Top

Automatic Control and Computer Sciences

Published in:

01-06-2023

An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition

Author: Mamouni El Mamoun

Published in: Automatic Control and Computer Sciences | Issue 3/2023

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to extract features from character images. Then, a support vector machine (SVM) was used for classification. By combining CNN and SVM, the aim is to exploit both technologies’ strengths. Four hybrid models are proposed in this work. Several databases such as HACDB, HIJJA, AHCD, and MNIST were used to evaluate them. The results obtained are satisfactory compared to similar studies in the literature, with a test accuracy of 89.7, 88.8, 97.3, and 99.4%, respectively.

previous article Adaptive Peak Environmental Density Clustering Algorithm in Cloud Computing Technology

next article Spatial Adaptive Iterative Learning Control Based High-Speed Train Operation Tracking under External Disturbance

Vapnik, V., Statistical Learning Theory, New York: John Wiley & Sons, 1995.CrossRefMATH

Elleuch, M., Lahiani, H., and Kherallah, M., Recognizing Arabic handwritten script using support vector machine classifier, 15th Int. Conf. on Intelligent Systems Design and Applications (ISDA), Marrakesch, Morocco, 2015, IEEE, 2015, pp. 551–556, https://doi.org/10.1109/ISDA.2015.7489176

Elleuch, M. and Kherallah, M., An improved Arabic handwritten recognition system using deep support vector machines, Int. J. Multimedia Data Eng. Manage., 2016, vol. 7, no. 2, p. 1. https://doi.org/10.4018/IJMDEM.2016040101CrossRef

Mamouni E., Zennaki M., and Sadouni K., SVM model selection using PSO for learning handwritten Arabic characters, Comput., Mater. Continua, 2019, vol. 61, no. 3, pp. 995–1008. https://doi.org/10.32604/cmc.2019.08081CrossRef

Batista, G.C., Silva, W.L.S., de Oliveira, D.L., and Saotome, O., Automatic speech patterns recognition of commands using SVM and PSO, Multimed. Tools Appl., 2019, vol. 78, pp. 31709–31731. https://doi.org/10.1007/s11042-019-07956-9CrossRef

Sasaki, Yu., Emaru, T., and Ravankar, A.A., SVM based pedestrian detection system for sidewalk snow removing machines, 2021 IEEE/SICE International Symposium on System Integration (SII), Iwaki, Fukushima, Japan, 2021, IEEE, 2021, pp. 700–701. https://doi.org/10.1109/IEEECONF49454.2021.9382618

Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P., Gradient-based learning applied to document recognition, Proc. IEEE, 1998, vol. 86, no. 11, pp. 2278–2324. https://doi.org/10.1109/5.726791CrossRef

Biswas, A. and Islam, Md.S., An efficient CNN model for automated digital handwritten digit classification, J. Inf. Syst. Eng. Business Intell., 2021, vol. 7, no. 1. https://e-journal.unair.ac.id/JISEBI/article/view/24237/13992.

Altwaijry, N. and Al-Turaiki, I., Arabic handwriting recognition system using convolutional neural network, Neural Comput. Appl., 2021, vol. 33, pp. 2249–2261. https://doi.org/10.1007/s00521-020-05070-8CrossRef

10.

Chen, X., Li, H., Wu, Q., Ngan, K.N., and Xu, L., High-quality R-CNN object detection using multi-path detection calibration network, IEEE Trans. Circuits Syst. Video Technol., 2021, vol. 31, no. 2, pp. 715–727. https://doi.org/10.1109/TCSVT.2020.2987465CrossRef

11.

Huang, Ya. and Hu, H., A parallel architecture of age adversarial convolutional neural network for cross-age face recognition, IEEE Trans. Circuits Syst. Video Technol., 2021, vol. 31, no. 1, pp. 148–159. https://doi.org/10.1109/TCSVT.2020.2965739CrossRef

12.

Fukushima, K., Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern., 1980, vol. 36, pp. 193–202. https://doi.org/10.1007/BF00344251CrossRefMATH

13.

