CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection

Abstract To advance the integration of traditional Chinese medicine (TCM) with next-generation information technologies, the intelligent identification of Chinese herbal decoction pieces (CHDP) has become a crucial research direction. However, the performance of current algorithms remains unsatisfac...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuhe Lin, Zhijun Xie, Xing Jin, Hangjuan Lin, Renguang Shan
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00111-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330421076066304
author Chuhe Lin
Zhijun Xie
Xing Jin
Hangjuan Lin
Renguang Shan
author_facet Chuhe Lin
Zhijun Xie
Xing Jin
Hangjuan Lin
Renguang Shan
author_sort Chuhe Lin
collection DOAJ
description Abstract To advance the integration of traditional Chinese medicine (TCM) with next-generation information technologies, the intelligent identification of Chinese herbal decoction pieces (CHDP) has become a crucial research direction. However, the performance of current algorithms remains unsatisfactory. To address this, we have constructed a diverse CHDP dataset and proposed a lightweight network for CHDP detection, named CHDPL-Net. Based on YOLOv8, this model introduces a new network scaling factor to reduce redundant channels in deep feature maps and optimizes the Neck and Head structures to better accommodate CHDP detection, which primarily involves medium and large targets. Additionally, a newly designed downsampling module, RDown, replaces conventional downsampling methods to reduce computational overhead, while the adopted upsampling module, DySample, significantly enhances the recovery of detailed features. To further improve lightweight performance, we apply GhostConv to optimize the SPPF and C2F modules and incorporate a novel attention mechanism, EHA, which makes the model more sensitive to color and texture information, mitigating the performance degradation caused by lightweight design. Ultimately, CHDPL-Net achieved excellent results with only 31.9% of the Parameters and 30.6% of the FLOPs compared to YOLOv8, obtaining $$mAP_{50}$$ m A P 50 and $$mAP_{50:95}$$ m A P 50 : 95 scores of 98.2% and 95.4%, respectively, with only a 0.8% performance drop. This demonstrates that the model can meet practical detection needs to a certain extent.
format Article
id doaj-art-efd93dadc8cd401cb6054ca456e45845
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-efd93dadc8cd401cb6054ca456e458452025-08-20T03:46:54ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137712310.1007/s44443-025-00111-5CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detectionChuhe Lin0Zhijun Xie1Xing Jin2Hangjuan Lin3Renguang Shan4Faculty of Electrical Engineering and Computer Science, Ningbo UniversityFaculty of Electrical Engineering and Computer Science, Ningbo UniversityFaculty of Electrical Engineering and Computer Science, Ningbo UniversityDepartment of Pharmacy, Ningbo Hospital of Traditional Chinese MedicineDepartment of Pharmacy, Ningbo Hospital of Traditional Chinese MedicineAbstract To advance the integration of traditional Chinese medicine (TCM) with next-generation information technologies, the intelligent identification of Chinese herbal decoction pieces (CHDP) has become a crucial research direction. However, the performance of current algorithms remains unsatisfactory. To address this, we have constructed a diverse CHDP dataset and proposed a lightweight network for CHDP detection, named CHDPL-Net. Based on YOLOv8, this model introduces a new network scaling factor to reduce redundant channels in deep feature maps and optimizes the Neck and Head structures to better accommodate CHDP detection, which primarily involves medium and large targets. Additionally, a newly designed downsampling module, RDown, replaces conventional downsampling methods to reduce computational overhead, while the adopted upsampling module, DySample, significantly enhances the recovery of detailed features. To further improve lightweight performance, we apply GhostConv to optimize the SPPF and C2F modules and incorporate a novel attention mechanism, EHA, which makes the model more sensitive to color and texture information, mitigating the performance degradation caused by lightweight design. Ultimately, CHDPL-Net achieved excellent results with only 31.9% of the Parameters and 30.6% of the FLOPs compared to YOLOv8, obtaining $$mAP_{50}$$ m A P 50 and $$mAP_{50:95}$$ m A P 50 : 95 scores of 98.2% and 95.4%, respectively, with only a 0.8% performance drop. This demonstrates that the model can meet practical detection needs to a certain extent.https://doi.org/10.1007/s44443-025-00111-5Chinese herbal decoction piecesObject detectYOLOv8Lightweight model
spellingShingle Chuhe Lin
Zhijun Xie
Xing Jin
Hangjuan Lin
Renguang Shan
CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
Journal of King Saud University: Computer and Information Sciences
Chinese herbal decoction pieces
Object detect
YOLOv8
Lightweight model
title CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
title_full CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
title_fullStr CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
title_full_unstemmed CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
title_short CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection
title_sort chdpl net a lightweight network for chinese herbal decoction pieces detection
topic Chinese herbal decoction pieces
Object detect
YOLOv8
Lightweight model
url https://doi.org/10.1007/s44443-025-00111-5
work_keys_str_mv AT chuhelin chdplnetalightweightnetworkforchineseherbaldecoctionpiecesdetection
AT zhijunxie chdplnetalightweightnetworkforchineseherbaldecoctionpiecesdetection
AT xingjin chdplnetalightweightnetworkforchineseherbaldecoctionpiecesdetection
AT hangjuanlin chdplnetalightweightnetworkforchineseherbaldecoctionpiecesdetection
AT renguangshan chdplnetalightweightnetworkforchineseherbaldecoctionpiecesdetection