A Lightweight Fully Convolutional Neural Network of High Accuracy Surface Defect Detection

被引：6

作者：

Li, Yajie ^{[1
,2
,3
]}

Chen, Yiqiang ^{[1
,2
,3
]}

Gu, Yang ^{[1
,3
]}

Ouyang, Jianquan ^{[2
]}

Wang, Jiwei ^{[1
,3
]}

Zeng, Ni ^{[1
,3
]}

机构：

[1] Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China

[2] Xiangtan Univ, Xiangtan 411105, Peoples R China

[3] Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT II | 2020年 / 12397卷

关键词：

Surface defect detection; Convolutional neural network; Lightweight; VISUAL-SPATIAL ILLUSIONS; INSPECTION; SELECTION;

D O I：

10.1007/978-3-030-61616-8_2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Surface defect detection is an indispensable step in the production process. Recent researches based on deep learning have paid primarily attention to improving accuracy. However, it is difficult to apply in real situation, because of huge number of parameters and the strict hardware requirements. In this paper, a lightweight fully convolutional neural network, named LFCSDD, is proposed. The parameters of our model are llx fewer than baselines at least, and obtain the accuracy of 99.72% and 98.74% on benchmark defect datasets, DAGM 2007 and KolektorSDD, respectively, outperforming all the baselines. In addition, our model can process the images with different sizes, which is verified on the RSDDs with the accuracy of 97.00%.

引用

页码：15 / 26

页数：12

共 50 条

[41] A lightweight convolutional neural network for disease detection of fruit leaves
Hari, Pragya
Singh, Maheshwari Prasad
[J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (20): : 14855 - 14866
[42] FlameNet: a lightweight convolutional neural network for flame detection and localisation
Hu, Xing
Li, Mei
Zhang, Dawei
[J]. INTERNATIONAL JOURNAL OF VEHICLE DESIGN, 2023, 91 (1-3) : 87 - 106
[43] A lightweight convolutional neural network for disease detection of fruit leaves
Pragya Hari
Maheshwari Prasad Singh
[J]. Neural Computing and Applications, 2023, 35 : 14855 - 14866
[44] Deep Learning Implementation using Convolutional Neural Network in Mangosteen Surface Defect Detection
Azizah, Laila Ma'rifatul
Umayah, Sitti Fadillah
Riyadi, Slamet
Damarjati, Cahya
Utama, Nafi Ananda
[J]. 2017 7TH IEEE INTERNATIONAL CONFERENCE ON CONTROL SYSTEM, COMPUTING AND ENGINEERING (ICCSCE), 2017, : 242 - 246
[45] A pixel-wise framework based on convolutional neural network for surface defect detection
Dong, Guozhen
[J]. MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2022, 19 (09) : 8786 - 8803
[46] Track Surface Defect Detection Method Based on Machine Vision and Convolutional Neural Network
Yao, Zongwei
Yang, Hongfei
Hu, Jiyong
Huang, Qiuping
Wang, Zhen
Bi, Qiushi
[J]. Tiedao Xuebao/Journal of the China Railway Society, 2021, 43 (04): : 101 - 107
[47] A Defect Detection Method for Rail Surface and Fasteners Based on Deep Convolutional Neural Network
Zheng, Danyang
Li, Liming
Zheng, Shubin
Chai, Xiaodong
Zhao, Shuguang
Tong, Qianqian
Wang, Ji
Guo, Lizheng
[J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2021, 2021
[48] Copper Strip Surface Defect Detection Model Based on Deep Convolutional Neural Network
Xu, Yanghuan
Wang, Dongcheng
Duan, Bowei
Yu, Huaxin
Liu, Hongmin
[J]. APPLIED SCIENCES-BASEL, 2021, 11 (19):
[49] Solar Cell Busbars Surface Defect Detection Based on Deep Convolutional Neural Network
Balcioglu, Yavuz Selim
Sezen, Bulent
Cubukcu Cerasi, Ceren
[J]. IEEE LATIN AMERICA TRANSACTIONS, 2023, 21 (02) : 242 - 250
[50] A new multiscale texture surface defect detection method based on convolutional neural network
Li, Kaixiang
Dong, Min
Li, Dezhen
[J]. 2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 1296 - 1300

← 1 2 3 4 5 →