Project Abstract

In today’s visually oriented world, there is a crucial need for an efficient image classification system. To solve this problem, our project will help, and this is our primary motivation. This project aims to create a flexible framework that can handle the complexity of real-world image datasets by utilising state-of-the-art deep learning algorithms. Our objective is to develop a reliable system that can accurately classify pictures across a range of domains, with the help of various techniques such as Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs), and Convolutional Neural Networks (CNNs). Our main research question is investigating the effectiveness of these deep learning algorithms in real-life scenarios. Our research includes preprocessing datasets, implementing algorithms, evaluating algorithm performance, and concluding our findings. The expected outcomes of this project include superior classification performance across multiple domains and application scenarios, offering insights into the effectiveness of different deep learning architectures and techniques for image classification tasks. Our study will significantly advance the field of visual intelligence by presenting a flexible and adaptable image classification framework that can be used to develop transformative applications in various industries.

Keywords: Intelligence Analysis, Deep Learning, Image Classification

 Conference Details

Session: Presentation Stream 5 at Presentation Slot 3

Location: GH011 at Tuesday 7th 13:30 – 17:00

Markers: Nader Al Khatib (GTA), Tom Owen

Course: MSc Data Science, Masters PG

Future Plans: I’m looking for work