Handwritten Digits Recognition using Deep Convolutional Neural Network: An Experimental Study using EBlearn

TL;DR

This paper presents an experimental study of a deep convolutional neural network built with EBLearn to classify handwritten digits from the MNIST dataset, demonstrating its effectiveness in digit recognition.

Contribution

It explores the application of a deep CNN architecture using EBLearn for handwritten digit classification, providing new insights into its performance.

Findings

High accuracy in classifying MNIST digits

Effective use of EBLearn for deep learning tasks

Potential for improved digit recognition systems

Abstract

In this paper, results of an experimental study of a deep convolution neural network architecture which can classify different handwritten digits using EBLearn library are reported. The purpose of this neural network is to classify input images into 10 different classes or digits (0-9) and to explore new findings. The input dataset used consists of digits images of size 32X32 in grayscale (MNIST dataset).