LeCun, Ya., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., and Jackel, L., Handwritten digit recognition with a backpropagation network, Advances in Neural Information Processing Systems, Touretzky, D., Ed., Morgan-Kaufmann, 1980, vol. 2. https://proceedings.neurips.cc/paper_files/paper/1989/file/ 53c3bce66e43be4f209556518c2fcb54-Paper.pdf.

14.

Chang, Ch.-Ch. and Lin, Ch.-J., LIBSVM: A library for support vector machines, ACM Trans. Intell. Syst. Technol., 2011, vol. 2, no. 3, pp. 1–27. https://doi.org/10.1145/1961189.1961199CrossRef

15.

Lawgali, A., Angelova, M., and Bouridane, A., HACDB: Handwritten Arabic characters database for automatic character recognition, European Workshop on Visual Information Processing (EUVIP), Paris, 2013, IEEE, 2013, pp. 255–259.

16.

El-Sawy, A., Loey, M., and Hazem, E., Arabic handwritten characters dataset, 2017. https://www.kaggle.com/ mloey1/ahcd1. Cited May 30, 2019.

17.

Abu Ghosh, M.M. and Maghari, A.Y., A comparative study on handwriting digit recognition using neural networks, 2017 Int. Conf. on Promising Electronic Technologies, Deir El-Balah, Palestine, 2017, IEEE, 2017, pp. 77–81. https://doi.org/10.1109/ICPET.2017.20

18.

Latif, G., Alghazo, J., Alzubaidi, L., Naseer, M.M., and Alghazo, Y., Deep convolutional neural network for recognition of unified multi-language handwritten numerals, IEEE 2nd Int. Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), London, 2018, IEEE, 2018, pp. 90–95. https://doi.org/10.1109/ASAR.2018.8480289

19.

Peres, A.A., Vieira, S.M., and Pinto, J.R.C., Hybrid neural models for automatic handwritten digits recognition, 2018 Int. Joint Conf. on Neural Networks (IJCNN), Rio de Janeiro, 2018, IEEE, 2018, pp. 1–8, https://doi.org/10.1109/IJCNN.2018.8489525

20.

Ahlawata, S. and Choudhary, A., Hybrid CNN-SVM classifier for handwritten digit recognition, Procedia Comput. Sci., 2020, vol. 167, pp. 2554–2560. https://doi.org/10.1016/j.procs.2020.03.309CrossRef

21.

Lawgali, A., An evaluation of methods for Arabic character recognition, Int. J. Signal Process., Image Process. Pattern Recognit., 2014, vol. 7, no. 6, pp. 211–220.

22.

El-Sawy, A., Loey, M., and El-Bakry, H., Arabic handwritten characters recognition using convolutional neural network, WSEAS Trans. Comput. Res., 2017, 5, pp. 11–19.

23.

Younis, Kh.S., Arabic handwritten characters recognition based on deep convolutional neural networks, Jordan J. Comput. Inf. Technol., 2018, vol. 3, no. 3, pp. 186–200. https://doi.org/10.5455/jjcit.71-1498142206CrossRef

Title: An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition
Author: Mamouni El Mamoun
Publication date: 01-06-2023
Publisher: Pleiades Publishing
Published in: Automatic Control and Computer Sciences / Issue 3/2023
Print ISSN: 0146-4116
Electronic ISSN: 1558-108X
DOI: https://doi.org/10.3103/S0146411623030069

Springer Professional

Abstract

Please log in to get access to your license.

Other articles of this Issue 3/2023

Adaptive Peak Environmental Density Clustering Algorithm in Cloud Computing Technology

Source Level Protection for HEVC Video Coded in Low Delay Mode for Real-Time Applications

Event-Triggered Exponential Synchronization of Nonfragile Neural Networks

A Unified Technique for Prediction and Optimization of Future Outcomes under Parametric Uncertainty via Pivotal Quantities and Ancillary Statistics

Comparison of Advanced Classification Algorithms Based Intrusion Detection from Real-Time Dataset

Improving the Feature Section Method Based on Genetic Algorithm to Increase the Efficiency of Detecting Phishing Websites