Next Article in Journal
Numerical Modelling of a Distributed Acoustic Sensor Based on Ultra-Low Loss-Enhanced Backscattering Fibers
Next Article in Special Issue
Smoothing Complete Feature Pyramid Networks for Roll Mark Detection of Steel Strips
Previous Article in Journal
Communication Network Architectures for Driver Assistance Systems
Previous Article in Special Issue
Fault Detection of Wind Turbine Electric Pitch System Based on IGWO-ERF
Article

Binary Neural Network for Automated Visual Surface Defect Detection

1
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
2
Center for Machine Vision and Signal Analysis, University of Oulu, 90570 Oulu, Finland
3
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, China
*
Author to whom correspondence should be addressed.
Academic Editor: Anastasios Doulamis
Sensors 2021, 21(20), 6868; https://doi.org/10.3390/s21206868
Received: 31 August 2021 / Revised: 12 October 2021 / Accepted: 14 October 2021 / Published: 16 October 2021
(This article belongs to the Special Issue Intelligent Sensing and Monitoring for Industrial Process)
As is well-known, defects precisely affect the lives and functions of the machines in which they occur, and even cause potentially catastrophic casualties. Therefore, quality assessment before mounting is an indispensable requirement for factories. Apart from the recognition accuracy, current networks suffer from excessive computing complexity, making it of great difficulty to deploy in the manufacturing process. To address these issues, this paper introduces binary networks into the area of surface defect detection for the first time, for the reason that binary networks prohibitively constrain weight and activation to +1 and −1. The proposed Bi-ShuffleNet and U-BiNet utilize binary convolution layers and activations in low bitwidth, in order to reach comparable performances while incurring much less computational cost. Extensive experiments are conducted on real-life NEU and Magnetic Tile datasets, revealing the least OPs required and little accuracy decline. When classifying the defects, Bi-ShuffleNet yields comparable results to counterpart networks, with at least 2× inference complexity reduction. Defect segmentation results indicate similar observations. Some network design rules in defect detection and binary networks are also summarized in this paper. View Full-Text
Keywords: automated defect detection; binary network; binary neural network; efficient network; automated visual inspection; surface defect detection automated defect detection; binary network; binary neural network; efficient network; automated visual inspection; surface defect detection
Show Figures

Figure 1

MDPI and ACS Style

Liu, W.; Zhang, J.; Su, Z.; Zhou, Z.; Liu, L. Binary Neural Network for Automated Visual Surface Defect Detection. Sensors 2021, 21, 6868. https://doi.org/10.3390/s21206868

AMA Style

Liu W, Zhang J, Su Z, Zhou Z, Liu L. Binary Neural Network for Automated Visual Surface Defect Detection. Sensors. 2021; 21(20):6868. https://doi.org/10.3390/s21206868

Chicago/Turabian Style

Liu, Wenzhe, Jiehua Zhang, Zhuo Su, Zhongzhu Zhou, and Li Liu. 2021. "Binary Neural Network for Automated Visual Surface Defect Detection" Sensors 21, no. 20: 6868. https://doi.org/10.3390/s21206868

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop