Presenter: Prof Dr. Ahmed Khorsheed Mohammed

Host: ECE Department

Title of the Seminar: Handwritten Digit Classification Using Deep Learning

Convolutional Neural Network

Objectives or Summary: Due to the wide range of handwriting styles among individuals

and the low image quality of the handwritten text, accurate handwriting detection has been

a difficult challenge in computer vision. This is because static feature analysis of the text

images is frequently insufficient to account for these factors. The accuracy of recognizing

different handwriting patterns has recently progressively increased because of the

introduction of machine learning, particularly convolutional neural networks (CNNs). This

study uses various filter sizes to create a deep CNN model to increase the handwritten

digit recognition rate. The proposed model's multi-layer deep structure includes a fully

linked layer (also known as a dense layer) for classification and one convolution and

activation layer for feature extraction. The proposed methodology has an average

classification accuracy of up to 99.5% on the MNIST dataset.

The seminar is presented as a fellow up for a paper title "Handwritten Digit Classification

Using Deep Learning Convolutional Neural Network" published at "Journal of Soft

Computing and Data Mining" Vol. 5 No. 1 (2024) 79-90

Place of the Seminar:

Seminar Hall – 3 rd Floor – Electrical and Computer Engineering Department –

College of Engineering

Date and Time: Tuesday 12/Nov/2024 10:30AM