Image Text Deblurring Method Based on Generative Adversarial Network
In the automatic sorting process of express delivery, a three-segment code is used to represent a specific area assigned by a specific delivery person. In the process of obtaining the courier order information, the camera is affected by factors such as light, noise, and subject shake, which will cau...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/9/2/220 |
id |
doaj-a73eeaeb94f04942b94af478e2cb3b2b |
---|---|
record_format |
Article |
spelling |
doaj-a73eeaeb94f04942b94af478e2cb3b2b2020-11-25T02:21:14ZengMDPI AGElectronics2079-92922020-01-019222010.3390/electronics9020220electronics9020220Image Text Deblurring Method Based on Generative Adversarial NetworkChunxue Wu0Haiyan Du1Qunhui Wu2Sheng Zhang3School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaShanghai HEST Co. Ltd. Shanghai 201610, ChinaSchool of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaIn the automatic sorting process of express delivery, a three-segment code is used to represent a specific area assigned by a specific delivery person. In the process of obtaining the courier order information, the camera is affected by factors such as light, noise, and subject shake, which will cause the information on the courier order to be blurred, and some information will be lost. Therefore, this paper proposes an image text deblurring method based on a generative adversarial network. The model of the algorithm consists of two generative adversarial networks, combined with Wasserstein distance, using a combination of adversarial loss and perceptual loss on unpaired datasets to train the network model to restore the captured blurred images into clear and natural image. Compared with the traditional method, the advantage of this method is that the loss function between the input and output images can be calculated indirectly through the positive and negative generative adversarial networks. The Wasserstein distance can achieve a more stable training process and a more realistic generation effect. The constraints of adversarial loss and perceptual loss make the model capable of training on unpaired datasets. The experimental results on the GOPRO test dataset and the self-built unpaired dataset showed that the two indicators, peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), increased by 13.3% and 3%, respectively. The human perception test results demonstrated that the algorithm proposed in this paper was better than the traditional blur algorithm as the deblurring effect was better.https://www.mdpi.com/2079-9292/9/2/220image deblurringgenerative adversarial networkwasserstein distanceadversarial lossperceptual loss |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Chunxue Wu Haiyan Du Qunhui Wu Sheng Zhang |
spellingShingle |
Chunxue Wu Haiyan Du Qunhui Wu Sheng Zhang Image Text Deblurring Method Based on Generative Adversarial Network Electronics image deblurring generative adversarial network wasserstein distance adversarial loss perceptual loss |
author_facet |
Chunxue Wu Haiyan Du Qunhui Wu Sheng Zhang |
author_sort |
Chunxue Wu |
title |
Image Text Deblurring Method Based on Generative Adversarial Network |
title_short |
Image Text Deblurring Method Based on Generative Adversarial Network |
title_full |
Image Text Deblurring Method Based on Generative Adversarial Network |
title_fullStr |
Image Text Deblurring Method Based on Generative Adversarial Network |
title_full_unstemmed |
Image Text Deblurring Method Based on Generative Adversarial Network |
title_sort |
image text deblurring method based on generative adversarial network |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2020-01-01 |
description |
In the automatic sorting process of express delivery, a three-segment code is used to represent a specific area assigned by a specific delivery person. In the process of obtaining the courier order information, the camera is affected by factors such as light, noise, and subject shake, which will cause the information on the courier order to be blurred, and some information will be lost. Therefore, this paper proposes an image text deblurring method based on a generative adversarial network. The model of the algorithm consists of two generative adversarial networks, combined with Wasserstein distance, using a combination of adversarial loss and perceptual loss on unpaired datasets to train the network model to restore the captured blurred images into clear and natural image. Compared with the traditional method, the advantage of this method is that the loss function between the input and output images can be calculated indirectly through the positive and negative generative adversarial networks. The Wasserstein distance can achieve a more stable training process and a more realistic generation effect. The constraints of adversarial loss and perceptual loss make the model capable of training on unpaired datasets. The experimental results on the GOPRO test dataset and the self-built unpaired dataset showed that the two indicators, peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), increased by 13.3% and 3%, respectively. The human perception test results demonstrated that the algorithm proposed in this paper was better than the traditional blur algorithm as the deblurring effect was better. |
topic |
image deblurring generative adversarial network wasserstein distance adversarial loss perceptual loss |
url |
https://www.mdpi.com/2079-9292/9/2/220 |
work_keys_str_mv |
AT chunxuewu imagetextdeblurringmethodbasedongenerativeadversarialnetwork AT haiyandu imagetextdeblurringmethodbasedongenerativeadversarialnetwork AT qunhuiwu imagetextdeblurringmethodbasedongenerativeadversarialnetwork AT shengzhang imagetextdeblurringmethodbasedongenerativeadversarialnetwork |
_version_ |
1724867526140100608 |