Handwritten Digit Image Recognition Using Machine Learning
Keywords:Machine Learning, Artificial Intelligence, Convolutional Neural Network, MNIST
Machine Learning is a type AI (also known as Artificial Intelligence) that makes the pc or computer to act like individuals and learn more as they experience additional infor-mation from their client or user. So here in this report we got basic introduction about machine learning like actually what is it, what are its use, how it works, languages for coding, value of python for machine learning, and many more things. As python is ma-jorly used for machine learning, so we discussed about its use and its libraries. Thereaf-ter, we discussed about the categories in machine learning, i.e., supervised learning, un-supervised learning, semi-supervised learning and reinforcement learning. After this discussion we got a glimpse of some basic pros and cons of machine learning in artificial intelligence. After that we discussed about basic implementation formats of the algo-rithm in machine learning. Then we discussed about some majorly used applications of machine learning which are trending nowadays and has a great demand in today’s market. At the end we came to know about the future scopes in machine learning and concluded it.
U. Pal, T. Wakabayashi, and F. Kimura, “Handwritten numeral recognition of six popular scripts,” Ninth International conference on Document Analysis and Recognition ICDAR 07, vol. 2, pp. 749–753, 2010.
J. Brownlee, “Your first deep learning project in Python with keras step-by-step,” Machine Learning Mastery, 17-Jun-2022. [Online].
V. Singh, “Digit recognition using single layer neural network with principal component analysis,” Asia-Pacific World Congress on Computer Science and Engineering, pp. 1–7, 2014.
A. K. Seewald, “Digits-a dataset for handwritten digit recognition,” Osterreichisches Forschungsinstitut f ¨ ur Artificial ¨ Intelligence TR, 2005.
R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: an overview and application in radiolo-gy,” Insights Imaging, vol. 9, no. 4, pp. 611–629, 2018.
M. Neill, Neural Network for Recognition of Handwritten Digits, Code Project. 2006.
L. Yann and B. Yoshua, “Convolutional networks for images speech and time series,” in Arbib 4 2019 6th International Confer-ence on Signal Processing and Integrated Networks (SPIN) 605 Michael A. The handbook of brain theory and neural networks, pp. 276–278, 1995.
M. S, C. N. Vanitha, N. Narayan, R. Kumar and G. R, "An Enhanced Handwritten Digit Recognition Using Convolutional Neural Network," 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), pp. 1724-1727, 2021. DOI: 10.1109/ICIRCA51532.2021.9544669
M. Jain, G. Kaur, M. P. Quamar and H. Gupta, "Handwritten Digit Recognition Using CNN," 2021 International Conference on In-novative Practices in Technology and Management (ICIPTM), pp. 211-215, 2021. DOI: 10.1109/ICIPTM52218.2021.9388351
C. Zhang, Z. Zhou and L. Lin, "Handwritten Digit Recognition Based on Convolutional Neural Network," 2020 Chinese Automa-tion Congress (CAC), 2020, pp. 7384-7388, 2020. DOI: 10.1109/CAC51589.2020.9326781
R. Sethi and I. Kaushik, "Hand Written Digit Recognition using Machine Learning," 2020 IEEE 9th International Conference on Communication Systems and Network Technologies (CSNT), pp. 49-54, 2020. DOI: 0.1109/CSNT48778.2020.9115746
K. Matsuoka, L. Wilen, S. P. Hurley, and C. F. Raymond, “Effects of birefringence within ice sheets on obliquely propagating radio waves,” IEEE Trans. Geosci. Remote Sens., vol. 47, no. 5, pp. 1429–1443, 2009.
A. Shrivastava, I. Jaggi, S. Gupta and D. Gupta, "Handwritten Digit Recognition Using Machine Learning: A Review," 2019 2nd International Conference on Power Energy, Environment and Intelligent Control (PEEIC), pp. 322-326, 2019. DOI: 10.1109/PEEIC47157.2019.8976601
L. Liu and H. Fujisawa, “Classification and learning for character recognition: comparison of methods and remaining problems,” in Proceedings of the International Workshop on Neural Networks and Learning in Document Analysis and Recognition, Seoul, Korea, 2005.
“A database for handwritten text recognition research,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 5, pp. 550–554, 1994.
K. Gaurav and P. K. Bhatia, “Analytical Review of Preprocessing Techniques for Offline Handwritten Character Recognition”,” in 2nd International Conference on Emerging Trends in Engineering & Management, ICETEM, 2014.
A. Yavariabdi and H. Kusetogullari, “DIDA: A dataset of handwritten digit images in the context of HCR.” IEEE DataPort, 2021. DOI: 10.21227/hv16-0j03
How to Cite
Copyright (c) 2022 Aditya Srivastava, Dr. Pawan Singh
This work is licensed under a Creative Commons Attribution 4.0 International License.