Publication Date: 2023/12/19
Abstract: Due to the variations in human handwriting, computerized handwritten digit recognition is a challenging task. This abstract describes a system that identifies handwritten digits in images and documents using Convolutional Neural Networks built with PyTorch. In order to solve a variety of practical problems, this technology is crucial in applications like check processing, postal sorting, and number plate recognition. The abstract compares different machine learning and deep learning algorithms, such as Support Vector Machine, Multilayer Perceptron, and Convolutional Neural Network, based on their performance, accuracy, and training times. The results are presented visually for easy comprehension through Matplotlib-generated plots and charts, providing insightful information into the state of handwritten digit recognition and opening the door for improvements in this crucial area of artistic endeavor.
Keywords: Deep Learning, Convolutional Neural Network(CNN), Support Vector Machine(SVM),MINIST Dataset.
DOI: https://doi.org/10.5281/zenodo.10405523
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23DEC250.pdf
REFERENCES