A Compact Convolutional Neural Network for Surface Defect Inspection

doi:10.3390/s20071974

	A Compact Convolutional Neural Network for Surface Defect Inspection
	Huang, Yibin1,3 ; Qiu, Congying 2; Wang, Xiaonan1 ; Wang, Shijun1 ; Yuan, Kui1
发表期刊	SENSORS
	2020-04-01
卷号	20 期号:7 页码:19
通讯作者	Wang, Xiaonan(wangxiaonan2012@ia.ac.cn)
摘要	The advent of convolutional neural networks (CNNs) has accelerated the progress of computer vision from many aspects. However, the majority of the existing CNNs heavily rely on expensive GPUs (graphics processing units). to support large computations. Therefore, CNNs have not been widely used to inspect surface defects in the manufacturing field yet. In this paper, we develop a compact CNN-based model that not only achieves high performance on tiny defect inspection but can be run on low-frequency CPUs (central processing units). Our model consists of a light-weight (LW) bottleneck and a decoder. By a pyramid of lightweight kernels, the LW bottleneck provides rich features with less computational cost. The decoder is also built in a lightweight way, which consists of an atrous spatial pyramid pooling (ASPP) and depthwise separable convolution layers. These lightweight designs reduce the redundant weights and computation greatly. We train our models on groups of surface datasets. The model can successfully classify/segment surface defects with an Intel i3-4010U CPU within 30 ms. Our model obtains similar accuracy with MobileNetV2 while only has less than its 1/3 FLOPs (floating-point operations per second) and 1/8 weights. Our experiments indicate CNNs can be compact and hardware-friendly for future applications in the automated surface inspection (ASI).
关键词	surface defect inspection convolutional neural network machine vision
DOI	10.3390/s20071974
关键词[WOS]	FEATURE-EXTRACTION
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018YFB1306500] ; National Natural Science Foundation of China[61421004]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation of China
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000537110500170
出版者	MDPI
引用统计	被引频次：36[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39641
专题	智能制造技术与系统研究中心_智能机器人
通讯作者	Wang, Xiaonan
作者单位	1.Univ Chinese Acad Sci, Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Columbia Univ, Civil Engn & Engn Mech Dept, New York, NY 10024 USA 3.95 Zhongguancun East Rd, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Huang, Yibin,Qiu, Congying,Wang, Xiaonan,et al. A Compact Convolutional Neural Network for Surface Defect Inspection[J]. SENSORS,2020,20(7):19.
APA	Huang, Yibin,Qiu, Congying,Wang, Xiaonan,Wang, Shijun,&Yuan, Kui.(2020).A Compact Convolutional Neural Network for Surface Defect Inspection.SENSORS,20(7),19.
MLA	Huang, Yibin,et al."A Compact Convolutional Neural Network for Surface Defect Inspection".SENSORS 20.7(2020):19.