|
二维码（扫一下试试看！） |
| Study on Surface Defects of Paper Based on YOLOv7 |
| Received:April 28, 2023 |
| DOI：10.11980/j.issn.0254-508X.2023.11.021 |
| Key Words:machine vision paper surface defects paper defects YOLOv7 attention mechanism |
| Fund Project:四川省科技计划重点研发项目（2021YFG0055）；企业信息化与物联网测控技术四川省高校重点实验室（2022WZJ01）；四川省自贡市科技局重点科技计划项目（2019YYJC15）；四川轻化工大学科研基金项目（2020RC32）。 |
| Author Name | Affiliation | Postcode | | CHEN Yumei* | School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan Province, 643002 | 643002 | | LI Zhaofei | School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan Province, 643002
Artificial Intelligence Key Lab of Sichuan Province, Yibin, Sichuan Province, 644002
Sichuan University Key Lab of Enterprise Informatization and Internet of Things Measurement and Control Technology, Yibin, Sichuan Province, 643002 | 643002 | | HOU Jin | School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan Province, 643002
Artificial Intelligence Key Lab of Sichuan Province, Yibin, Sichuan Province, 644002 | 644002 | | ZHAO Jun | School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan Province, 643002
Artificial Intelligence Key Lab of Sichuan Province, Yibin, Sichuan Province, 644002 | 644002 |
|
| Hits: 1016 |
| Download times: 996 |
| Abstract:A one-step paper surface defect detection algorithm with improved YOLOv7 was proposed in this study. The attention mechanism module CBAM was integrated into the backbone and feature extraction network structure to extract information from 2 dimensions including space and channel， to improve the feature extraction accuracy and algorithm stability of small target paper disease. ASPP was added to the backbone network SPP， and could further expand the receptive field， so that the feature information of the smaller target was preserved in the network transmission， which solved the small target information insufficient problem， to improve the performance of paper disease recognition for small targets. Through the homemade paper disease dataset detection experiments， compared with YOLOv7， the precision rate， recall rate and average precision rate mean mAP 0.5 of improved YOLOv7 were improved by 1.5， 2.3 and 2.1 percentage points， respectively. |
| View Full Text HTML View/Add Comment Download reader |
|
|
|