Digits Recognition for Arabic Handwritten through Convolutional Neural Networks, Local Binary Patterns, and Histogram of Oriented Gradients
DOI:
https://doi.org/10.21123/bsj.2024.9173Keywords:
Image Processing, Deep Learning, K Nearest Neighbor, Pattern Recognition, Machine LearningAbstract
The recognition of handwritten text is a topic of study that has several applications. One of these applications is the recognition of handwriting in official documents, historical scripts, bank checks, etc., which is a problem that might be considered relatively a security issue. The topic of handwriting recognition has been the subject of a significant amount of study and analysis in recent years. People from a variety of countries, including all of the countries that use Arabic as their primary language, as well as Persian, Urdu, and Pashto languages, also use Arabic characters in their scripts. As people's handwriting is infinitely varied, recognition systems confront numerous challenges. This paper aims to examine the efficacy of some techniques in addressing the problem of Arabic Handwritten Numbers Recognition (AHNR). Specifically, the methods under consideration are Convolutional Neural Networks (CNNs), which have demonstrated their utility in diverse domains and offer effective solutions. Local Binary Pattern (LBP) is a unique, efficient textural operator that finds widespread application in the area of computers such as biometric identification and detection of targets as feature extraction techniques. In addition, a Histogram of Oriented Gradients (HOG) is a feature extraction technique that is used in computer vision and image processing for the purpose of object detection. The HOG descriptor focuses on the structure or the shape of an object. It is better than any edge descriptor as it uses magnitude as well as the angle of the gradient to compute the features. Furthermore, the K-Nearest Neighbor (KNN) algorithm will be employed as a classifier in conjunction with LBP and HOG. Comparing the performance of the three methods, the (CNN) model achieved nearly 99% recognition accuracy, which is asymptotic for the HOG approach. In terms of computational efficacy, the CNN model was 0.61 seconds faster than the HOG approach.
Received 03/06/2023
Revised 08/09/2023
Accepted 10/09/2023
Published Online First 20/03/2024
References
Ali AA, Mallaiah S. Intelligent handwritten recognition using hybrid CNN architectures based-SVM classifier with dropout. J King Saud Univ Comput Inf Sci. 2022 Jun; 1; 34(6): 3294-300. https://dx.doi.org/10.1016/j.jksuci.2021.01.012
Younis KS. Arabic hand-written character recognition based on deep convolutional neural networks. Jordanian J Comput Inf Technol. 2017 Dec; 1; 3(3). https://dx.doi.org/10.5455/jjcit.71-1498142206.pp186-200
Ettaouil EH. Generalization Ability Augmentation and Regularization of Deep Convolutional Neural Networks Using l1/2 Pooling. Int J Tech Phys Probl Eng. 2021 September; 13(48): 1-6.
El-Sawy A, Loey M, El-Bakry H. Arabic handwritten characters recognition using convolutional neural network. WSEAS Trans Comput Res. 2017 Jan; 5(1): 11-9.
