BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection

In the field of bookbinding, accurately and efficiently detecting signature sequences during the binding process is crucial for enhancing quality, improving production efficiency, and advancing industrial automation. Despite significant advancements in object detection technology, verifying the corr...

Full description

Saved in:
Bibliographic Details
Main Authors: Long Guo, Lubin Wang, Qiang Yu, Xiaolan Xie
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/23/10829
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260894377836544
author Long Guo
Lubin Wang
Qiang Yu
Xiaolan Xie
author_facet Long Guo
Lubin Wang
Qiang Yu
Xiaolan Xie
author_sort Long Guo
collection DOAJ
description In the field of bookbinding, accurately and efficiently detecting signature sequences during the binding process is crucial for enhancing quality, improving production efficiency, and advancing industrial automation. Despite significant advancements in object detection technology, verifying the correctness of signature sequences remains challenging due to the small size, dense distribution, and abundance of low-quality signature marks. To tackle these challenges, we introduce the Book Signature Marks Detection (BSMD-YOLOv8) model, specifically designed for scenarios involving small, closely spaced objects such as signature marks. Our proposed backbone, the Lightweight Multi-scale Residual Network (LMRNet), achieves a lightweight network while enhancing the accuracy of small object detection. To address the issue of insufficient fusion of local and global feature information in PANet, we design the Low-stage gather-and-distribute (Low-GD) module and the High-stage gather-and-distribute (High-GD) module to enhance the model’s multi-scale feature fusion capabilities, thereby refining the integration of local and global features of signature marks. Furthermore, we introduce Wise-IoU (WIoU) as a replacement for CIoU, prioritizing anchor boxes with moderate quality and mitigating harmful gradients from low-quality examples. Experimental results demonstrate that, compared to YOLOv8n, BSMD-YOLOv8 reduces the number of parameters by 65%, increases the frame rate by 7 FPS, and enhances accuracy, recall, and mAP50 by 2.2%, 8.6%, and 3.9% respectively, achieving rapid and accurate detection of signature marks.
format Article
id doaj-art-b2a9d5159e994b329954e6a9e4e28794
institution OA Journals
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-b2a9d5159e994b329954e6a9e4e287942025-08-20T01:55:32ZengMDPI AGApplied Sciences2076-34172024-11-0114231082910.3390/app142310829BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks DetectionLong Guo0Lubin Wang1Qiang Yu2Xiaolan Xie3College of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaCollege of Information Engineering, Guilin Institute of Information Technology, Guilin 541004, ChinaNational Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaCollege of Computer Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaIn the field of bookbinding, accurately and efficiently detecting signature sequences during the binding process is crucial for enhancing quality, improving production efficiency, and advancing industrial automation. Despite significant advancements in object detection technology, verifying the correctness of signature sequences remains challenging due to the small size, dense distribution, and abundance of low-quality signature marks. To tackle these challenges, we introduce the Book Signature Marks Detection (BSMD-YOLOv8) model, specifically designed for scenarios involving small, closely spaced objects such as signature marks. Our proposed backbone, the Lightweight Multi-scale Residual Network (LMRNet), achieves a lightweight network while enhancing the accuracy of small object detection. To address the issue of insufficient fusion of local and global feature information in PANet, we design the Low-stage gather-and-distribute (Low-GD) module and the High-stage gather-and-distribute (High-GD) module to enhance the model’s multi-scale feature fusion capabilities, thereby refining the integration of local and global features of signature marks. Furthermore, we introduce Wise-IoU (WIoU) as a replacement for CIoU, prioritizing anchor boxes with moderate quality and mitigating harmful gradients from low-quality examples. Experimental results demonstrate that, compared to YOLOv8n, BSMD-YOLOv8 reduces the number of parameters by 65%, increases the frame rate by 7 FPS, and enhances accuracy, recall, and mAP50 by 2.2%, 8.6%, and 3.9% respectively, achieving rapid and accurate detection of signature marks.https://www.mdpi.com/2076-3417/14/23/10829small object detectionYOLOv8book signature marks detectionWIoU
spellingShingle Long Guo
Lubin Wang
Qiang Yu
Xiaolan Xie
BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
Applied Sciences
small object detection
YOLOv8
book signature marks detection
WIoU
title BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
title_full BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
title_fullStr BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
title_full_unstemmed BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
title_short BSMD-YOLOv8: Enhancing YOLOv8 for Book Signature Marks Detection
title_sort bsmd yolov8 enhancing yolov8 for book signature marks detection
topic small object detection
YOLOv8
book signature marks detection
WIoU
url https://www.mdpi.com/2076-3417/14/23/10829
work_keys_str_mv AT longguo bsmdyolov8enhancingyolov8forbooksignaturemarksdetection
AT lubinwang bsmdyolov8enhancingyolov8forbooksignaturemarksdetection
AT qiangyu bsmdyolov8enhancingyolov8forbooksignaturemarksdetection
AT xiaolanxie bsmdyolov8enhancingyolov8forbooksignaturemarksdetection