Mon, Nov 4, 2024
[Archive]
Volume 15, Issue 2 (3-2023)
itrc 2023, 15(2): 29-41 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Modhej N, Teshnehlab M, Bastanfard A, Raiesdana S. Arabic Handwritten Recognition Using Hybrid CNN, HMM and an Intelligent Network Based on Dentate Gyrus of the Brain. itrc 2023; 15 (2) : 4
URL: http://journal.itrc.ac.ir/article-1-551-en.html
URL: http://journal.itrc.ac.ir/article-1-551-en.html
1- Department of Computer Engineering, Karaj Branch, Islamic Azad University, Karaj, Iran
2- Department of Electrical Engineering of K. N. Toosi University of Technology, Tehran, Iran
3- Department of Computer Engineering, Karaj Branch, Islamic Azad University, Karaj, Iran
4- Department of Biomedical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran
2- Department of Electrical Engineering of K. N. Toosi University of Technology, Tehran, Iran
3- Department of Computer Engineering, Karaj Branch, Islamic Azad University, Karaj, Iran
4- Department of Biomedical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran
Abstract: (1286 Views)
Handwritten character recognition has occupied a substantial area due to its applications in several fields and is used widely in the modern world. Handwritten Arabic recognition is a major challenge because of the high similarity in its characters and its various writing styles. Deep learning algorithms have recently shown high performance in this area. The problem is that a deep learning algorithm requires large datasets for training. To overcome this problem, an efficient architecture is presented in this study, which comprises Hidden Markovian Model for character modeling, Convolutional Neural Network for feature extraction, and an intelligent network for recognition. The proposed network is modeled based on the dentate gyrus of the hippocampus of the brain. This part of the brain is responsible for identifying highly overlapping samples. The handwritten Arabic alphabet is characterized by this high overlap. Modeling the functionality of the dentate gyrus can improve the accuracy of the handwritten Arabic characters. Experiments are done using IFN/ENIT, CMATERdb3.3.1 and, MADBase datasets. The proposed approach outperformed recently published works using the same dataset. Although in all the experiments, a character error rate (CER) of less than 1.63 was obtained, the CMATERdb3.3.1 dataset resulted in a CER of 0.35. Compared with the convolutional neural network, the proposed network showed superiority in recognizing patterns with high noise.
Article number: 4
Keywords: Handwritten Arabic recognition, Convolutional Neural Network, Hidden Markovian Model, Dentate Gyrus, Overlap.
References
1. [1] Sahlol AT, Abd Elaziz M, Mohammed A. AL-Qaness A,Kim S, "Handwritten Arabic Optical Character Recognition Approach Based on Hybrid Whale Optimization Algorithm With Neighborhood Rough Set", IEEE ACCESS, 2020, vol. 8, pp. vol., pp. 23011-23021. [DOI:10.1109/ACCESS.2020.2970438]
2. [2] Boufenar C, Kerboua A, Batouche M, "Investigation on Deep Learning for Off-line Handwritten Arabic Character Recognition. Cognitive System Research",2018, vol. 50, pp. 180-195. [DOI:10.1016/j.cogsys.2017.11.002]
3. [3] Ghanim TM, Khalil MI, Abbas HM, "Comparative Study on Deep Convolution Neural Networks DCNN-based Offline Arabic Handwriting Recognition", IEEE ACCESS, 2020, vol. 8, pp. 95465 - 9548. [DOI:10.1109/ACCESS.2020.2994290]
4. [4] Abandah GA, Younis KS, Khedher MZ, "Handwritten arabic character recognition using multiple classifiers based on letter form. in: Proceedings of the 5th IASTED International Conference on Signal Processing", Pattern Recognition, and Applications (SPPRA'08), 2008, pp.128-133.
5. [5] Abandah GA, Malas TM, "Feature selection for recognizing handwritten Arabic letters", Dirasat Engineering Sciences Journal, 2010, vol. 37, no 2, pp.242-256.
