[{“box”:0,”content”:”
n
n
- n t
n
Radhey Shyam, Shilpi Khanna, Priyanka Verma, Sakshi Maurya
[/foreach]
n
n
n
- [foreach 286] [if 1175 not_equal=””]n t
- Professor & Head, Student, Student, Student, Department of Information Technology, Shri Ramswaroop Memorial College of Engineering and Management, Lucknow, Department of Information Technology, Shri Ramswaroop Memorial College of Engineering and Management, Lucknow, Department of Information Technology, Shri Ramswaroop Memorial College of Engineering and Management, Lucknow, Department of Information Technology, Shri Ramswaroop Memorial College of Engineering and Management, Lucknow, Uttar Pradesh, Uttar Pradesh, Uttar Pradesh, Uttar Pradesh, India, India, India, India
n[/if 1175][/foreach]
n
Abstract
nHandwritten digit recognition is a computer vision task that involves the automatic identification and classification of hand-written digits. The objective is to develop models capable of accurately recognizing and distinguishing digits handwritten by humans. With the development of machine learning and deep learning techniques, this field has advanced remarkably. The convolutional neural network (CNN) is the most often used technique for this purpose. By utilizing CNN, the model can learn to identify unique features of each digit, such as shape, thickness, and curvature patterns, enabling it to effectively classify and differentiate handwritten digits with high precision. Additionally, other machine learning techniques like artificial neural networks (ANN) and recurrent neural networks (RNN) can also be utilized. Handwritten digit recognition has practical uses in postal services, vehicle number plate detection, and extracting numbers from bank cheques. In this particular study, we focus on the detection and classification of handwritten digits by employing various techniques and models. Specifically, we compare the performance of ANN, CNN, and RNN models and found the accuracies to be 97.73, 96.61 and 96.13% respectively based on the evaluation. These evaluations are performed under the most popular dataset i.e., modified national institute of standards technology (MNIST) dataset. The collection consists of about 70,000 photos in grayscale that show handwritten digits from 0 to 9. The study’s outcomes have significant implications for practical applications across different domains.
n
Keywords: Digit recognition, CNN, ANN, RNN, MNIST
n[if 424 equals=”Regular Issue”][This article belongs to International Journal of Data Structure Studies(ijdss)]
n
n
n
n
n
nn
nn
Full Text
n[if 992 equals=”Open Access”] [else] nvar fieldValue = “[user_role]”;nif (fieldValue == ‘indexingbodies’) {n document.write(”);n }nelse if (fieldValue == ‘administrator’) { document.write(”); }nelse if (fieldValue == ‘ijdss’) { document.write(”); }n else { document.write(‘ ‘); }n [/if 992] [if 379 not_equal=””]n
Browse Figures
n
n[/if 379]n
References
n[if 1104 equals=””]n
1. Goodfellow I, Bengio Y, Courville A. Deep learning. Massachusetts: MIT press; 2016 Nov 10.
2. Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Technical report, University of Toronto; 2009.
3. Shyam R, Singh R. A taxonomy of machine learning techniques. J Adv Robot. 2021; 8(3): 18–25.
4. LeCun Y, Cortes C, Burges CJ. MNIST handwritten digit database. 2010. URL http://yann. lecun. com/exdb/mnist. 2010; 7(23): 6.
5. Aggarwal CC. Neural networks and deep learning. Cham: Springer; 2018 Sep; 10(978): 3.
6. Wan L, Zeiler M, Zhang S, Cun YL, Fergus R. Regularization of neural networks using dropconnect. In Proceedings of Proceedings of the International Conference on Machine Learning. 2013; 1058–1066.
7. Shyam R, Chakraborty R. Machine learning and its dominant paradigms. J Adv Robot. 2021; 8(2): 1–10.
8. Zhang X, Zhou Y, Lin M, Sun J. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Pattern Recognition. 2015; 684–691.
9. Simran, Tandon S, Khanna S, Shyam R. Detection of traffic sign using CNN. Recent Trends Parallel Comput. 2022; 9(1): 14–23.
10. Pandey A, Shyam R. Analysis of road lane detection using computer vision. International Journal of Software Computing and Testing (IJSCT). 2023; 9(1): 7–14.
11. Simard PY, Steinkraus D, Platt JC. Best practices for convolutional neural networks applied to visual document analysis. In Proceedings of International Conference on Document Analysis and Recognition. 2003; 958–962.
12. Enhanced object detection with deep convolutional neural networks. Int J All Res Educ Sci Methods. 2021; 9(1): 4093–4102.
13. Verma S, Jaiswal V, Shyam R. Intensifying security with smart video surveillance. Recent Trends Program Lang. 2022; 9(1): 24–30.
14. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997; 9(8): 1735–1780.
15. Ciresan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2012; 3642–3649.
16. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998; 86(11): 2278–2324.
17. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV]. 2015.
18. 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 (CVPR). 2016 Jun; 770–778.
19. Graves A, Mohamed AR, Hinton G. Speech recognition with deep recurrent neural networks. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013; 6645–6649.
20. Shyam R. Convolutional neural network and its architectures. J Comput Technol Appl. 2021; 12(2): 6–14.
21. Brownlee J. (2019 May 8). How to Develop a CNN for MNIST Handwritten Digit Classification. [Online]. Machine Learning Mastery. Available from: https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-from-scratch-for-mnist-handwritten-digit-classification/
22. Ahlawat S, Choudhary A, Nayyar A, Singh S, Yoon B. Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors. 2020; 20(12): 3344.
23. Pham V, Bluche T, Kermorvant C, Louradour J. Dropout improves recurrent neural networks for handwriting recognition. 2014 14th International Conference on Frontiers in Handwriting Recognition, Hersonissos, Greece. 2014; 285–290.
24. Jarrett K, Kavukcuoglu K, Ranzato MA, Yann LeCun. What is the best multi-stage architecture for object recognition? In 2009 IEEE 12th International Conference on Computer Vision. 2009; 2146–2153.
25. Multiobjective optimization for recognition of isolated handwritten indic scripts. Pattern Recognit Lett. 2019; 128: 318–325.
26. Nguyen CT, Khuong VTM, Nguyen HT, Nakagawa M. CNN based spatial classification features for clustering offline handwritten mathematical expressions. Pattern Recognit Lett. 2020; 131: 113–120.
27. Hua C, Jie B. A new hyperparameters optimization method for convolutional neural networks. Pattern Recognit Lett. 2019; 125: 828–834.
28. William TW, Baris B, Efstratios PN. Hy-pop: Hyperparameter optimization of machine learning models through parametric programming. Comput Chem Eng. 2020; 139: 106902.
29. Jian S, Kaiming H, Shaoqing R, Xiangyu Z. Deep residual learning for image recognition. InIEEE Conference on Computer Vision & Pattern Recognition 2016 (pp. 770-778).
30. Christian S, Wei L, Yangqing J, Pierre S, Scott R, Dragomir A, Dumitru E, Vincent V, Andrew R. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA. 2015; 1–9.
31. Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, NIPS. 2012.
nn[/if 1104][if 1104 not_equal=””]n
- [foreach 1102]n t
- [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]
n[/foreach]
n[/if 1104]
nn
nn[if 1114 equals=”Yes”]n
n[/if 1114]
n
n
n
n
n
| Volume | 01 |
| Issue | 01 |
| Received | July 19, 2023 |
| Accepted | July 28, 2023 |
| Published | August 14, 2023 |
n
n
n
n
n[/foreach]
n[/if 1190] [if 1177 not_equal=””]n
n
n[/foreach]
n[/if 1177]
n
n
n
n function myFunction2() {n var x = document.getElementById(“browsefigure”);n if (x.style.display === “block”) {n x.style.display = “none”;n }n else { x.style.display = “Block”; }n }n document.querySelector(“.prevBtn”).addEventListener(“click”, () => {n changeSlides(-1);n });n document.querySelector(“.nextBtn”).addEventListener(“click”, () => {n changeSlides(1);n });n var slideIndex = 1;n showSlides(slideIndex);n function changeSlides(n) {n showSlides((slideIndex += n));n }n function currentSlide(n) {n showSlides((slideIndex = n));n }n function showSlides(n) {n var i;n var slides = document.getElementsByClassName(“Slide”);n var dots = document.getElementsByClassName(“Navdot”);n if (n > slides.length) { slideIndex = 1; }n if (n (item.style.display = “none”));n Array.from(dots).forEach(n item => (item.className = item.className.replace(” selected”, “”))n );n slides[slideIndex – 1].style.display = “block”;n dots[slideIndex – 1].className += ” selected”;n }n n function myfun() {n x = document.getElementById(“editor”);n y = document.getElementById(“down”);n z = document.getElementById(“up”);n if (x.style.display == “none”) {n x.style.display = “block”;n }n else {n x.style.display = “none”;n }n if (y.style.display == “none”) {n y.style.display = “block”;n }n else {n y.style.display = “none”;n }n if (z.style.display == “none”) {n z.style.display = “block”;n }n else {n z.style.display = “none”;n }n }n function myfun2() {n x = document.getElementById(“reviewer”);n y = document.getElementById(“down2”);n z = document.getElementById(“up2”);n if (x.style.display == “none”) {n x.style.display = “block”;n }n else {n x.style.display = “none”;n }n if (y.style.display == “none”) {n y.style.display = “block”;n }n else {n y.style.display = “none”;n }n if (z.style.display == “none”) {n z.style.display = “block”;n }n else {n z.style.display = “none”;n }n }n”}]