This is the authors' abstract. We don't add key points for this paper.
Handwritten digit recognition is a complex task in various real-world applications such as bank check processing, postal automation recognition etc. In recent time, different kind of learning algorithms are used to analyze and resolve this issue. This paper presents a comparative study on machine learning and deep learning algorithms such as Convolutional Neural Network (CNN), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest, LeNet-5, and YOLOv7. Publically available MNIST, DIDA, and MNIST MIX handwritten digit dataset were used in experimental work. The objective of this study is to find the best algorithm which can give an acceptable accuracy. For measuring the accuracy various parameters such as precision, recall, specificity, and F-measure were used. On the basic of experimental results, YOLOv7 has achieved detection accuracies above 98.3% and LeNet 5 has detection accuracy of 99.15%. It has been observed that deep learning algorithms have achieved higher accuracy than machine learning algorithms.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Sohail et al. (2023) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: