Super-Resolution Reconstruction of Particleboard Images Based on Improved SRGAN

被引:7
作者
Yu, Wei [1 ]
Zhou, Haiyan [1 ]
Liu, Ying [1 ]
Yang, Yutu [1 ]
Shen, Yinxi [1 ]
机构
[1] Nanjing Forestry Univ, Coll Mech & Elect Engn, Jiangsu Coinnovat Ctr Efficient Proc & Utilizat Fo, Nanjing 210037, Peoples R China
关键词
particleboard; super-resolution reconstruction; generate adversarial networks; defect;
D O I
10.3390/f14091842
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
As an important forest product, particleboard can greatly save forestry resources and promote low-carbon development by reusing wood processing residues. The size of the entire particleboard is large, and there are problems with less image feature information and blurred defect outlines when obtaining the particleboard images. The super-resolution reconstruction technology can improve the quality of the particleboard surface images, making the defects clearer. In this study, the super-resolution dense attention generative adversarial network (SRDAGAN) model was improved to solve the problem that the super-resolution generative adversarial network (SRGAN) reconstructed image would produce artifacts and its performance needed to be improved. The Batch Normalization (BN) layer was removed, the convolutional block attention module (CBAM) was optimized to construct the dense block, and the dense blocks were constructed via a densely skip connection. Then, the corresponding 52,400 image blocks with high resolution and low resolution were trained, verified, and tested according to the ratio of 3:1:1. The model was comprehensively evaluated from the effect of image reconstruction and the three indexes of PSNR, SSIM, and LPIPS. It was found that compared with BICUBIC, SRGAN, and SWINIR, the PSNR index of SRDAGAN increased by 4.88 dB, 3.25 dB, and 2.68 dB, respectively; SSIM increased by 0.0507, 0.1122, and 0.0648, respectively; and LPIPS improved by 0.1948, 0.1065, and 0.0639, respectively. The reconstructed images not only had a clearer texture, but also had a more realistic expression of various features, and the performance of the model had been greatly improved. At the same time, this study also emphatically discussed the image reconstruction effect with defects. The result showed that the SRDAGAN proposed in this study can complete the super-resolution reconstruction of the particleboard images with high quality. In the future, it can also be further combined with defect detection for the actual production to improve the quality of forestry products and increase economic benefits.
引用
收藏
页数:16
相关论文
共 38 条
[1]   αβ-GAN: Robust generative adversarial networks [J].
Aurele Tohokantche, Aurele Tohokantche ;
Cao, Wenming ;
Mao, Xudong ;
Wu, Si ;
Wong, Hau-San ;
Li, Qing .
INFORMATION SCIENCES, 2022, 593 :177-200
[2]   Development and performance of particleboard from various types of organic waste and adhesives: A review [J].
Baharuddina, M. N. M. ;
Zain, Norazwani Muhammad ;
Harunc, W. S. W. ;
Roslina, Eida Nadirah ;
Ghazali, Farizah Adliza ;
Som, Siti Norzailina Md .
INTERNATIONAL JOURNAL OF ADHESION AND ADHESIVES, 2023, 124
[3]   Semantic segmentation using reinforced fully convolutional densenet with multiscale kernel [J].
Brahimi, Sourour ;
Ben Aoun, Najib ;
Benoit, Alexandre ;
Lambert, Patrick ;
Ben Amar, Chokri .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (15) :22077-22098
[4]   Resizing and cleaning of histopathological images using generative adversarial networks [J].
Celik, Gaffari ;
Talu, Muhammed Fatih .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2020, 554
[5]   Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform [J].
Chang, Zihan ;
Zhang, Yang ;
Chen, Wenbo .
ENERGY, 2019, 187
[6]   The Impact of Post-Manufacture Treatments on the Surface Characteristics Important for Finishing of OSB and Particleboard [J].
Copak, Antonio ;
Jirous-Rajkovic, Vlatka ;
Spanic, Nikola ;
Miklecic, Josip .
FORESTS, 2021, 12 (08)
[7]   Learning a Deep Convolutional Network for Image Super-Resolution [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 :184-199
[8]   Bi-discriminator GAN for tabular data synthesis [J].
Esmaeilpour, Mohammad ;
Chaalia, Nourhene ;
Abusitta, Adel ;
Devailly, Fransois-Xavier ;
Maazoun, Wissem ;
Cardinal, Patrick .
PATTERN RECOGNITION LETTERS, 2022, 159 :204-210
[9]   Physical and Mechanical Properties of Particleboard Made from Palm Tree Prunings [J].
Ferrandez-Garcia, Clara-Eugenia ;
Ferrandez-Garcia, Antonio ;
Ferrandez-Villena, Manuel ;
Fernando Hidalgo-Cordero, Juan ;
Garcia-Ortuno, Teresa ;
Ferrandez-Garcia, Maria-Teresa .
FORESTS, 2018, 9 (12)
[10]   On the proper use of structural similarity for the robust evaluation of medical image synthesis models [J].
Gourdeau, Daniel ;
Duchesne, Simon ;
Archambault, Louis .
MEDICAL PHYSICS, 2022, 49 (04) :2462-2474