6. [6] Sahlol AT, Elfattah MA, Suen YC, Hassanien AE, "Particle swarm optimization with random forests for handwritten Arabic recognition system", Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016, pp. 437-446. [DOI:10.1007/978-3-319-48308-5_42]
7. [7] Sahlol AT, Suen CY, Zawbaa HM, Hassanien AE, Elfattah MA, "Bio-inspired BAT optimization algorithm for handwritten Arabic characters recognition", IEEE Congress on Evolutionary Computation (CEC), Vancouver, 2016, pp. 1749-1756. [DOI:10.1109/CEC.2016.7744000]
8. [8] Morris AM, Churchwell JC, Raymond PK, Gilbert PE, "Selective Lesions of the Dentate Gyrus Produce Distributions in Place Learning for Adjacent Spatial Locations", Neurobiology of Learning and Memory,2012, vol. 97, no. 3, pp. 326, 331. [DOI:10.1016/j.nlm.2012.02.005] [PMID] []
9. [9] Bernstein E, McNally R. J., "Examining the effects of exercise on pattern separation and the moderating effects of mood symptoms, Behavior therapy, 2019, vol. 50, no. 3, pp. 582-593. [DOI:10.1016/j.beth.2018.09.007] [PMID]
10. [10] Sahlol AT, Suen C, "A novel method for the recognition of isolated handwritten arabic characters", arXiv preprint arXiv, 2014, pp. 1402-6650.
11. [11] Bahashwan MA, Abu-Bakar SAR, "Offline Handwritten Arabic Character Recognition using Features Extracted from Curvelet and Spatial Domains", Research Journal of Applied Sciences, Engineering and Technology, 2015, vol. 11, no. 2, pp.158-164. [DOI:10.19026/rjaset.11.1702]
12. [12] Rashad M, Amin K, Hadhoud M, Elkilani W, "Arabic character recognition using statistical and geometric moment features. Japan-Egypt", Conference on Electronics, Communications and Computers, 2012, Alexandria, pp. 68-72. [DOI:10.1109/JEC-ECC.2012.6186959]
13. [13] Al-Jawfi R, "Handwriting arabic character recognition lenet using neural network", International Arab Journal of Information Technolog, 2009, vol. 6, no. 3, pp. 304-309.
14. [14] Abandah GA, Jamour FT, Qaralleh EA, "Recognizing handwritten Arabic words using grapheme segmentation and recurrent neural networks",InternationalJournal on Document Analysis and Recognition (IJDAR), 2014, vol. 17, no. 3, pp. 275-291. [DOI:10.1007/s10032-014-0218-7]
15. [15] Graves A, "Offline arabic handwriting recognition with multi-dimensional recurrent neural networks," in Guide to OCR for Arabic, Springer-Verlag London, 2012, pp.297-313. [DOI:10.1007/978-1-4471-4072-6_12]
16. [16] Awni M, Khalil MI, Abbas HM, "Deep learning ensemble for offline arabisc handwritten words recognition" in 14th International Conference on Computer Engineering and Systems (ICCES), IEEE,2019, pp. 40-45. [DOI:10.1109/ICCES48960.2019.9068184]
17. [17] Aljuaid H, Mohamad D, Sarfraz M, "Arabic handwriting recognition using projection profile and genetic approach", in: 2009 Fifth International Conference on Signal Image Technology and Internet Based Systems. [DOI:10.1109/SITIS.2009.29]
18. [18] Mohamad RAH, Likforman-Sulem L, Mokbel C, "Combining slanted-frame classifiers for improved hmm-based arabic handwriting recognition", IEEE transactions on pattern analysis and machine intelligence, 2009, vol. 31, no. 7, pp. 1165-1177. [DOI:10.1109/TPAMI.2008.136] [PMID]
