Data augmentation using rotation and shifting

• Main Author: Muhammad Haziq Bin Mornin
• Other Authors: Wang Lipo
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering; Deep learning; Data augmentation
• Online Access: https://hdl.handle.net/10356/176102
• Institution: Nanyang Technological University

In recent times, the usage of Deep Learning has been on the rise in the medical industry. It helps automate many different aspects of the Medical Field and there is still room for improvement in the different aspects. For this project, it will focus on the use of deep learning for image classification of chest X-ray (CXR) scans of the human body for diseases. The usage of Augmentation in supervised learning has been shown to improve the efficiency of the deep learning model. This project will focus on the effectiveness of using Augmentation methods, Shifting, and Rotation, to train a Convolution Neural Network (CNN) model to help improve Image Classification in the medical industry [1]. Since this project is a follow-up of a previous study, it would follow the main sequence of testing to obtain results.