Skip to content
DraconiticResearch
Search Sources API
184,937 studies31 sourcesUpdated 48 min ago
Peer-reviewedCC BY 4.0Frontiers in Plant Science

TomaNet-6H: towards transparent plant disease detection using a modified CNN with Grad-CAM for tomato leaves

  • Shubham Roy1
  • Shakir Khan2,3
  • Neha Gupta1
  • Achin Jain1
  • Arvind Panwar4
  • Fahad Omar Alomary5
  • Abeer Aljohani6
  • Saqib Qamar7,8
8 affiliations
  1. 1Department of Information Technology, Bharati Vidyapeeth’s College of Engineering
  2. 2Information Technology Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)
  3. 3University Centre for Research and Development (UCRD), Chandigarh University
  4. 4Galgotias Multi-Disciplinary Research & Development Cell (G-MRDC), Galgotias University
  5. 5College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)
  6. 6Department of Computer Science and Information, Applied College, Taibah University
  7. 7Department of Intelligent Systems, KTH Royal Institute of Technology
  8. 8Faculty of Computing and IT (FCIT), Sohar University
Open at sourcePDFDOICite

Abstract

Plant diseases pose a critical challenge to agricultural productivity, underscoring the need for rapid and reliable automated detection methods. Manual disease identification is labor-intensive and error-prone, whereas deep learning techniques offer scalable alternatives. This study evaluates five convolutional neural network (CNN) architectures—XceptionNet, DenseNet121, a baseline five-layer CNN, a six-layer CNN, and a proposed custom architecture, TomaNet-6H—for classifying tomato leaf conditions using the PlantVillage dataset. Image preprocessing combines color space transformations and Contrast Limited Adaptive Histogram Equalization (CLAHE), alongside targeted data augmentation to mitigate class imbalance. Experimental results demonstrate that TomaNet-6H achieves a test accuracy of 97.42% and a macro F1-score of 96.60%, while maintaining moderate computational complexity (∼7M parameters) and an inference latency of 68.4 ms per image. Furthermore, Grad-CAM visualizations qualitatively indicate that the network predominantly focuses on symptomatic leaf areas rather than background artifacts. These findings highlight TomaNet-6H as an effective, resource-conscious framework for precision agriculture deployment.

Related

  1. Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection
    Yunchang Zheng, Mengfan Wang, Jiacheng Sun +2
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMCPMC
  2. A lightweight privacy-aware federated vision transformer for tomato leaf disease classification
    Debangana Ram, Manasi Gyanchandani, Akhtar Rasool +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textPlant biologyCrossref
  3. CGW-DETR: a multi-scale feature enhanced RT-DETR Qianxi cherry tomato maturity detection model for dense small targets
    Meng Li, Xue Ding, Na Nong +1
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Plant biologyFrontiersCrossref
  4. Drought-Spec-Net: Early Tomato Drought Detection and Potential Yield-Impact Assessment Using Vis NIR Data
    K. Hossain, A. Maiti, K. Chinnannan +7
    bioRxivPreprintCC BYFull textPlant biologybioRxiv
  5. MambaSeed: A lightweight Mamba-based hybrid vision network for tomato leaf disease recognition
    XueShen Wang, Heng Zhang, Yayong Chen +4
    PLOS OnePeer-reviewedCC BY 4.0Full textPlant biologyPLOS

Cite

BibTeXRIS
BibTeX
@article{roy2026tomanet6h,
  title = {{TomaNet-6H: towards transparent plant disease detection using a modified CNN with Grad-CAM for tomato leaves}},
  author = {Shubham Roy and Shakir Khan and Neha Gupta and Achin Jain and Arvind Panwar and Fahad Omar Alomary and Abeer Aljohani and Saqib Qamar},
  journal = {Frontiers in Plant Science},
  year = {2026},
  month = oct,
  doi = {10.3389/fpls.2026.1970111},
  url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1970111/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - TomaNet-6H: towards transparent plant disease detection using a modified CNN with Grad-CAM for tomato leaves
AU  - Shubham Roy
AU  - Shakir Khan
AU  - Neha Gupta
AU  - Achin Jain
AU  - Arvind Panwar
AU  - Fahad Omar Alomary
AU  - Abeer Aljohani
AU  - Saqib Qamar
PY  - 2026
DA  - 2026/10/23
JO  - Frontiers in Plant Science
DO  - 10.3389/fpls.2026.1970111
UR  - https://www.frontiersin.org/articles/10.3389/fpls.2026.1970111/full
AB  - Plant diseases pose a critical challenge to agricultural productivity, underscoring the need for rapid and reliable automated detection methods. Manual disease identification is labor-intensive and error-prone, whereas deep learning techniques offer scalable alternatives. This study evaluates five convolutional neural network (CNN) architectures—XceptionNet, DenseNet121, a baseline five-layer CNN, a six-layer CNN, and a proposed custom architecture, TomaNet-6H—for classifying tomato leaf conditions using the PlantVillage dataset. Image preprocessing combines color space transformations and Contrast Limited Adaptive Histogram Equalization (CLAHE), alongside targeted data augmentation to mitigate class imbalance. Experimental results demonstrate that TomaNet-6H achieves a test accuracy of 97.42% and a macro F1-score of 96.60%, while maintaining moderate computational complexity (∼7M parameters) and an inference latency of 68.4 ms per image. Furthermore, Grad-CAM visualizations qualitatively indicate that the network predominantly focuses on symptomatic leaf areas rather than background artifacts. These findings highlight TomaNet-6H as an effective, resource-conscious framework for precision agriculture deployment.
SN  - 1664-462X
ER  -