International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

Performance Analysis on Bangla Handwritten Digit Recognition using CNN and Transfer


Affiliations
1 Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh
 

A computer can read and interpret intelligible handwritten input from sources like paper, photos, and other devices, known as Handwriting recognition (HWR). Besides, handwritten recognition is an interesting challenge in machine learning and deep learning. Because several strategies and approaches have been followed already to solve this challenge, machine learning and deep learning provided the best results.Handwritten digit recognition is a part of HWR. It is getting popular day by day because many applications could be made using this system like OCR, postal code recognition, license plate recognition, bank checks recognition, etc. Besides, the importance of recognizing the Bangla digit from the document is increasing. But the works available in Bangla handwritten digit recognition are very few.

Similarly, none of them are robust, and some of them are overfitted. Therefore, we need to make some improvements to this system considering its importance. This paper explores the presentation of transfer learning with the help of some best-in-class profound CNN strategies for the acknowledgment of manually written Bangla digits. It considers two deep CNN architectures, such as Mobile Net and Residual Network (Reset) based on performance and accuracy. This model was trained and tested with the CMATERdb dataset. The study suggests that transfer learning provides 97% accurate results, where traditional CNN provides 86-92 %.


Keywords

BangleHandwritten Digit, CNN, MobileNet, ResNet50, Transfer Learning.
User
Notifications
Font Size

  • T. Hassan, and A.H. Khan, “Handwritten Bangla numeral recognitionusing Local Binary Pattern,” In Electrical Engineering and Information Communication Technology (ICEEICT), 2015 InternationalConference on, pp. 1-4. IEEE, 2015,doi: 10.1109/ICEEICT.2015.7307371

  • U. Bhattacharya, and B. B Chaudhuri, “Handwritten numeral databasesof indian scripts and multistage recognition of mixed numerals”, InIEEE transactions on pattern analysis and machine intelligence, 31(3)on pp.444-457. IEEE,2009.

  • A. Shawon, M. Jamil-Ur Rahman, F. Mahmud, and M. M. Arefin Zaman, "Bangla Handwritten Digit Recognition Using Deep CNN for Large and Unbiased Dataset," 2018 International Conference on Bangla Speech and Language Processing (ICBSLP), Sylhet, 2018, pp. 1-6, doi: 10.1109/ICBSLP.2018.8554900.

  • R. V. Kumar Reddy, B. Srinivasa Rao and K. P. Raju, "Handwritten Hindi Digits Recognition Using Convolutional Neural Network with RMS prop Optimization," 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2018, pp. 45-51, doi: 10.1109/ICCONS.2018.8662969.

  • P. V. Bhagyasree, A. James and C. Saravanan, "A Proposed Framework for Recognition of Handwritten Cursive English Characters using DAG-CNN," 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), CHENNAI, India, 2019, pp. 14, doi: 10.1109/ICIICT1.2019.8741412.

  • Al-Wzwazy, Haider. (2016). Handwritten Digit Recognition Using Convolutional Neural Networks. International Journal of Innovative Research in Computer and Communication Engineering. 4.

  • Das, Nibaran & Sarkar, Ram &Basu, Subhadip & Kundu, Mahantapas&Nasipuri, Mita&Basu, Dipak. (2012). A genetic algorithm-based region sampling for selection of local features in handwritten digit recognition application. Applied Soft Computing. 12. 10.1016/j.asoc.2011.11.030.

  • D. H. Hubel and T. N. Wiesel, “Receptive fields and functional architecture of monkey striate cortex,” Journal of Physiology, vol. 195, no. 1, pp. 215–243, 1968.

  • "Understanding of Convolutional Neural Network (CNN) — Deep Learning", Medium, 2020. [Online]. Available: https://medium.com/@RaghavPrabhu/understandin g-of-convolutional-neural-network-cnn-deeplearning99760835f148. [Accessed: 30- Sep- 2020].

  • "CNN Architectures — LeNet, AlexNet, VGG, GoogLeNet and ResNet", Medium, 2020. [Online]. Available: https://medium.com/@RaghavPrabhu/cnnarchitectureslenet-alexnet-vgg-googlenet-andresnet-7c81c017b848. [Accessed: 30- Sep- 2020].

  • A. Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications", arXiv.org, 2020. [Online]. Available: https://arxiv.org/abs/1704.04861. [Accessed: 30Sep- 2020].

  • M. Alom, P. Sidike, T. Taha and V. Asari, "Handwritten Bangla Digit Recognition Using Deep Learning", arXiv.org, 2020. [Online]. Available: https://arxiv.org/abs/1705.02680. [Accessed: 16Oct- 2020].

  • O. F. Rakib, S. Akter, M. A. Khan, A. K. Das and K. M. Habibullah, "Bangla Word Prediction and Sentence Completion Using GRU: An Extended Version of RNN on Ngram Language Model," 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), 24-25 December, Dhaka.

