EUVIMEDEUVIMED entdecken
Crossref

An Explainable Xception-Based Approach for Multi-Class Tomato Leaf Disease Detection

Chirag Tiwari, Dinesh Swami, Khyati Zalawadia, Vipul M Dabhi, Himadri M Vegad, Krupali Dave

International Journal of Drug Delivery Technology · 01.06.2026 · 16 (42s)

DOI: 10.25258/ijddt.16.42s.83 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 01.06.2026. Verfasst von Chirag Tiwari und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The early identification of tomato leaf diseases is paramount if farmers wish to maximize their yield while minimizing crop loss. However, as the labour-intensive process of inspecting each plant is often tedious and subjective, the requirement now exists for a reliable automated system for tomato leaf disease recognition. In this paper, we propose a deep learning approach for the automated multi-class identification of tomato leaf diseases from a collection of images taken within greenhouses. Dataset consists of 15254 tomato leaf disease images, which include healthy tomato leaves as well as images depicting various combinations of one or more diseases afflicting a single tomato leaf. For our proposed methodology, we employed a transfer-learning framework, which takes advantage of using the Xception architecture and makes use of pretrained visual representations adapted to fit the requirements of plant pathology via fine-tuning process. The results of our experiments demonstrate a strong discriminative power of all seven identified classes, with 94.71 percent accuracy being achieved for the test dataset and a consistently high per-class performance being maintained, even amongst visually similar and minority classes. The results reinforce that the methodology examined presents an appropriate and extensive practical means of discovering tomato leaf diseases in greenhouses.

Zitieren

APA

Tiwari, C., Swami, D., Zalawadia, K., Dabhi, V. M., Vegad, H. M., & Dave, K. (2026). An Explainable Xception-Based Approach for Multi-Class Tomato Leaf Disease Detection. International Journal of Drug Delivery Technology, 16(42s). https://doi.org/10.25258/ijddt.16.42s.83

Vancouver

Tiwari C, Swami D, Zalawadia K, Dabhi VM, Vegad HM, Dave K. An Explainable Xception-Based Approach for Multi-Class Tomato Leaf Disease Detection. International Journal of Drug Delivery Technology. 2026;16(42s). doi:10.25258/ijddt.16.42s.83

BibTeX
@article{Tiwari2026,
  author = {Tiwari, Chirag and Swami, Dinesh and Zalawadia, Khyati and Dabhi, Vipul M and Vegad, Himadri M and Dave, Krupali},
  title = {An Explainable Xception-Based Approach for Multi-Class Tomato Leaf Disease Detection},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {42s},
  doi = {10.25258/ijddt.16.42s.83}
}
Kostenlos starten →