Modification of existing genetic algorithm optimization image restoration method through convolutional neural networks

• Main Author: Tan, Jun Meng
• Other Authors: Li Fang
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• Online Access: https://hdl.handle.net/10356/148377
• Institution: Nanyang Technological University

In recent years, image restoration has been gaining increasing attention due to the widespread usage of image-based information such as in complex classification models used throughout multiple industries. Due to image restoration algorithms, the abundance of data has not only increased but slightly damaged images are no longer a source of concern to use as data. Furthermore, image restoration has various other uses such as for medical imaging, astronomical imaging to forensic science and even recreational uses. Genetic algorithm (GA) is widely applicable to multiple industries due to its optimization abilities. Despite it being an emerging domain, GA has been applied to image restoration projects as well. Specifically, through the use of genetic algorithm optimization, images are able to be restored with structure-priority. In the existing method, structural information is extracted using canny edge detection. However, this project seeks to optimize the structural information obtain through the use of convolutional neural networks instead.