19. [19] AlKhateeb JH, Ren J, Jiang J, Al-Muhtaseb H, "Offline handwritten Arabic cursive text recognition using hidden markov models and re-ranking. Pattern Volume 15- Number 2 - 2023 (29 -41) 39 Recognition Letters, 2011, vol. 32, no. 8, pp. 1081-1088. [DOI:10.1016/j.patrec.2011.02.006]
20. [20] Ahmad T, Fink GA, "Handwritten arabic text recognition using multi-stage sub-core-shape hmms",International Journal on Document Analysis and Recognition (IJDAR), 2019, vol. 22, pp. 1-21. [DOI:10.1007/s10032-019-00339-8]
21. [21] Sadr H, Pedram MM, Teshnehlab M, "Multi-View Deep Network: A Deep Model Based on Learning Features From Heterogeneous Neural Networks for Sentiment Analysis", IEEE ACCESS, 2020, vol. 8, pp. 86984-86997. [DOI:10.1109/ACCESS.2020.2992063]
22. [22] Choi W, Duraisamy K, Kim RG, Doppa JR, Pande PP, Marculescu D, Marculescu R, "On-Chip Communication Network for Efficient Training of Deep Convolutional Networks on Heterogeneous Manycore Systems", IEEE Transactions on Computers, 2018, vol.67, no. 5, pp. 672-686. [DOI:10.1109/TC.2017.2777863]
23. [23] Vivekanandan K, Praveena N, "Hybrid convolutional neural network (CNN) and long‐short term memory (LSTM) based deep learning model for detecting shilling attack in the social‐aware network", Journal of Ambient Intelligence and Humanized Computing, 2020, [DOI:10.1007/s12652-020-02164-y]
24. [24] Essa N, El-Daydamony E, Mohamed MM, "Enhanced technique for arabic handwriting recognition using deep belief network and a morphological algorithm for solving ligature segmentation" ETRI Journal, 2018, vol. 40, no. 6, pp. 774-787. [DOI:10.4218/etrij.2017-0248]
25. [25] Yan R, Peng L, Bin G, Wang S, Cheng Y, "Residual recurrent neural network with sparse training for offline arabic handwriting recognition", in 2017 14th IAPR International Conference on Document Analysis and [DOI:10.1109/ICDAR.2017.171] [PMID] []
26. Recognition (ICDAR), 2017, IEEE vol. 1, pp. 1031-1037.
27. [26] Elleuch M, Tagougui N, Kherallah M, "Optimization of dbn using regularization methods applied for recognizing Arabic handwritten script", Procedia Computer Science 2017, vol. 108, pp. 2292-2297 [DOI:10.1016/j.procs.2017.05.070]
28. [27] Elleuch M, Tagougui N, Kherallah M, "Arabic handwritten characters recognition using Deep Belief Neural", 12th International Multi-Conference on Systems, Signals & Devices (SSD15) Mahdia,2015, pp.1-5. [DOI:10.1109/SSD.2015.7348121]
29. [28] Poznanski A, Wolf L, "Cnn-n-gram for handwriting word recognition", in Proceedings of the IEEE conference on computer vision and pattern recognition,2016, pp. 2305-2314. [DOI:10.1109/CVPR.2016.253]
30. [29] Bluche, T, Ney H, Kermorvant C, "Tandem HMM with convolutional neural network for handwritten word recognition", In: 38th International Conference on Acoustics Speech and Signal Processing (ICASSP2013), 2013, pp. 2390-2394. [DOI:10.1109/ICASSP.2013.6638083]
31. [30] El-Sawy A, Loey M, Hazem EB, "Arabic handwritten characters recognition using convolutional neural network", WSEAS Transactions on Computer Research, 2017, vol. 108, pp. 11-19.
