A Compact Convolutional Neural Network for Surface Defect Inspection

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 ins...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2020-04, Vol.20 (7), p.1974
Main Authors: Huang, Yibin, Qiu, Congying, Wang, Xiaonan, Wang, Shijun, Yuan, Kui
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Central processing units
Classification
Computer vision
Convolution
convolutional neural network
CPUs
Datasets
Deep learning
Defective products
Defects
Embedded systems
Field programmable gate arrays
Floating point arithmetic
Graphics processing units
Inspection
Lightweight
machine vision
Manufacturing
Model accuracy
Neural networks
surface defect inspection
Weight reduction
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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).
ISSN:1424-8220
1424-8220
DOI:10.3390/s20071974