Abstract
Handwritten digit recognition is a complex problem that has stumped even the brilliant minds of this century. Getting precise results from different handwritten samples has been a challenge that needs to be addressed due to the occurrence of this issue in several sectors like document verification, post mail, deciphering, etc. Hence, we introduce our paper as a response to the requirement of an accurate model that can acutely recognize and then predict the handwriting of a variety of individuals with ease. Our model aims to do number recognition through the implementation of neural networks. We tested out different models with each optimizer to verify which model provided the best performance and with which optimizer. Optimizers are an inherent part of Deep learning, and they are used to upgrade the weights, so the model can learn accordingly and get a more accurate system. Instead of just comparing the performance of various optimizers with only one model, we compared different model performances, while trying to select the optimizer that would best suit that learning model. Rigorous training and experimentalizing have resulted in an accuracy of 98.55% for an ANN model employed with an Adagrad optimizer.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Agnes Lydia A (2019) Adagrad - an optimizer for stochastic gradient. Int J Inform Comput Sci 6:566–568
Ahlawat S, Choudhary A (2020) Hybrid CNN-SVM classifier for handwritten digit recognition. Procedia Comput Sci 167:2554–2560
Albahli S, Alhassan F, Albattah W, Khan RU (2020) Handwritten digit recognition: Hyperparameters-based analysis. Appl Sci 10(17):5988
Ali S, Shaukat Z, Azeem M, Sakhawat Z, Mahmood T (2019) An efficient and improved scheme for handwritten digit recognition based on a convolutional neural network. SN Appl Sci 1(9):1–9
Almodfer R, Xiong S, Mudhsh M, Duan P (2017) Enhancing AlexNet for Arabic handwritten word recognition using incremental dropout. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, pp 663–669
Altwaijry N, Al-Turaiki I (2021) Arabic handwriting recognition system using convolutional neural network. Neural Comput Appl 33(7):2249–2261
Alyahya H, Ismail MMB, Al-Salman A (2020) Accents. Trans Image Process Comput Vis 6(21):68
An S, Lee M, Park S, Yang H, So J (2020) An ensemble of simple convolutional neural network models for MNIST Digit Recognition. arXiv preprint arXiv:2008.10400
Ayush Kumar Agrawal VK (2021) Novel deep neural network model for handwritten digit classification and recognition. Int J Adv Res Sci Commun Technol (IJARSCT) 2(2):30–35
Beskopylny A, Lyapin A, Beskopylny N, Kadomtseva E (2020) Comparison of the efficiency of neural network algorithms in recognition and classification problems. In: E3S Web of Conferences, vol 224. EDP Sciences, p 01025
Chen F, Chen N, Mao H, Hu H (2018) Assessing four neural networks on a handwritten digit recognition dataset (MNIST). arXiv preprint arXiv:1811.08278
Choudhary SA (2020) Hybrid CNN-SVM classifier for handwritten digit recognition. International Conference on Computational Intelligence and Data Science (ICCIDS 2019), pp 2554–2560
Chowdhury RR, Hossain MS, ul Islam R, Andersson K, Hossain S (2019) Bangla handwritten character recognition using a convolutional neural network with data augmentation. In: (icIVPR). IEEE, pp 318–323
Diaz GI, Fokoue-Nkoutche A, Nannicini G, Samulowitz H (2017) An effective algorithm for hyperparameter optimization of neural networks. IBM J Res Dev 61(4/5):9–1
Fathma Siddique SS (2019) Recognition of handwritten digit using convolutional neural network in Python with Tensorflow and comparison of performance for various hidden layers. Preprints. https://doi.org/10.20944/preprints201903
Garg A, Gupta D, Saxena S, Sahadev PP (2019) Validation of random dataset using an efficient CNN model trained on MNIST handwritten dataset. In: 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN). IEEE, pp 602–606
Hamel L (2009) Model assessment with ROC curves. In: Encyclopedia of Data Warehousing and Mining, Second Edition (pp 1316-1323). IGI Global
Hossain A (2019) Recognition of handwritten digit using convolutional neural network (CNN). Global J Comput Sci Technol: D Neural Artif Intell. https://doi.org/10.17406/GJCST
James A, Manjusha J, Saravanan C (2018) Malayalam handwritten character recognition using AlexNet based architecture. Indones J Electr Eng Inf (IJEEI) 6(4):393–400
Jangid M, Srivastava S (2018) Handwritten devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J Imaging 4(2):41
Jerome Fan SU (2006) Understanding receiver operating characteristic. Can J Emerg Med 8(1):19–20
Katarzyna Janocha WM (2017) On loss functions for deep neural networks in classification. arXiv:1702.05659.
Ketkar N. Stochastic Gradient Descent. Deep Learning with Python. Apress, Berkeley, pp 113–132. https://doi.org/10.1007/978-1-4842-2766-4_8
Kumar A, Mohan A, George DS (2020) Performance evaluation of a convolutional neural network for handwritten digit recognition. In: 2020 International Conference on Power, Instrumentation, Control, and Computing (PICC). IEEE, pp 1–5
Lee SG, Sung Y, Kim YG, Cha EY (2018) Variations of AlexNet and GoogLeNet to improve korean character recognition performance. J Inform Process Syst 14(1):205–217
Munsarif M, Noersasongko E, Andono PN, Soeleman A and Sam’an M. An improved convolutional neural networks based on variation types of optimizers for handwritten digit recognition. Available at SSRN 4055758
Niu XX, Suen CY (2012) A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recogn 45(4):1318–1325
Postalcıoğlu S (2020) Performance analysis of different optimizers for deep learning-based image recognition. Int J Pattern recognit Artif Intell 34(02):2051003
Prachi Sharma RS (2021) A comprehensive evaluation of deep models and optimizers for indian sign language recognition. Graph Vis Comput. https://doi.org/10.1016/j.gvc.2021.200032
Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv:1609.04747v2
Shima Y, Nakashima Y, Yasuda M (2018) In: Proceedings of the 3rd international conference on multimedia systems and signal processing, pp 36–40
Soham De AM (2018) Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration. arXiv:1807.06766v3.
Tabik S, Peralta D, Herrera-Poyatos A, Herrera Triguero F (2017) A snapshot of image pre-processing for convolutional neural networks: case study of MNIST
Trivedi A, Srivastava S, Mishra A, Shukla A, Tiwari R (2018) A hybrid evolutionary approach for devanagari handwritten numeral recognition using convolutional neural network. Procedia Comput Sci 125:525–532
Vani STM (2019) An experimental approach towards the performance assessment of various optimizers on convolutional neural network. 3rd International Conference on Trends in Electronics and Informatics (ICOEI). IEEE, Tirunelveli, pp 331–336. https://doi.org/10.1109/ICOEI.2019.8862686
Yanli Liu YG (2020) An improved analysis of Stochastic Gradient Descent. arXiv Database
Zhan H, Lyu S, Lu Y (2018) Handwritten digit string recognition using convolutional neural network. In: 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, pp 3729–3734
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
No animals were involved in this study. All applicable international, national, and/or institutional guidelines for the care and use of animals were followed.
Conflict of interest
The authors declare that they do not have any conflict of interests that influence the work reported in this paper.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Swain, D., Parmar, B., Shah, H. et al. Enhanced handwritten digit recognition using optimally selected optimizer for an ANN. Multimed Tools Appl 82, 44021–44036 (2023). https://doi.org/10.1007/s11042-023-15402-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15402-0