A Novel Approach for Hand-written Digit Classification Using Deep Learning

Abstract

Humans' control over technology is at an all-time high, with applications ranging from visual object recognition to the dubbing of dialogue into silent films. Using algorithms for deep learning and machine learning. Similarly, the most crucial technologies are text line recognition fields of study and development, with an increasing number of potential outcomes. Handwriting recognition (HWR), also identified as Handwriting Text Acknowledgment, is the capacity of a computer to understand legibly handwritten input from bases such as paper documents, screens, and other devices. Evidently, we have performed handwritten digit recognition using MNIST datasets and SVM, Multi-Layer Perceptron (MLP), and CNN models in this research. Our primary purpose is to compare the accuracy and execution times of the aforementioned models to determine the optimal model for digit recognition.