AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs

Abstract Defect detection in cigarette packaging is a crucial process for ensuring product quality meets industry standards within the tobacco manufacturing sector. Defect detection methods based on deep learning have significantly enhanced efficiency. However, challenges remain in addressing issues...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng Dong, Yongsheng Wang, Qianyuan Yu, Weihua Feng, Guohao Zong
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Image Processing
Subjects:
Online Access:https://doi.org/10.1049/ipr2.13272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121445127618560
author Peng Dong
Yongsheng Wang
Qianyuan Yu
Weihua Feng
Guohao Zong
author_facet Peng Dong
Yongsheng Wang
Qianyuan Yu
Weihua Feng
Guohao Zong
author_sort Peng Dong
collection DOAJ
description Abstract Defect detection in cigarette packaging is a crucial process for ensuring product quality meets industry standards within the tobacco manufacturing sector. Defect detection methods based on deep learning have significantly enhanced efficiency. However, challenges remain in addressing issues such as blurred boundary textures of cigarette pack defects and the complex differentiability and similarity among defects. Consequently, this study presents the design of a defect detector for cigarette packs that is sensitive to detail features, named AMC‐YOLO. Initially, an Adaptive Spatial Weight Perception (ASWP) module is designed to emphasize local information from different regions during the downsampling process and integrate effective features. Additionally, a Multidimensional Aggregation Radiative Feature Pyramid Networks (MARFPN) is proposed to aggregate multi‐scale semantic information across dimensions and relay it back to various levels within the network to facilitate the learning of more refined feature. Lastly, a Cross‐Layer Collaborative Detection Head (CLCDH) is introduced to further weight and fuse the contextual information between local and global aspects. Experimental results demonstrate that AMC‐YOLO outperforms state‐of‐the‐art methods on the Cigarette Pack Defect and GC10‐DET datasets, exhibiting the highest detection precision and excellent generalization. These findings highlight the significant potential for the application of AMC‐YOLO in cigarette pack defect detection.
format Article
id doaj-art-758c0a1caf5c43b9b9be56a1639da479
institution Kabale University
issn 1751-9659
1751-9667
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Image Processing
spelling doaj-art-758c0a1caf5c43b9b9be56a1639da4792024-12-16T04:00:31ZengWileyIET Image Processing1751-96591751-96672024-12-0118144873488610.1049/ipr2.13272AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packsPeng Dong0Yongsheng Wang1Qianyuan Yu2Weihua Feng3Guohao Zong4Henan Institute of Advanced Technology Zhengzhou University Zhengzhou ChinaZhengzhou Tobacco Research of CNTC China National Tobacco Corporation Zhengzhou ChinaZhengzhou Tobacco Research of CNTC China National Tobacco Corporation Zhengzhou ChinaZhengzhou Tobacco Research of CNTC China National Tobacco Corporation Zhengzhou ChinaZhengzhou Tobacco Research of CNTC China National Tobacco Corporation Zhengzhou ChinaAbstract Defect detection in cigarette packaging is a crucial process for ensuring product quality meets industry standards within the tobacco manufacturing sector. Defect detection methods based on deep learning have significantly enhanced efficiency. However, challenges remain in addressing issues such as blurred boundary textures of cigarette pack defects and the complex differentiability and similarity among defects. Consequently, this study presents the design of a defect detector for cigarette packs that is sensitive to detail features, named AMC‐YOLO. Initially, an Adaptive Spatial Weight Perception (ASWP) module is designed to emphasize local information from different regions during the downsampling process and integrate effective features. Additionally, a Multidimensional Aggregation Radiative Feature Pyramid Networks (MARFPN) is proposed to aggregate multi‐scale semantic information across dimensions and relay it back to various levels within the network to facilitate the learning of more refined feature. Lastly, a Cross‐Layer Collaborative Detection Head (CLCDH) is introduced to further weight and fuse the contextual information between local and global aspects. Experimental results demonstrate that AMC‐YOLO outperforms state‐of‐the‐art methods on the Cigarette Pack Defect and GC10‐DET datasets, exhibiting the highest detection precision and excellent generalization. These findings highlight the significant potential for the application of AMC‐YOLO in cigarette pack defect detection.https://doi.org/10.1049/ipr2.13272computer visionobject detectionproduct quality
spellingShingle Peng Dong
Yongsheng Wang
Qianyuan Yu
Weihua Feng
Guohao Zong
AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
IET Image Processing
computer vision
object detection
product quality
title AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
title_full AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
title_fullStr AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
title_full_unstemmed AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
title_short AMC‐YOLO: Improved YOLOv8‐based defect detection for cigarette packs
title_sort amc yolo improved yolov8 based defect detection for cigarette packs
topic computer vision
object detection
product quality
url https://doi.org/10.1049/ipr2.13272
work_keys_str_mv AT pengdong amcyoloimprovedyolov8baseddefectdetectionforcigarettepacks
AT yongshengwang amcyoloimprovedyolov8baseddefectdetectionforcigarettepacks
AT qianyuanyu amcyoloimprovedyolov8baseddefectdetectionforcigarettepacks
AT weihuafeng amcyoloimprovedyolov8baseddefectdetectionforcigarettepacks
AT guohaozong amcyoloimprovedyolov8baseddefectdetectionforcigarettepacks