Next Article in Journal
Study of the Hygrothermal Behavior of Wood Fiber Insulation Subjected to Non-Isothermal Loading
Next Article in Special Issue
An Experimental Analytics on Discovering Work Transference Networks from Workflow Enactment Event Logs
Previous Article in Journal
Image Classification for Automated Image Cross-Correlation Applications in the Geosciences
Previous Article in Special Issue
Modeling the Power Consumption of Function-Level Code Relocation for Low-Power Embedded Systems
Open AccessArticle

Wasserstein Generative Adversarial Network Based De-Blurring Using Perceptual Similarity

Department of Electrical & Electronic Engineering, Yonsei University, Seoul 03722, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(11), 2358; https://doi.org/10.3390/app9112358
Received: 31 May 2019 / Revised: 31 May 2019 / Accepted: 4 June 2019 / Published: 8 June 2019
(This article belongs to the Special Issue Applied Sciences Based on and Related to Computer and Control)
The de-blurring of blurred images is one of the most important image processing methods and it can be used for the preprocessing step in many multimedia and computer vision applications. Recently, de-blurring methods have been performed by neural network methods, such as the generative adversarial network (GAN), which is a powerful generative network. Among many different types of GAN, the proposed method is performed using the Wasserstein generative adversarial network with gradient penalty (WGANGP). Since edge information is the most important factor in an image, the style loss function is applied to represent the perceptual information of the edge in order to preserve small edge information and capture its perceptual similarity. As a result, the proposed method improves the similarity between sharp and blurred images by minimizing the Wasserstein distance, and it captures well the perceptual similarity using the style loss function, considering the correlation of features in the convolutional neural network (CNN). To confirm the performance of the proposed method, three experiments are conducted using two datasets: the GOPRO Large and Kohler dataset. The optimal solutions are found by changing the parameter values experimentally. Consequently, the experiments depict that the proposed method achieves 0.98 higher performance in structural similarity (SSIM) and outperforms other de-blurring methods in the case of both datasets. View Full-Text
Keywords: deblurring; generative adversarial network; perceptual similarity; style information; Wasserstein distance deblurring; generative adversarial network; perceptual similarity; style information; Wasserstein distance
Show Figures

Figure 1

MDPI and ACS Style

Hong, M.; Choe, Y. Wasserstein Generative Adversarial Network Based De-Blurring Using Perceptual Similarity. Appl. Sci. 2019, 9, 2358.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop