DEU-Net: A Multi-Scale Fusion Staged Network for Magnetic Tile Defect Detection

Author:

Huang Yifan1,Huang Zhiwen2,Jin Tao1

Affiliation:

1. School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

2. School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Abstract

Surface defect detection is a critical task in the manufacturing industry to ensure product quality and machining efficiency. Image-based precise defect detection faces significant challenges due to defects lacking fixed shapes and the detection being heavily influenced by lighting conditions. Addressing the efficiency demands of defect detection algorithms, often deployed on embedded devices, and the highly imbalanced pixel ratio between foreground and background images, this paper introduces a multi-scale fusion staged U-shaped convolutional neural network (DEU-Net). The network provides segmentation results for defect anomalies while indicating the probability of defect presence. It enables the model to train with fewer parameters, a crucial requirement for practical applications. The proposed model achieves an MIoU of 66.94 and an F1 score of 74.89 with lower Params (36.675) and Flops (19.714). Comparative analysis with FCN, U-Net, Deeplab v3+, U-Net++, Attention U-Net, and Trans U-Net demonstrates the superiority of the proposed approach in surface defect detection.

Funder

National Key R&D Program of China

Publisher

MDPI AG

Reference34 articles.

1. Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., and Shao, L. (2021). Surface defect detection methods for industrial products: A review. Appl. Sci., 11.

2. Qi, S., Yang, J., and Zhong, Z. (2020, January 26–28). A review on industrial surface defect detection based on deep learning technology. Proceedings of the International Conference on Machine Learning and Machine Intelligence (MLMI), Online.

3. Backpropagation applied to handwritten zip code recognition;Boser;Neural Comput.,2019

4. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.

5. Faster r-cnn: Towards real-time object detection with region proposal networks;Ren;Adv. Neural Inf. Process. Syst.,2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3