Deep Learning Based Pashto Characters Recognition
LSTM-Based Handwritten Pashto characters recognition system
DOI:
https://doi.org/10.53560/PPASA(58-3)743Keywords:
Optical Characters Recognition, Decision Trees, Deep Learning, Pashto, Zoning Technique, Invariant Moments, Long Short Term MemoryAbstract
In artificial intelligence, text identification and analysis that are based on images play a vital role in the text retrieving process. Automatic text recognition system development is a difficult task in machine learning, but in the case of cursive languages, it poses a big challenge to the research community due to slight changes in character’s shapes and the unavailability of a standard dataset. While this recognition task becomes more challenging in the case of Pashto language due to a large number of characters in its dataset than other similar cursive languages (Persian, Urdu, Arabic) and a slight change in character’s shape. This paper aims to address accept these challenges by developing an optimal optical character recognition (OCR) system to recognise isolated handwritten Pashto characters. The proposed OCR system is developed using multiple long short-term memory (LSTM) based deep learning model. The applicability of the proposed model is validated by using the decision trees (DT) classification tool based on the zoning feature extraction technique and the invariant moment approaches. An overall accuracy rate of 89.03% is calculated for the multiple LSTM-based OCR system while DT-based recognition rate of 72.9% is achieved using zoning feature vector and 74.56% is achieved for invariant moments-based feature map. Applicability of the system is evaluated using different performance metrics of accuracy, f-score, specificity, and varying training and test sets.
References
S. Valikhani, F. Abdali-Mohammadi, and A. Fathi. Online continuous multi-stroke Persian/Arabic character recognition by novel spatio-temporal features for digitiser pen devices. Neural Computing and Applications p. 1-20 (2019).
M. J. Rafeeq, Z. ur Rehman, A. Khan, I. A. Khan, and W. Jadoon. Ligature categorisation based Nastaliq Urdu recognition using deep neural networks. Computational and Mathematical Organisation Theory 25: 184-195 (2019).
W. Khan, A. Daud, F. Alotaibi, N. Aljohani, and S. Arafat. Deep recurrent neural networks with word embeddings for Urdu named entity recognition. ETRI Journal (2019).
R. Hussain, A. Raza, I. Siddiqi, K. Khurshid, and C. Djeddi. A comprehensive survey of handwritten document benchmarks: structure, usage and evaluation. EURASIP Journal on Image and Video Processing, 2015: 46, (2015).
N. Tagougui, M. Kherallah, and A. M. Alimi. Online Arabic handwriting recognition: a survey. International Journal on Document Analysis and Recognition (IJDAR) 16: 209-226 (2013).
H. Chen, S. Khan, B. Kou, S. Nazir, W. Liu, and A. Hussain. A Smart Machine Learning Model for the Detection of Brain Hemorrhage Diagnosis Based Internet of Things in Smart Cities. Complexity 2020: 3047869 (2020).
Z. Gu, S. Nazir, C. Hong, and S. Khan. Convolution Neural Network-Based Higher Accurate Intrusion Identification System for the Network Security and Communication. Security and Communication Networks 2020: 8830903 (2020).
Y. He, S. Nazir, B. Nie, S. Khan, and J. Zhang. Developing an Efficient Deep Learning-Based Trusted Model for Pervasive Computing Using an LSTM-Based Classification Model. Complexity 2020: 4579495 (2020).
S. Wang, S. Khan, C. Xu, S. Nazir, and A. Hafeez, Deep Learning-Based Efficient Model Development for Phishing Detection Using Random Forest and BLSTM Classifiers. Complexity 2020: 8694796 (2020).
S. Naz, A. I. Umar, R. Ahmad, S. B. Ahmed, S.H. Shirazi, and M. I. Razzak. Urdu Nasta’liq text recognition system based on multi-dimensional recurrent neural network and statistical features. Neural computing and applications 28: 219-231 (2017).
S. Naz, A. I. Umar, R. Ahmad, I. Siddiqi, S.B. Ahmed, M. I. Razzak, et al. Urdu Nastaliq recognition using convolutional–recursive deep learning. Neurocomputing, 243: 80-87 (2017).
