An Image Deblurring Algorithm Based on Improved Generative Adversarial Network

Abstract

Motion blur is one of the most common factors degrading image quality It is commonly found from photos taken by hand-held cameras or low-frame-rate videos containing moving objects Many computer vision algorithms such as semantic segmentation object detection rely on visual inputs blurry images affect the performance of these algorithms In this Thesis an image deblurring algorithm based on generative adversarial network is proposed It contains a generator and a discriminator The generator is based on an encoder-decoder architecture which synthesizes the output image that tends to be real and the discriminator distinguishes whether the real image is relatively more realistic than the output image In addition the hybrid loss function enables the network to output high-quality images The experimental results show that the proposed approach has better performance than other methods on subjective visual quality which can obtain sharper edges and more detail textures and also the objective measurement

Date of Award	2020
Original language	English
Supervisor	Shen-Chuan Tai (Supervisor)