Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 11 min ago
Peer-reviewedCC BY 4.0Frontiers in Plant Science

A two-stage method for defect detection and mechanical damage assessment in mechanically harvested tobacco leaves

  • Erdeng Ma1
  • Hezheng Wang2
  • Siwei Zhang3
  • Wanxin Li2
  • Jiahui Liu2,4
  • Dong Zhao2,4
  • Jian Zhao2,4,5
5 affiliations
  1. 1Yunnan Academy of Tobacco Agricultural Sciences
  2. 2School of Technology, Beijing Forestry University
  3. 3Wenshan Branch of Yunnan Provincial Tobacco Company, Wenshan
  4. 4Key Lab of State Forestry Administration on Forestry Equipment and Automation, Beijing Forestry University
  5. 5State Key Laboratory of Efficient Production of Forest Resources
Read full textPDFDOICite

Abstract

Defects on mechanically harvested tobacco leaves may originate from diseases and pests or from harvesting operations, with distinct implications for crop quality. Dense small defects are easily missed, whereas local detection boxes cannot describe whole-leaf structural damage. We developed a two-stage vision method for non-destructive defect screening and assessment of harvest-related mechanical damage. Stage I used Tobacco Leaf Defect YOLO11n (TLD-YOLO11n), a task-adapted detector with high-resolution feature fusion, to identify four disease and pest categories and mechanical damage. Stage II used reference-midrib and leaf-morphology features to distinguish midrib breakage from lamina loss, while a relative lamina loss index provided an operational measure of tissue-loss severity. TLD-YOLO11n achieved mAP 0.5 and mAP 0.5:0.95 values of 84.5% and 64.1%, exceeding YOLO11n by 4.0 and 3.9 percentage points, respectively. Under controlled single-leaf imaging conditions, all 50 images with mechanical damage were passed to stage II, whereas none of the 156 disease- or pest-affected images were incorrectly passed. Damage type was correctly determined for 47 of the 50 mechanical-damage test images, yielding a joint accuracy of 94.0%. F1-scores for lamina loss and midrib breakage were 91.4% and 95.4%, respectively. The framework provides an approach for distinguishing harvest-related damage from other visual defects and quantifying loss of structural integrity in mechanically harvested tobacco leaves.

Related

  1. DTL-YOLO: a lightweight model for real-time tobacco leaf damage detection and mechanical harvesting quality assessment
    Yue Luo, Jun Yang, Chenhui Zhu +3
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMCPMC
  2. Development of mechanically optimized biomimetic hybrid scaffold–stem cell constructs for functional tendon regeneration and restoration of mechanical integrity
    Alani Mohanad Khalid Ahmed
    PLOS OnePeer-reviewedCC BY 4.0Full textDevelopmental biologyPhysiologyPLOS
  3. Patterns of tobacco product single and co-use – Findings from the Population Assessment of Tobacco and Health Study (PATH) wave 7 data
    Shu Xu, Yelan Wang, Luchang Cui +2
    PLOS OnePeer-reviewedCC BY 4.0Full textGeneral biologyGeneral chemistryPLOSPMC
  4. Detection of bacterial gene expression elements on Tobacco mosaic virus RNA using cDNA analysis
    Yoshiyuki Nishimiya
    PLOS OnePeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationMicrobiologyPLOS
  5. Genetic divergence and signatures of historical isolation of the traditionally harvested Amolops marmoratus from the Darjeeling Hill Region in the Himalaya Biodiversity Hotspot
    Kumaresh Mandal, Shishir Tamang, Soni Subba +9
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Full textGenetics & genomicsCrossref

Cite

BibTeXRIS
BibTeX
@article{ma2026twostage,
  title = {{A two-stage method for defect detection and mechanical damage assessment in mechanically harvested tobacco leaves}},
  author = {Erdeng Ma and Hezheng Wang and Siwei Zhang and Wanxin Li and Jiahui Liu and Dong Zhao and Jian Zhao},
  journal = {Frontiers in Plant Science},
  year = {2026},
  month = oct,
  doi = {10.3389/fpls.2026.1956974},
  url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1956974/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A two-stage method for defect detection and mechanical damage assessment in mechanically harvested tobacco leaves
AU  - Erdeng Ma
AU  - Hezheng Wang
AU  - Siwei Zhang
AU  - Wanxin Li
AU  - Jiahui Liu
AU  - Dong Zhao
AU  - Jian Zhao
PY  - 2026
DA  - 2026/10/08
JO  - Frontiers in Plant Science
DO  - 10.3389/fpls.2026.1956974
UR  - https://www.frontiersin.org/articles/10.3389/fpls.2026.1956974/full
AB  - Defects on mechanically harvested tobacco leaves may originate from diseases and pests or from harvesting operations, with distinct implications for crop quality. Dense small defects are easily missed, whereas local detection boxes cannot describe whole-leaf structural damage. We developed a two-stage vision method for non-destructive defect screening and assessment of harvest-related mechanical damage. Stage I used Tobacco Leaf Defect YOLO11n (TLD-YOLO11n), a task-adapted detector with high-resolution feature fusion, to identify four disease and pest categories and mechanical damage. Stage II used reference-midrib and leaf-morphology features to distinguish midrib breakage from lamina loss, while a relative lamina loss index provided an operational measure of tissue-loss severity. TLD-YOLO11n achieved mAP 0.5 and mAP 0.5:0.95 values of 84.5% and 64.1%, exceeding YOLO11n by 4.0 and 3.9 percentage points, respectively. Under controlled single-leaf imaging conditions, all 50 images with mechanical damage were passed to stage II, whereas none of the 156 disease- or pest-affected images were incorrectly passed. Damage type was correctly determined for 47 of the 50 mechanical-damage test images, yielding a joint accuracy of 94.0%. F1-scores for lamina loss and midrib breakage were 91.4% and 95.4%, respectively. The framework provides an approach for distinguishing harvest-related damage from other visual defects and quantifying loss of structural integrity in mechanically harvested tobacco leaves.
SN  - 1664-462X
ER  -