  • E. A. Emon, S. Rahman, J. Banarjee, A. K. Das and T. Mittra, "A Deep Learning Approach to Detect Abusive Bengali Text," 2019 7th International Conference on Smart Computing & Communications (ICSCC), Sarawak, Malaysia, Malaysia, 2019.

  • M. M. Hossain, M. F. Labib, A. S. Rifat, A. K. Das and M. Mukta, "Auto-correction of English to Bengali Transliteration System using Levenshtein Distance," 2019 7th International Conference on Smart Computing & Communications (ICSCC), Sarawak, Malaysia, Malaysia, 2019.

  • M. D. Drovo, M. Chowdhury, S. I. Uday and A. K. Das, "Named Entity Recognition in Bengali Text Using Merged Hidden Markov Model and Rule Base Approach," 2019 7th International Conference on Smart Computing &Communications (ICSCC), Sarawak, Malaysia, Malaysia, 2019.

  • E. Biswas and A. K. Das, "Symptom-Based Disease Detection System In Bengali Using Convolution Neural Network," 2019 7th International Conference on Smart Computing & Communications (ICSCC), Sarawak, Malaysia, Malaysia, 2019.

  • A. K. Das, A. Ashrafi and M. Ahmmad, "Joint Cognition of Both Human and Machine for Predicting Criminal Punishment in Judicial System," 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS), Singapore, 2019, pp. 36-40.

  • R. A. Tuhin, B. K. Paul, F. Nawrine, M. Akter and A. K. Das, "An Automated System of Sentiment Analysis from Bangla Text using Supervised Learning Techniques," 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS), Singapore, 2019, pp. 360-364.

  • J. Islam, M. Mubassira, M. R. Islam and A. K. Das, "A Speech Recognition System for Bengali Language using Recurrent Neural Network," 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS), Singapore, 2019, pp. 73-76.

  • T. F. Mumu, I. J. Munni, and A. K. Das, “Depressed People Detection from Bangla Social Media Status using LSTM and CNN Approach”, J. eng. adv., vol. 2, no. 01, pp. 41-47, Mar. 2021.

  • M. T. Hossain, M. W. Hasan and A. K. Das, "Bangla Handwritten Word Recognition System Using Convolutional Neural Network," 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM), 2021, pp. 1-8.

  • A. K. Das, A. A. Asif, A. Paul and M. N. Hossain, "Bangla hate speech detection on social media using attention-based recurrent neural network" Journal of Intelligent Systems 30, no. 1 (2021): 578-591.

  • M. S. S.Khan, S. R. Rafa, and A. K. Das, "Sentiment Analysis on Bengali Facebook Comments To Predict Fan's Emotions Towards a Celebrity" Journal of Engineering Advancements,pp. 118-124, July 2021.

  • M. Mubassira, and A. K. Das, “Implementation Of Recurrent Neural Network With Language Model For Automatic Articulation Identification System In Bangla”, International Journalof Advanced Networking and Applications - IJANA., vol. 12, no. 06, pp. 4800-4808, May-June, 2021.


Abstract Views: 198

PDF Views: 1




  • Performance Analysis on Bangla Handwritten Digit Recognition using CNN and Transfer

Abstract Views: 198  |  PDF Views: 1

Authors

Afsana Hossain
Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh
Md. Sabbir Hasan
Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh
Md. Mujtaba Asif
Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh
Amit Kumar Das
Department of Computer Science and Engineering, East West University, Dhaka, Bangladesh

Abstract


A computer can read and interpret intelligible handwritten input from sources like paper, photos, and other devices, known as Handwriting recognition (HWR). Besides, handwritten recognition is an interesting challenge in machine learning and deep learning. Because several strategies and approaches have been followed already to solve this challenge, machine learning and deep learning provided the best results.Handwritten digit recognition is a part of HWR. It is getting popular day by day because many applications could be made using this system like OCR, postal code recognition, license plate recognition, bank checks recognition, etc. Besides, the importance of recognizing the Bangla digit from the document is increasing. But the works available in Bangla handwritten digit recognition are very few.

Similarly, none of them are robust, and some of them are overfitted. Therefore, we need to make some improvements to this system considering its importance. This paper explores the presentation of transfer learning with the help of some best-in-class profound CNN strategies for the acknowledgment of manually written Bangla digits. It considers two deep CNN architectures, such as Mobile Net and Residual Network (Reset) based on performance and accuracy. This model was trained and tested with the CMATERdb dataset. The study suggests that transfer learning provides 97% accurate results, where traditional CNN provides 86-92 %.


Keywords


BangleHandwritten Digit, CNN, MobileNet, ResNet50, Transfer Learning.

References