Al-wajih E, Ghazali R. An enhanced LBP-based technique with various size of sliding window approach for handwritten Arabic digit recognition. Multimed Tools Appl. 2021 Jul; 80: 24399-418. https://doi.org/10.1007/s11042-021-10762-x
Jebril NA, Al-Zoubi HR, Abu Al-Haija Q. Recognition of handwritten Arabic characters using histograms of oriented gradient (HOG). Pattern Recognit. Image Anal. 2018 Apr; 28: 321-45. https://doi.org/10.1134/S1054661818020141
Hussain BA, Hathal MS. Developing Arabic License Plate Recognition System Using Artificial Neural Network and Canny Edge Detection. Baghdad Sci J. 2020 Sep. 1; 17(3): 909-15. https://doi.org/10.21123/bsj.2020.17.3.0909
Gunawan TS, Noor AF, Kartiwi M. Development of english handwritten recognition using deep neural network. Indones J Electr Eng Comput Sci. 2018 May;10(2):562-8. http://doi.org/10.11591/ijeecs.v10.i2.pp562-568
Alnedawe SM, Aljobouri HK. A New Model Design for Combating COVID-19 Pandemic Based on SVM and CNN Approaches. Baghdad Sci J. 2023. https://doi.org/10.21123/bsj.2023.7403
Kadir NH, Hidayah SN, NorasiahMohammad ZI. Comparison of convolutional neural network and bag of features for multi-font digit recognition. Indones J Electr Eng Comput Sci.. 2019 Sep; 15(3): 1322-8. http://doi.org/10.11591/ijeecs.v15.i3.pp1322-1328
Can YS, Kabadayı ME. Automatic cnn-based Arabic numeral spotting and handwritten digit recognition by using deep transfer learning in Ottoman population registers. Appl. Sci. 2020 Aug 6; 10(16): 5430. https://doi.org/10.3390/app10165430
Alkhawaldeh RS. Arabic (Indian) digit handwritten recognition using recurrent transfer deep architecture. Soft Comput. 2021 Feb; 25(4): 3131-41. https://doi.org/10.1007/s00500-020-05368-8
Alqudah A, Alqudah AM, Alquran H, Al-Zoubi HR, Al-Qodah M, Al-Khassaweneh MA. Recognition of handwritten arabic and hindi numerals using convolutional neural networks. Appl. Sci. 2021 Feb 9; 11(4): 1573. https://doi.org/10.3390/app11041573
Gupta D, Bag S. CNN-based multilingual handwritten numeral recognition: A fusion-free approach. Expert Syst Appl. 2021 Mar 1; 165: 113784. https://doi.org/10.1016/j.eswa.2020.113784
Finjan RH, Rasheed AS, Hashim AA, Murtdh M. Arabic handwritten digits recognition based on convolutional neural networks with resnet-34 model. Indones J Electr Eng Comput Sci.. 2021 Jan; 21(1): 174-8. https://doi.org/10.11591/ijeecs.v21.i1.pp174-178
Alabid N. Interpretation of Spatial Relationships by Objects Tracking in a Complex Streaming Video. ECTI-CIT. 2021 May 5; 15(2): 245-57. https://doi.org/10.37936/ecti-cit.2021152.240953
Kusetogullari H, Grahn H, Lavesson N. Handwriting image enhancement using local learning windowing, Gaussian Mixture Model and k-means clustering. IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2016 Dec 12 (pp. 305-310). IEEE. https://doi.org/10.1109/ISSPIT.2016.7886054
Hassan AK. Arabic (Indian) Handwritten Digits Recognition Using Multi feature and KNN Classifier. JUBPAS. 2018 Feb 1; 26(4): 10-7. https://doi.org/10.29196/jub.v26i4.679
Alqaralleh BA, Alksasbeh MZ, Abukhalil T, Almahafzah H, Al Rawashdeh T. Recognition of handwritten Arabic (Indian) numerals using skeleton matching. Indones J Electr Eng Comput Sci. 2020 Sep; 19(3): 1461-8. https://doi.org/10.11591/ijeecs.v19.i3.pp1461-1468
Mohammed MJ, Tariq SM, Ayad H. Isolated Arabic handwritten words recognition using EHD and HOG methods. Indones J Electr Eng Comput Sci. 2021 May; 22(2): 193-200. https://doi.org/10.11591/ijeecs.v22.i2.pp801-808
Agarap AF. Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375. 2018 Mar 22. https://doi.org/10.48550/arXiv.1803.08375
Hamida S, Cherradi B, Ouajji H. Handwritten arabic words recognition system based on hog and gabor filter descriptors. In2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) 2020 Apr 16 (pp. 1-4). IEEE. https://doi.org/10.1109/IRASET48871.2020.9092067
Downloads
Issue
Section
License
Copyright (c) 2024 Bushra Mahdi Hasan, Zahraa Jasim Jaber, Ahmad Adel Habeeb
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
