Digitally refocusing an unfocused image

• Main Author: Yang, RuiZhi
• Other Authors: Cuong Dang
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering
• Online Access: https://hdl.handle.net/10356/177118
• Institution: Nanyang Technological University

Due to advancement in technology over the year, images gradually gain importance in our daily lives. Satellite imagery is of extra importance due to contributions across various domains, including environmental monitoring, disaster management, urban planning, and agriculture. However, when satellite images are out-of-focus, this situation will hinder the extraction of fine details necessary for accurate analysis and decision making. In this project, a comprehensive review is conducted on existing deblurring algorithms and methodologies, especially on deep learning-based techniques. The project focuses on the implementation and evaluation of selected deblurring models using real-world satellite imagery datasets. These models are tested to assess their effectiveness in restoring spatial details and improving image quality. Different models will be evaluated through metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) to quantify the performance of the deblurring methods.