVM and MLP as to produce reliable results in terms of optimal accuracy. Therefore, using the CNN model is a viable choice to recognize Urdu handwritten characters from the images. And proposed study provides significant contribution in automatic learning of Urdu handwritten Characters.

Keywords: Urdu Handwritten Characters; Machine Learning; Deep Learning; Urdu Character Recognition


  1. Husnain M, Missen MMS, Mumtaz S, Jhanidr MZ, Coustaty M, Luqman MM, et al. Recognition of Urdu Handwritten Characters Using Convolutional Neural Network. Applied Sciences. 2019;9(13):1–21. doi: 10.3390/app9132758
  2. Naz S, Umar AI, Ahmad R, Siddiqi I, Ahmed SB, Razzak MI, et al. Urdu Nastaliq recognition using convolutional–recursive deep learning. Neurocomputing. 2017;243:80–87. doi: 10.1016/j.neucom.2017.02.081
  3. Rizvi SSR, Sagheer A, Adnan K, Muhammad A. Optical Character Recognition System for Nastalique Urdu-Like Script Languages Using Supervised Learning. International Journal of Pattern Recognition and Artificial Intelligence. 2019;33(10). doi: 10.1142/s0218001419530045
  4. Naz S, Hayat K, Razzak MI, Anwar MW, Madani SA, Khan SU. The optical character recognition of Urdu-like cursive scripts. Pattern Recognition. 2014;47(3):1229–1248. doi: 10.1016/j.patcog.2013.09.037
  5. Choudhary P, Nain N, Ahmed M. A Structure for Annotation and Ground-truthing of Urdu Handwritten Text Image Corpus. Procedia - Social and Behavioral Sciences. 2015;198:84–88. doi: 10.1016/j.sbspro.2015.07.422
  6. Mukhtar N, Khan MA, Chiragh N. Lexicon-based approach outperforms Supervised Machine Learning approach for Urdu Sentiment Analysis in multiple domains. Telematics and Informatics. 2018;35(8):2173–2183. doi: 10.1016/j.tele.2018.08.003
  7. Jabbar A, Islam S, Hussain S, Akhunzada A, Ilahi M. A comparative review of Urdu stemmers: Approaches and challenges. Computer Science Review. 2019;34. doi: 10.1016/j.cosrev.2019.100195
  8. Mahmood Z, Safder I, Nawab RMA, Bukhari F, Nawaz R, Alfakeeh AS, et al. Deep sentiments in Roman Urdu text using Recurrent Convolutional Neural Network model. Information Processing & Management. 2020;57(4):102233. doi: 10.1016/j.ipm.2020.102233
  9. Chen MH, Chen WF, Ku LW. Application of Sentiment Analysis to Language Learning. IEEE. 2018;6:24433–24442. doi: 10.1109/access.2018.2832137
  10. Shehab A, Elhenway I. A drugs classifier system based on machine learning algorithms. Indian Journal of Science and Technology. 2020;13(09):1046–1056. doi: 10.17485/%20ijst/2020/v013i09/148136
  11. Bilal M, Israr H, Shahid M, Khan A. Sentiment classification of Roman-Urdu opinions using Naïve Bayesian, Decision Tree and KNN classification techniques. Journal of King Saud University - Computer and Information Sciences. 2016;28(3):330–344. doi: 10.1016/j.jksuci.2015.11.003
  12. Rafeeq MJ, Rehman Zu, Khan A, Khan IA, Jadoon W. Ligature categorization based Nastaliq Urdu recognition using deep neural networks. Computational and Mathematical Organization Theory. 2019;25:184–195. doi: 10.1007/s10588-018-9271-y
  13. Ali I, Ali I, Subhash, Khan A, Raza SA, Hassan B, et al. Sindhi Handwritten-Digits Recognition Using Machine Learning Techniques”. International Journal of Computer Network and Information Security. 2019;9(5):195–201. Available from: http://paper.ijcsns.org/07_book/201905/20190526.pdf
  14. Breiman L. Random Forests. Machine Learning. 2001;45(1):5–32. doi: doi.org/10.1023/A


© 2020 Chhajro, Khan, Khan, Kumar, Wagan, Solangi. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.