Leather Defect Detection Based on Improved YOLOv8 Model

Addressing the low accuracy and slow detection speed experienced by algorithms based on deep learning for a leather defect detection task, a lightweight and improved leather defect detection algorithm, dubbed YOLOv8-AGE, has been proposed based on YOLOv8n. In the backbone network, the EMA attention...

Full description

Saved in:
Bibliographic Details
Main Authors: Zirui Peng, Chen Zhang, Wei Wei
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/11566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050218259644416
author Zirui Peng
Chen Zhang
Wei Wei
author_facet Zirui Peng
Chen Zhang
Wei Wei
author_sort Zirui Peng
collection DOAJ
description Addressing the low accuracy and slow detection speed experienced by algorithms based on deep learning for a leather defect detection task, a lightweight and improved leather defect detection algorithm, dubbed YOLOv8-AGE, has been proposed based on YOLOv8n. In the backbone network, the EMA attention mechanism and C2f module have been fused into the C2f-EMA module, achieving performance enhancement with lower computational overhead. In the neck, the AFPN structure has been combined with the VoV-GSCSP module constructed using GSConv, to reduce the number of parameters while enhancing the model’s multi-scale detection capability. Finally, a shared convolutional layer has been introduced for simplifying the design of the detection head. Experimental results demonstrate that the improved algorithm achieves an improvement of 1.39% in mAP50 and reduces the number of parameters and GFLOPs by 9.3% and 7.41%, respectively, as compared to the original YOLOv8 model. On the dataset in this paper, there is an improvement in accuracy and detection speed over mainstream algorithms.
format Article
id doaj-art-87169c6cc1574c2bbdde780d2f1bbd7c
institution DOAJ
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-87169c6cc1574c2bbdde780d2f1bbd7c2025-08-20T02:53:31ZengMDPI AGApplied Sciences2076-34172024-12-0114241156610.3390/app142411566Leather Defect Detection Based on Improved YOLOv8 ModelZirui Peng0Chen Zhang1Wei Wei2School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaDepartment of Electronic Information Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430048, ChinaAddressing the low accuracy and slow detection speed experienced by algorithms based on deep learning for a leather defect detection task, a lightweight and improved leather defect detection algorithm, dubbed YOLOv8-AGE, has been proposed based on YOLOv8n. In the backbone network, the EMA attention mechanism and C2f module have been fused into the C2f-EMA module, achieving performance enhancement with lower computational overhead. In the neck, the AFPN structure has been combined with the VoV-GSCSP module constructed using GSConv, to reduce the number of parameters while enhancing the model’s multi-scale detection capability. Finally, a shared convolutional layer has been introduced for simplifying the design of the detection head. Experimental results demonstrate that the improved algorithm achieves an improvement of 1.39% in mAP50 and reduces the number of parameters and GFLOPs by 9.3% and 7.41%, respectively, as compared to the original YOLOv8 model. On the dataset in this paper, there is an improvement in accuracy and detection speed over mainstream algorithms.https://www.mdpi.com/2076-3417/14/24/11566attention mechanismconvolution moduledeep learningYOLOv8
spellingShingle Zirui Peng
Chen Zhang
Wei Wei
Leather Defect Detection Based on Improved YOLOv8 Model
Applied Sciences
attention mechanism
convolution module
deep learning
YOLOv8
title Leather Defect Detection Based on Improved YOLOv8 Model
title_full Leather Defect Detection Based on Improved YOLOv8 Model
title_fullStr Leather Defect Detection Based on Improved YOLOv8 Model
title_full_unstemmed Leather Defect Detection Based on Improved YOLOv8 Model
title_short Leather Defect Detection Based on Improved YOLOv8 Model
title_sort leather defect detection based on improved yolov8 model
topic attention mechanism
convolution module
deep learning
YOLOv8
url https://www.mdpi.com/2076-3417/14/24/11566
work_keys_str_mv AT ziruipeng leatherdefectdetectionbasedonimprovedyolov8model
AT chenzhang leatherdefectdetectionbasedonimprovedyolov8model
AT weiwei leatherdefectdetectionbasedonimprovedyolov8model