banner
Home > Open Journal Systems

Comprehensive robustness evaluation of an automatic writer identification system using convolutional neural networks

Irfan Hamid, Rameez Raja, Monika Anand, Vijay Karnatak, Aleem Ali

Abstract


This research paper presents a convolutional neural network (CNN) model for identifying handwritten Urdu characters. A dataset of 38 fundamental Urdu characters from 100 different writers in the Kashmir valley was manually collected. The developed system was trained on a training dataset of 30,400 samples and verified on a test dataset of 7600 samples, and it outperformed previously proposed AI based writer identification systems in Urdu language with an identification rate of 91.44 percent for 38 classes. This study highlights the effectiveness of deep learning techniques in solving the challenging task of the Urdu writer identification. The findings demonstrate the potential of the developed CNN model for real-world applications in handwritten character recognition and verification systems. Future work involves expanding the dataset to include numerals and isolated characters for improved system performance.


Keywords


deep learning; convolutional neural network; Urdu characters; text independent; text identification

Full Text:

PDF

References


1. Nabi ST, Kumar M, Singh P. DeepNet-WI: A deep-net model for offline Urdu writer identification. Evolving Systems 2023; 17: 41–47. doi: 10.1007/s12530-023-09504-1

2. Dargan S, Kumar M. Writer identification system based on offline handwritten text in gurumukhi script. In: Proceedings of the 2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC); 6–8 November 2020; Solan, India. pp. 544–549.

3. Tang Y, Wu X. Text-independent writer identification via CNN features and joint Bayesian. In: Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR); 23–26 October 2016; Shenzhen, China. pp. 566–571.

4. Nguyen HT, Nguyen CT, Ino T, et al. Text-independent writer identification using convolutional neural network. Pattern Recognition Letters 2019; 121: 104–112. doi: 10.1016/j.patrec.2018.07.022

5. Yang W, Jin L, Liu M. DeepWriterID: An end-to-end online text-independent writer identification system. IEEE Intelligent Systems 2015; 31(2): 45–53. doi: 10.1109/MIS.2016.22

6. Rehman A, Naz S, Razzak MI. Writer identification using machine learning approaches a comprehensive review. Multimedia Tools and Applications 2019; 78(8): 10889–10931. doi: 10.1007/s11042-018-6577-1

7. Schomaker L. Advances in writer identification and verification. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007); 23–26 September 2007; Parana, Brazil. pp. 1268–1273.

8. Xing L, Qiao Y. Deepwriter: A multi-stream deep CNN for text-independent writer identification. In: Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR); 23–26 October 2016; Shenzhen, China. pp. 584–589.

9. Ali H, Ullah A, Iqbal T, Khattak S. Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep auto-encoder and convolutional neural network. SN Applied Sciences 2019; 2(2): 1–12. doi: 10.1007/s42452-019-1914-1

10. Sachdeva S, Ali A. Advanced approach using deep learning for healthcare data analysis in IOT system. In: Emergent Converging Technologies and Biomedical Systems. Springer; 2022. pp. 163–172.

11. Mushtaq F, Misgar MM, Kumar M, Khurana SS. UrduDeepNet: Offline handwritten Urdu character recognition using deep neural network. Neural Computing and Applications 2021; 1–24. doi: 10.1007/s00521-021-06144-x

12. Chhajro MA, Khan H, Khan F, et al. Handwritten Urdu character recognition via images using different machine learning and deep learning techniques. Indian Journal of Science and Technology 2020; 13(17): 1746–1754. doi: 10.17485/IJST/v13i17.113

13. Liu CL, Yin F, Wang DH, Wang QF. Online and offline handwritten Chinese character recognition: Benchmarking on new databases. Pattern Recognition 2013; 46(1): 155–162. doi: 10.1016/j.patcog.2012.06.021

14. Rehman A, Naz S, Razzak MI, Hameed IA. Automatic visual features for writer identification: A deep learning approach. IEEE Access 2019; 7: 17149–17157. doi: 10.1109/ACCESS.2018.2890810

15. Sachdeva S, Ali A. Machine learning with digital forensics for attack classification in cloud network environment. International Journal of Systems Assurance Engineering and Management 2022; 13: 156–165. doi: 10.1007/s13198-021-01323-4

16. Priyatharsini GS, Babu AJ, Kiran MG, et al. Self-secured model for cloud-based IOT systems. Measurement: Sensors 2022; 24: 100490. doi: 10.1016/j.measen.2022.100490

17. Zhu Y, Wan Y. An offline text-independent writer identification system with SAE feature extraction. In: Proceedings of the International Conference on Progress in Informatics and Computing (PIC); 23–25 December 2016; Shanghai, China. pp. 432–436.

18. Ahmed SB, Naz S, Swati S, Razzak MI. Handwritten Urdu character recognition using one-dimensional BLSTM classifier. Neural Computing and Applications 2019; 31(6): 1143–1151. doi: 10.1007/s00521-017-3146-x

19. Bulacu M, Schomaker L. Text-independent writer identification and verification using textural and allographic features. IEEE Transactions on Pattern Analysis and Machine Intelligence 2007; 29(4): 701–717. doi: 10.1109/TPAMI.2007.1009

20. Ahlawat S, Choudhary A, Nayyar A, et al. Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors 2020; 20(12): 3344. doi: 10.3390/s20123344




DOI: https://doi.org/10.32629/jai.v7i1.763

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Irfan Hamid, Rameez Raja, Monika Anand, Vijay Karnatak, Aleem Ali

License URL: https://creativecommons.org/licenses/by-nc/4.0/