Identification of Handwritten Digits using Machine Learning
Keywords:
Handwritten recognition, CNN, SVM, machine learning algorithm, classification algorithmAbstract
Handwritten Digit Recognition is one of the practical issues in sample recognition applications. The task for handwritten recognition has been difficult due to various variations in written styles. The capacity to create an effective algorithm that can detect handwritten numbers given by users via a scanner, tablet, and other digital devices is at the core of the issue. Artificial intelligence is used in machine learning, which automatically corrects errors based on experience. In this paper, we present a proposal to off-line Handwritten Digit Recognition through machine learning techniques. This article compares classifiers like KNN, PSVM, NN, and convolution neural network on the basis of performance, accuracy, time, sensitivity, positive productivity, and specificity while using different parameters with the classifiers. The handwritten digits (0 to 9) from the well-known Modified National Institute of Standard and Technology (MNIST) dataset are recognized.
References
Rahaman MA, Mahin M, Ali MH, Hasanuzzaman M. BHCDR: Real-Time Bangla Handwritten Characters and Digits Recognition using Adopted Convolutional Neural Network. In 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT) 2019 May 3 (pp. 1–6). IEEE.
Alsobaie H, Ahmad I. Compression Techniques for Handwritten Digit Recognition. In2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies (3ICT) 2020 Dec 20 (pp. 1–6). IEEE.
Debnath B, Anika A, Abrar MA, Chowdhury T, Chakraborty R, Khan AI, Fattah SA, Shahnaz C. Automatic Handwritten words on Touchscreen to Text file converter. In TENCON 2018-2018 IEEE Region 10 Conference 2018 Oct 28 (pp. 0219–0223). IEEE.
Wang H, Zhou Z, Li Y, Chen Z, Lu P, Wang W, Liu W, Yu L. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18 F-FDG PET/CT images. EJNMMI Research. 2017 Dec; 7: 1–1.
Ahlawat S, Choudhary A. Hybrid CNN-SVM classifier for handwritten digit recognition. Procedia Comput Sci. 2020 Jan 1; 167: 2554–2560.
Zahangir Alom M, Sidike P, Taha TM, Asari VK. Handwritten Bangla Digit Recognition Using Deep Learning. arXiv e-prints. 2017 May:arXiv-1705.
Hanning Y, Peng W. Handwritten digits recognition using multiple instance learning. In2013 IEEE International Conference on Granular Computing (GrC) 2013 Dec 13 (pp. 408–411). IEEE.
Priya, Rajendra Singh, Soni Changlani, Handwritten Digit Recognition using Proximal Support Vector Machine, J Emerg Technol Innov Res. April 2017; 4(04): 251–254, ISSN Number: 2349–5162.
Ghosh MM, Maghari AY. A comparative study on handwriting digit recognition using neural networks. In2017 international conference on promising electronic technologies (ICPET) 2017 Oct 16 (pp. 77–81). IEEE.
Kayumov Z, Tumakov D, Mosin S. An effect of binarization on handwritten digits recognition by hierarchical neural networks. In Second International Conference on Image Processing and Capsule Networks: ICIPCN 2021 2 2022 (pp. 94–106). Springer International Publishing.
Challa A. Automatic Handwritten Digit Recognition On Document Images Using Machine Learning Methods. 2019.
LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L. Handwritten digit recognition with a back-propagation network. Advances in Neural Information Processing Systems. 1989; 2.
Patil P. Handwritten digit recognition using various machine learning algorithms and models. International Journal of Innovative Research in Computer Science & Technology (IJIRCST). 2020 Jul; 23: ISSN 2347–5552.
Siddique F, Sakib S, Siddique MA. Recognition of handwritten digit using convolutional neural network in python with tensorflow and comparison of performance for various hidden layers. In2019 5th International Conference on Advances in Electrical Engineering (ICAEE) 2019 Sep 26 (pp. 541–546). IEEE.
Pashine S, Dixit R, Kushwah R. Handwritten digit recognition using machine and deep learning algorithms. arXiv preprint arXiv:2106.12614. 2021 Jun 23.
Gundavarapu MR, Yannam VV, Velagala A, Lankela SR, Koundinya S, Regonda SC. Smart Bot for Handwritten Digit String Recognition. In2022 International Conference for Advancement in Technology (ICONAT) 2022 Jan 21 (pp. 1–5). IEEE.
Persi E, Wolf YI, Horn D, Ruppin E, Demichelis F, Gatenby RA, Gillies RJ, Koonin EV. Mutation–selection balance and compensatory mechanisms in tumour evolution. Nat Rev Genet. 2021 Apr; 22(4): 251–262.
Rudraswamimath VR, Bhavanishankar K. Handwritten digit recognition using CNN. Int J Innov Sci Res Technol. 2019 Jun; 4(6): 182–187.
Sultana F, Sufian A, Dutta P. Advancements in image classification using convolutional neural network. In2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) 2018 Nov 22 (pp. 122–129). IEEE.
Von Thaden S, Hampton S. Exploring Alternative CNN for Digit and Letter Recognition. In2018 IEEE MIT Undergraduate Research Technology Conference (URTC) 2018 Oct 5 (pp. 1–4). IEEE.
Bhatia A, Kedia V, Shroff A, Kumar M, Shah BK. Fake currency detection with machine learning algorithm and image processing. In2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS) 2021 May 6 (pp. 755–760). IEEE.
Kumar A, Kumar A. Dog breed classifier for facial recognition using convolutional neural networks. In2020 3rd International Conference on Intelligent Sustainable Systems (ICISS) 2020 Dec 3 (pp. 508–513). IEEE.
Dash A, Sahu A, Shringi R, Gamboa J, Afzal MZ, Malik MI, Dengel A, Ahmed S. Airscript-creating documents in air. In2017 14th IAPR international conference on document analysis and recognition (ICDAR) 2017 Nov 9 (Vol. 1, pp. 908–913). IEEE.
Lohit S, Kulkarni K, Turaga P. Direct inference on compressive measurements using convolutional neural networks. In2016 IEEE International Conference on Image Processing (ICIP) 2016 Sep 25 (pp. 1913–1917). IEEE.
Sethi R, Kaushik I. Handwritten digit recognition using machine learning. In2020 IEEE 9th International Conference on Communication Systems and Network Technologies (CSNT) 2020 Apr 10 (pp. 49–54). IEEE.