A. ElAdel, M. Zaied, and C. Ben Amar. Trained convolutional neural network based on selected beta filters for Arabic letter recognition. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 9: e1250 (2019).
A. Jabbar, S. Iqbal, A. Akhunzada, and Q. Abbas. An improved Urdu stemming algorithm for text mining based on multi-step hybrid approach. Journal of Experimental & Theoretical Artificial Intelligence, 30: 703-723 (2018).
S. Jehangir, S. Khan, S. Khan, S. Nazir, and A. Hussain. Zernike moments based handwritten Pashto character recognition using linear discriminant analysis. Mehran University Research Journal Of Engineering & Technology, 40(1), 152-159 (2021).
J. Huang, I. U. Haq, C. Dai, S. Khan, S. Nazir, and M. Imtiaz. Isolated Handwritten Pashto Character Recognition Using a K-NN Classification Tool based on Zoning and HOG Feature Extraction Techniques. Complexity, 2021: 5558373 (2021).
S. Khan, H. Ali, Z. Ullah, N. Minallah, S. Maqsood, and A. Hafeez. KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features. Machine learning 9: 570-577 (2018).
N. Ahmad, M. Naeem, S. A. R. Abid, and A. Gul. Pashto optical character recognition using neural network. Journal of engineering and applied sciences (37) (2018).
D. Das, D. R. Nayak, R. Dash, and B. Majhi. An empirical evaluation of extreme learning machine: application to handwritten character recognition. Multimedia Tools and Applications, p. 1-29 (2019).
S. Naz, S. B. Ahmed, R. Ahmad, and M. I. Razzak. Zoning features and 2DLSTM for Urdu text-line recognition. Procedia Computer Science 96: 16-22, (2016).
M.-K. Hu. Visual pattern recognition by moment invariants. IRE transactions on information theory, 8: 179-187 (1962).
S. Khan, A. Hafeez, H. Ali, S. Nazir, A. Hussain. Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks. Measurement and Control (2020).
M. Schlemmer, M. Heringer, F. Morr, I. Hotz, M. Hering-Bertram, C. Garth, et al. Moment invariants for the analysis of 2D flow fields. IEEE Transactions on Visualization and Computer Graphics, 13: 1743- 1750 (2007).
Q. Chen, E. Petriu, and X. Yang. A comparative study of Fourier descriptors and Hu's seven moment invariants for image recognition. in Canadian conference on electrical and computer engineering 2004 (IEEE Cat. No. 04CH37513), p. 103-106 (2004).
R. Mouhcine, A. Mustapha, and M. Zouhir. Recognition of cursive Arabic handwritten text using embedded training based on HMMs. Journal of Electrical Systems and Information Technology, 5: 245-251 (2018).
S. L. Marie-Sainte and N. Alalyani. Firefly algorithm based feature selection for Arabic text classification. Journal of King Saud University-Computer and Information Sciences (2018).
S. Khan, S. Nazir, I. García-Magariño, A. Hussain. Deep learning-based urban big data fusion in smart cities: Towards traffic monitoring and flow-preserving fusion. Computers & Electrical Engineering, 89: 106906, (2021).
S. Khan, S. Nazir, H. U. Khan. Smart object detection and home appliances control system in smart cities. Computers, Materials and Continua, 67: 895-915 (2021).
S. Khan, S. Nazir, H. U. Khan, and A. Hussain. Pashto Characters recognition using multi-class enabled support vector machine. CMC-Computers Materials & Continua, 67(3), 2831-2844 (2021).
X. Liao, S. Nazir, J. Shen, B. Shen, and S. Khan. Rough Set Approach toward Data Modelling and User Knowledge for Extracting Insights. Complexity 2021: 7815418 (2021).
M. Elleuch, N. Tagougui, and M. Kherallah. Optimisation of DBN using regularisation methods applied for recognising arabic handwritten script. Procedia Computer Science 108: 2292-2297 (2017).
A. J. Humaidi and T. M. Kadhim. Recognition of Arabic Characters using Spiking Neural Networks. in 2017 International Conference on Current Trends in Computer, Electrical, Electronics and Communication (CTCEEC), p. 7-11 (2017).