32. [31] hranjany S, Razzazi F, Ghassemian MH, "A very high accuracy handwritten character recognition system for Farsi/Arabic digits using convolutional neural networks. in: Bio-Inspired Computing: Theories and Ap", 525 plications (BIC-TA), 2010 IEEE Fifth International Conference on, 2010, pp. 1585-1592. [DOI:10.1109/BICTA.2010.5645265]
33. [32] Maalej R, Kherallah M, "Maxout into mdlstm for offline arabic handwriting recognition. in International Conference on Neural Information Processing", 2019, Springer pp. 534-545. [DOI:10.1007/978-3-030-36718-3_45]
34. [33] Elleuch M, Tagougui N, Kherallah M, "Deep learning for feature extraction of arabic handwritten script," in International Conference on Computer Analysis of Images and Patterns, 2015, Springer, pp. 371-382. [DOI:10.1007/978-3-319-23117-4_32]
35. [34] Elleuch M, Maalej R, Kherallah M, "A new design based-svm of the cnn classifier architecture with dropout for offline arabic handwritten recognition", Procedia Computer Science, 2016, vol. 80, pp. 1712-1723. [DOI:10.1016/j.procs.2016.05.512]
36. [35] Amrouch M, Rabi M, "Deep neural networks features for arabic handwriting recognition. in International Conference on Advanced Information Technology, Services and Systems, 2017, Springer, pp. 138-149. [DOI:10.1007/978-3-319-69137-4_14]
37. [36] Amrouch M, Rabi M, Es-Saady Y, "Convolutional feature learning and cnn based hmm for Arabic handwriting recognition", in International Conference on Image and Signal Processing", 2018, Springer, pp. 265-274. [DOI:10.1007/978-3-319-94211-7_29]
38. [37] Sahlol AT, Suen CY, Elbasyoni MR, Sallam AA, "A proposed OCR algorithm for cursive handwritten arabic character recognition. J. Pattern Recognit. Intell. Syst 2014, vol. 2, no. 1, pp. 90-104.
39. [38] Sahlol AT, Suen CY, Elbasyoni MR, Sallam AA, " Investigating of preprocessing techniques and novel features in recognition of handwritten arabic characters. In: El Gayar N., Schwenker F., Suen C.(eds) Artificial Neural Networks in Pattern Recognition.ANNPR 2014. Lecture Notes in Computer Science Springer, 2014, Cham vol. 8774, pp. 264-276. [DOI:10.1007/978-3-319-11656-3_24]
40. [39] Krizhevsky A, Sutskever I, Hinton GE, "Imagenet classification with deep convolutional neural networks", in Advances in neural information processing systems, 2012, pp. 1097-1105.
41. [40] Xie S, Girshick R, Dollár P, Tu Z, He K, "Aggregated residual transformations for deep neural Networks", in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1492-1500. [DOI:10.1109/CVPR.2017.634]
42. [41] Zhu Y, Newsam S, "Densenet for dense flow", in 2017 IEEE international conference on image processing(ICIP), 2017, pp. 790-794. [DOI:10.1109/ICIP.2017.8296389] []
43. [42] 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. 770-778. [DOI:10.1109/CVPR.2016.90] [PMID]
44. [43] Kumaran D, Maguire EA, "The Dynamics of Hippocampal Activation during Encoding of overlapping Sequences", Neuron, 2006, vol. 49, no. 4, pp. 617-629. [DOI:10.1016/j.neuron.2005.12.024] [PMID]
45. [44] Morris AM, Curtis BJ, Churchwell JC, Maasberg DW, Kesner RP, "Temporal associations for spatial events: The role of the dentate gyrus", Behavioral Brain Research, 2013, vol. 256, pp. 250-256. [DOI:10.1016/j.bbr.2013.08.021] [PMID]
46. [45] Chavlis S, Petrantonakis PC, Poirazi P, "Dendrites of Dentate Gyrus Granule Cells Contribute to Pattern Separation by Controlling Sparsity", 2017,Hippocampus vol. 27, no. 1, pp. 89-110. [DOI:10.1002/hipo.22675] [PMID] []
