Abstract

In recent years, handwritten character recognition has become an active research field. In particular, digitalization has triggered the interest of researchers from various computing disciplines to address several handwriting related challenges. Despite these efforts, there are still opportunities for the development and improvement of the recognition of the handwritten Arabic letters. In this paper, we designed and developed a deep ensemble architecture in which ResNet-18 architecture is exploited to model and classify character images. Specifically, we adapted ResNet-18 by adding a dropout layer after all convolutional layer and integrated it in multiple ensemble models to automatically recognize isolated handwritten Arabic characters. A standard Arabic Handwritten Character Dataset (AHCD) was used in the experiments to train and assess all the proposed models. Satisfactory results were obtained using all models. The best-attained accuracy was 98.30% using a typical ResNet-18 model. Similarly, 98.00% and 98.03% accuracies were obtained using an ensemble model with one fully connected layer (1 FC) and an ensemble with two fully connected layers (2 FC) coupled with a dropout layer, respectively.

Keyword

Handwriting character recognition, Arabic, OCR, Online recognition, Handwritten recognition.

Cite this article

Alyahya H, Ismail MM, Al-Salman A

Refference

[1][1]Davis RH, Lyall J. Recognition of handwritten characters—a review. Image and vision computing. 1986; 4(4):208-18.

[2][2]Inuganti S, Ramisetty RR. Preprocessing of online handwritten Telugu character recognition. International Journal of Advanced and Applied Sciences. 2017; 4(7):179-89.

[3][3]Arica N, Yarman-Vural FT. An overview of character recognition focused on off-line handwriting. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews). 2001; 31(2):216-33.

[4][4]Al-Salman A, Alyahya H. Arabic online handwriting recognition: a survey. In proceedings of the 1st international conference on internet of things and machine learning 2017 (pp. 1-4).

[5][5]Perwej Y, Chaturvedi A. Machine recognition of hand written characters using neural networks. arXiv preprint arXiv:1205.3964. 2012.

[6][6]El-Sheikh TS, El-Taweel SG. Real-time Arabic handwritten character recognition. Pattern Recognition. 1990; 23(12):1323-32.

[7][7]He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-8). IEEE.

[8][8]Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In proceedings of the IEEE conference on computer vision and pattern recognition 2015 (pp. 1-9).

[9][9]Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014.

[10][10]Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In advances in neural information processing systems 2012 (pp. 1097-105).

[11][11]LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998; 86(11):2278-324.

[12][12]Zhang Y. Deep convolutional network for handwritten Chinese character recognition. Computer Science Department, Stanford University. 2015.

[13][13]Alif MA, Ahmed S, Hasan MA. Isolated Bangla handwritten character recognition with convolutional neural network. In international conference of computer and information technology 2017 (pp. 1-6). IEEE.

[14][14]Abdurahman F. Handwritten Amharic character recognition system using convolutional neural networks. ICL 2020.

[15][[15]Aneja N, Aneja S. Transfer learning using CNN for handwritten Devanagari character recognition. In international conference on advances in information technology 2019 (pp. 293-6). IEEE.

[16][16]Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In proceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 4700-8).

[17][17]Acharya S, Pant AK, Gyawali PK. Deep learning based large scale handwritten Devanagari character recognition. In international conference on software, knowledge, information management and applications 2015 (pp. 1-6). IEEE.

[18][18]El-Sawy A, Loey M, El-Bakry H. Arabic handwritten characters recognition using convolutional neural network. WSEAS Transactions on Computer Research. 2017; 5:11-9.

[19][19]Younis KS. Arabic handwritten character recognition based on deep convolutional neural networks. Jordanian Journal of Computers and Information Technology. 2017; 3(3):186-200.

[20][20]Torki M, Hussein ME, Elsallamy A, Fayyaz M, Yaser S. Window-based descriptors for arabic handwritten alphabet recognition: a comparative study on a novel dataset. arXiv preprint arXiv:1411.3519. 2014.

[21][21]Najadat HM, Alshboul AA, Alabed AF. Arabic handwritten characters recognition using convolutional neural network. In international conference on information and communication systems 2019 (pp. 147-51). IEEE.

[22][22]Elmiad AK. Arab handwriting character recognition using deep learning. In international conference europe middle east & north africa information systems and technologies to support learning 2019 (pp. 410-5). Springer, Cham.

[23][23]Altwaijry N, Al-Turaiki I. Arabic handwriting recognition system using convolutional neural network. Neural Computing and Applications. 2020:1-3.

[24][24]Alom MZ, Taha TM, Yakopcic C, Westberg S, Sidike P, Nasrin MS, E et al. A state-of-the-art survey on deep learning theory and architectures. Electronics. 2019; 8(3):1-66.

[25][25]Almansari OA, Hashim NN. Recognition of isolated handwritten arabic characters. In international conference on mechatronics engineering 2019 (pp. 1-5). IEEE.