DGS-YOLOv8: A Method for Ginseng Appearance Quality Detection

Lijuan Zhang, Haohai You, Zhanchen Wei, Zhiyi Li, Haojie Jia, Shengpeng Yu, Chunxi Zhao, Yan Lv () and Dongming Li
Additional contact information
Lijuan Zhang: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Haohai You: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Zhanchen Wei: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Zhiyi Li: College of Instrument Science & Electrical Engineering, Jilin University, Changchun 130012, China
Haojie Jia: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Shengpeng Yu: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Chunxi Zhao: Information Center, Jilin Agricultural University, Changchun 130118, China
Yan Lv: College of Information Technology, Jilin Agricultural University, Changchun 130118, China
Dongming Li: College of Information Technology, Jilin Agricultural University, Changchun 130118, China

Agriculture, 2024, vol. 14, issue 8, 1-26

Abstract: In recent years, the research and application of ginseng, a famous and valuable medicinal herb, has received extensive attention at home and abroad. However, with the gradual increase in the demand for ginseng, discrepancies are inevitable when using the traditional manual method for grading the appearance and quality of ginseng. Addressing these challenges was the primary focus of this study. This study obtained a batch of ginseng samples and enhanced the dataset by data augmentation, based on which we refined the YOLOv8 network in three key dimensions: firstly, we used the C2f-DCNv2 module and the SimAM attention mechanism to augment the model’s effectiveness in recognizing ginseng appearance features, followed by the use of the Slim-Neck combination (GSConv + VoVGSCSP) to lighten the model These improvements constitute our proposed DGS-YOLOv8 model, which achieved an impressive mAP50 of 95.3% for ginseng appearance quality detection. The improved model not only has a reduced number of parameters and smaller size but also improves 6.86%, 2.73%, and 3.82% in precision, mAP50, and mAP50-95 over the YOLOv8n model, which comprehensively outperforms the other related models. With its potential demonstrated in this experiment, this technology can be deployed in large-scale production lines to benefit the food and traditional Chinese medicine industries. In summary, the DGS-YOLOv8 model has the advantages of high detection accuracy, small model space occupation, easy deployment, and robustness.

Keywords: ginseng appearance quality; machine vision; image analysis; attention mechanism; deep learning (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/14/8/1353/pdf (application/pdf)
https://www.mdpi.com/2077-0472/14/8/1353/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:14:y:2024:i:8:p:1353-:d:1455576

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().