EUVIMEDEUVIMED entdecken
Crossref

Benchmarking Local Vision-Language Models and Knowledge-Graph-Assisted Differential Diagnosis of Plant Diseases

Byungheon Choi, Yoeguang Hue, Yebin Nam, Jinyong Kim, Chaemin Lim, Jinsung Kim, Hyun Sim, Chulyoung Park, Ki-Tae Kim

The Plant Pathology Journal · 02.11.2026

DOI: 10.5423/ppj.ft.09.2026.0128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Plant Pathology Journal, online erschienen am 02.11.2026. Verfasst von Byungheon Choi und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plant Medicine, Sunchon National University, Suncheon 57922, Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image-based plant disease diagnosis is complicated by overlapping symptoms and variable imagining conditions. We evaluated six locally deployable vision-language models (VLMs) as generators of searchable symptom descriptions and integrated the selected model with knowledge-graph-assisted differential diagnosis. The dataset comprised 26,814 images representing 22 diseases, with 21,441 reference images and 5,373 internal-evaluation images. Symptom descriptions were embedded using Qwen3-Embedding-8B and evaluated by Top-1 retrieval, soft voting, and hard voting among same-host reference cases. Hard voting improved internal accuracy for all six VLMs. Qwen3.5-35B-A3B achieved 68.94% accuracy and 66.33% macro F1 at K = 19, compared with 40.87% accuracy and 46.25% macro F1 for a direct-classification baseline using the image, host, and allowed disease labels without retrieval. The selected VLM was integrated with a Neo4j knowledge graph in AI Plant Doctor version 2. In an idealized question-answering simulation using a balanced subset of 440 images and complete, ground-truth-consistent responses, the GraphRAG-only and hybrid retrieval-assisted workflows achieved accuracies of 74.55% and 97.27%, respectively. These values are not estimates of field diagnostic accuracy. This modular and explainable framework provides a promising foundation for plant disease decision support and is available through AI Plant Doctor version 2 at https://pdoc.scnu.ac.kr/pdoc2.

Schlagwörter

Stichwörter der Autor:innen

embedding retrievalfrequency-based votingknowledge graphplant disease diagnosisvision-language model

Autor:innen und Institutionen

  • Department of Plant Medicine, Sunchon National University, Suncheon 57922, Korea.
  • Department of Artificial Intelligence Engineering, Sunchon National University, Suncheon 57922, Korea.
  • Department of Agricultural Life Science, Sunchon National University, Suncheon 57922, Korea.
  • Department of Industry-Academic Collaboration Foundation, Sunchon National University, Suncheon 57922, Korea.
  • Department of Plant Medicine, Sunchon National University, Suncheon 57922, Korea. kitaekim@scnu.ac.kr.
  • Department of Agricultural Life Science, Sunchon National University, Suncheon 57922, Korea. kitaekim@scnu.ac.kr.

Zitieren

APA

Choi, B., Hue, Y., Nam, Y., Kim, J., Lim, C., Kim, J., Sim, H., Park, C., & Kim, K. T. (2026). Benchmarking Local Vision-Language Models and Knowledge-Graph-Assisted Differential Diagnosis of Plant Diseases. The Plant Pathology Journal. https://doi.org/10.5423/ppj.ft.09.2026.0128

Vancouver

Choi B, Hue Y, Nam Y, Kim J, Lim C, Kim J, et al. Benchmarking Local Vision-Language Models and Knowledge-Graph-Assisted Differential Diagnosis of Plant Diseases. The Plant Pathology Journal. 2026. doi:10.5423/ppj.ft.09.2026.0128

BibTeX
@article{Choi2026,
  author = {Choi, Byungheon and Hue, Yoeguang and Nam, Yebin and Kim, Jinyong and Lim, Chaemin and Kim, Jinsung and Sim, Hyun and Park, Chulyoung and Kim, Ki-Tae},
  title = {Benchmarking Local Vision-Language Models and Knowledge-Graph-Assisted Differential Diagnosis of Plant Diseases},
  journal = {The Plant Pathology Journal},
  year = {2026},
  doi = {10.5423/ppj.ft.09.2026.0128}
}
Kostenlos starten →