Deep learning based plant health disease detection in tomatoes using inception v4 convolutional neural network and YOLO V8
Abstract
Tomato plant diseases significantly impact agricultural productivity, posing a\\\\r\\\\nchallenge for sustainable crop management. This study proposes a deep learning-\\\\r\\\\nbased framework for accurate and automated detection of tomato plant diseases\\\\r\\\\nusing the Inception v4 convolutional neural network (CNN) and YOLOv8 (You Only\\\\r\\\\nLook Once, version 8) object detection model. A curated dataset of tomato plant\\\\r\\\\nimages, encompassing various diseases such as bacterial spot, early blight, late blight,\\\\r\\\\nand leaf mold, alongside healthy samples, was developed for training and evaluation.\\\\r\\\\nThe Inception v4 CNN is employed for feature extraction and classification, while\\\\r\\\\nYOLOv8 is utilized for real-time disease detection and localization. Experimental\\\\r\\\\nresults demonstrate that the combined use of Inception v4 and YOLOv8 achieves\\\\r\\\\na classification accuracy of 96% and a mean Average Precision (mAP@0.5) of 86%\\\\r\\\\nfor leaf disease detection with precision and recall improving by 5.3% and 4.8%,\\\\r\\\\nrespectively, compared to existing methods. The proposed model highlights the\\\\r\\\\npotential of deep learning techniques to enhance early disease diagnosis, enabling\\\\r\\\\nfarmers to take timely and effective measures to mitigate crop losses.
Keywords
Download Article
How to Cite
B. Sowmya;S. Guruprasad. "Deep learning based plant health disease detection in tomatoes using inception v4 convolutional neural network and YOLO V8." DELSU Journal of Communication and Media Studies, vol. 1, no. 1, pp. XX-XX, 2026.
SEO & Indexing Status
- Google Scholar metadata complete
- Structured data (Schema.org) implemented
- Dublin Core metadata present
- SEO-friendly URL:
/article/deep-learning-based-plant-health-disease-detection-in-tomatoes-using-inception-v4-convolutional-neural-network-and-yolo-v8
- Open Graph tags optimized
- Canonical URL set
- Robots directives enabled
- 301 redirects from old URLs
Journal Information
- Journal: DELSU Journal of Communication and Media Studies
- ISSN: XXXX-XXXX
- Publisher: Delta State University Abraka
- Country: Nigeria
- Language: English
- Access: Open Access
Issue Information
Google Scholar Indexing
This article is optimized for Google Scholar with:
- Complete citation metadata
- PDF availability with metadata
- DOI integration
- Structured abstract
- Separate author tags
- Proper publication dates