Login Search
FMDB Transactions on Sustainable Health Science Letters Submit Paper
    Crossref logo

    Archiving

    Portico

    Fernando Martins De Bulhão is a member of

    Crossref logo

Enhanced Sunflower Leaf Disease Identification Using YOLO and CNN-Based Feature Extraction with Optimizer-Driven Classification

Authors:
M. Arunadevi Thirumalraj, M. Mathumathi, R. Kannan, Rahul Panakkal

Addresses:
Department of Computer Science and Engineering, Karunya Institute of Technology and Science, Coimbatore, Tamil Nadu, India. Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Computer Science and Engineering, K. Ramakrishnan College of Technology, Tiruchirappalli, Tamil Nadu, India. Department of Computer Science and Engineering, University of Illinois at Urbana, Champaign, Illinois, United States of America.

Abstract:

Essential oilseed crops grown all around the globe include sunflowers (Helianthus annuus). Nevertheless, rust, powdery mildew, downy mildew, and Alternaria leaf blight are only a few of the leaf diseases that drastically reduce crop output. Lower yields and economic losses result from these diseases' effects on plant health, which diminish photosynthetic efficiency. Conventional approaches to disease detection rely on human observation, which can be laborious, biased, and prone to errors due to both the observer and their surroundings. A fast, accurate, and reliable disease-detection system is required to detect and categorise sunflower leaf illnesses in real time. This study utilises the YOLO (You Only Look Once) object detection network and a pre-trained CNN for feature extraction and classification to develop a deep learning-based process for disease diagnosis in sunflower leaves. An enhanced YOLO-based detection model is used for real-time classification, with a pre-trained CNN extracting deep spatial features from sunflower leaf images. To further improve detection accuracy while reducing computational complexity, an optimiser-based network is also used. The suggested method outperforms conventional machine learning techniques in identifying a range of diseases affecting sunflower leaves, achieving impressive recall and precision. 

Keywords: Sunflower Leaves Disease Detection; Convolutional Neural Network; Feature Extraction; Machine Learning Methods; Alternaria Leaf Blight; Modified Wiener Filter.

Received on: 10/02/2025, Revised on: 15/04/2025, Accepted on: 23/06/2025, Published on: 06/12/2025

DOI: 10.69888/FTSHSL.2025.000513

FMDB Transactions on Sustainable Health Science Letters, 2025 Vol. 3 No. 4, Pages: 246-255

  • Views : 253
  • Downloads : 19
Download PDF