47. [46] Deng W, Aimone JB, Gage FH, "New neurons and new memories: how does adult hippocampal neurogenesis affect learning and memory?", Nature Reviews Neuroscience, 2010, vol. 11, no. 5, pp. 339-350. Volume 15- Number 2 - 2023 (29 -41) 40 [DOI:10.1038/nrn2822] [PMID] []
48. [47] Engin E, Zarnow7aska ED, Benke D, Tsvetkov E, Sigal M, Keist R, Bolshakov VY, Pearce RA, Rudolph U, "Tonic Inhibitory Control of Dentate Gyrus Granule Cells by α5-Containing GABAA Receptors Reduces Memory Interference", JNeurosci, 2015, vol. 35, no. 40,pp. 13698-13712. [DOI:10.1523/JNEUROSCI.1370-15.2015] [PMID] []
49. [48] Hananeia N, Benuskova L, "Computational Simulation of Dentate Gyrus cell - The role of metaplasticity",Neurocomputing, 2016, vol. 175, pp. 300-309. [DOI:10.1016/j.neucom.2015.10.063]
50. [49] Fuhs MC, Touretzky DS, "Synaptic learning models of map separation in the hippocampus",cNeurocomputing, 2000, vol. 32, pp. 379-384. [DOI:10.1016/S0925-2312(00)00189-2]
51. [50] Kali S, Dayan P, "The involvemen of recurrent connections in area CA3 in establishing the properties of place fields: A model", J Neurosci, 2000, vol. 20, pp.7463-7477. [DOI:10.1523/JNEUROSCI.20-19-07463.2000] [PMID] []
52. [51] Myers CE, Scharfman HE, "A role for hilar cells in pattern separation in dentate gyrus: A computational approach", Hippocampus, 2009, vol. 19, no. 4, pp. 321-337. [DOI:10.1002/hipo.20516] [PMID] []
53. [52] Pechwitz M, Maddouri SS, Märgner V, Ellouze N, Amiri H, "IFN/ENIT-database of handwritten Arabic words. in Proc. of CIFED, 2002, vol. 2, pp. 127-136.
54. [53] Wu H, Gu X, "Towards dropout training for convolutional neural networks", Neural Netw, 2015, vol. 71, pp. 1-10. [DOI:10.1016/j.neunet.2015.07.007] [PMID]
55. [54] Das, Nibaran, Reddy, Mohan J, Sarkar, Ram, Subhadip B, Kundu, Mahantapas, Nasipuri, Mita, Basu, Dipak Kumar, "A statistical topological feature combination for recognition of handwritten numerals", Applied Soft Computing, 2012, vol. 12, no. 8, pp. 2486 - 2495. [DOI:10.1016/j.asoc.2012.03.039]
56. [55] Sudholt S, Fink GA, "Phocnet: A deep convolutional neural network for word spotting in handwritten documents," in 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE,2016, pp. 277-282. [DOI:10.1109/ICFHR.2016.0060]
57. [56] Ashiquzzaman A, Tushar AK, "Handwritten arabic numeral recognition using deep learning neural networks", In IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR) IEEE,2017, pp. 1-4. [DOI:10.1109/ICIVPR.2017.7890866]
58. [57] Ashiquzzaman A, Tushar AK, Rahman A, Mohsin F, "An Efficient Recognition Method for Handwritten Arabic Numerals Using CNN with Data Augmentation and Dropout. In: Balas V., Sharma N., Chakrabarti A. (eds) Data Management, Analytics and Innovation. Advances in Intelligent Systems and Computing, Springer, Singapore 808, 2019, [DOI:10.1007/978-981-13-1402-5_23]
59. [58] Finjan RH, Rasheed RS, Hashim AA, Murtdha M, "Arabic handwritten digits recognition based on convolutional neural networks with resnet-34 model", Indonesian Journal of Electrical Engineering and Computer Science, 2020, vol. 21, no. 1, pp. 174-178. [DOI:10.11591/ijeecs.v21.i1.pp174-178]
60. [59] Maalej R, Kherallah M, "Convolutional neural network and blstm for offline arabic handwriting recognition", in 2018 International Arab Conference on Information Technology (ACIT) IEEE, 2018, pp. 1-6. [DOI:10.1109/ACIT.2018.8672667]
61. [60] Boquera SE, Castro-Bleda MJ, Moya JG, Martinez FM, "Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, vol. 33, no. 4, pp. 767-779. [DOI:10.1109/TPAMI.2010.141] [PMID]
| Rights and permissions | |
 | This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
