EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Leaf Disease Segmentation Using U‐Net Architecture for Precision Agriculture: A Deep Learning Approach

Gurpreet Singh, Asma A Al-Huqail, Ahmad Almogren, Sukhdeep Kaur, Kapil Joshi, Ajay Singh, Salil Bharany, Seada Hussen iD, Ateeq Ur Rehman

Food Science & Nutrition · 2025-07 · 13 (7)

DOI: 10.1002/fsn3.70594 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Food Science & Nutrition, online erschienen am 14.07.2025. Verfasst von Gurpreet Singh und 8 weiteren Autor:innen. Beteiligte Einrichtung: Chitkara University Institute of Engineering and Technology Chitkara University Punjab India. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Saud University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a deep learning‐based image segmentation approach for leaf disease identification using the U‐Net architecture. Convolutional neural networks (CNNs), particularly U‐Net, are effective for precise segmentation tasks and were trained and validated on a high‐quality “Leaf Disease Segmentation” dataset. Each image contains annotated regions of unhealthy leaf tissue, enabling the model to distinguish between healthy and infected areas. Image preprocessing and augmentation further enhanced model performance and robustness. The U‐Net model, composed of an encoder for context extraction and a decoder for precise segmentation was trained to accurately identify diseased regions at the pixel level. Regularization techniques such as dropout, batch normalization, and ReLU activation were used to prevent overfitting and improve learning. Furthermore, Adam optimizer was employed with a learning rate of 0.001. The model demonstrated strong generalization by accurately segmenting disease regions in unseen validation images. It effectively captured complex patterns in both healthy and diseased leaf sections, outperforming traditional image processing techniques. Trained on 7056 images for 40 epochs, the model achieved 99.70% training accuracy, 0.062 training loss, and 98.99% validation accuracy. These results highlight the model's high accuracy, efficient learning, and robustness, making it suitable for real‐world applications in precision agriculture.

Schlagwörter

Stichwörter der Autor:innen

CNNU‐Net architecturedeep learningimage processingleaf disease segmentationplant pathologyprecision agriculturesemantic segmentation

Autor:innen und Institutionen

  • Chitkara University Institute of Engineering and Technology Chitkara University Punjab India.
  • Department of Botany and Microbiology, College of Science King Saud University Riyadh Saudi Arabia.
  • Department of Computer Science, College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia.
  • Department of CSE UIT, Uttaranchal University Dehradun Uttarakhand India.
  • School of Applied and Life Sciences Uttaranchal University Dehradun Uttarakhand India.
  • Department of Electrical Power Adama Science and Technology University Adama Ethiopia.

ORCID-Profile: Seada Hussen

Förderung

  • King Saud University

Zitieren

APA

Singh, G., Al-Huqail, A. A., Almogren, A., Kaur, S., Joshi, K., Singh, A., Bharany, S., Hussen, S., & Rehman, A. U. (2025). Enhanced Leaf Disease Segmentation Using U‐Net Architecture for Precision Agriculture: A Deep Learning Approach. Food Science & Nutrition, 13(7). https://doi.org/10.1002/fsn3.70594

Vancouver

Singh G, Al-Huqail AA, Almogren A, Kaur S, Joshi K, Singh A, et al. Enhanced Leaf Disease Segmentation Using U‐Net Architecture for Precision Agriculture: A Deep Learning Approach. Food Science & Nutrition. 2025;13(7). doi:10.1002/fsn3.70594

BibTeX
@article{Singh2025,
  author = {Singh, Gurpreet and Al-Huqail, Asma A and Almogren, Ahmad and Kaur, Sukhdeep and Joshi, Kapil and Singh, Ajay and Bharany, Salil and Hussen, Seada and Rehman, Ateeq Ur},
  title = {Enhanced Leaf Disease Segmentation Using U‐Net Architecture for Precision Agriculture: A Deep Learning Approach},
  journal = {Food Science & Nutrition},
  year = {2025},
  volume = {13},
  number = {7},
  doi = {10.1002/fsn3.70594}
}
Kostenlos starten →