Year: 2024
Type: article
Abstract: Turmeric plants are vulnerable to different diseases that threaten them throughout their growth cycle, potentially leading to reduced yields and crop losses in the absence of early detection. Common diseases observed in the Turmeric plant are leaf spots, leaf blotch, and rhizome rot. Rhizome rot is a devastating disease that impacts the production of turmeric. Its timely detection is crucial for disease management. This study introduces an efficient single-phase detection approach for identifying rhizome Rot disease in turmeric plants, offering an alternative to the conventional multi-stage method. This study uses Convolutional Neural Networks (CNNs), the VGG19 architecture, and the CNN-SVM (support vector machine) algorithm to establish a precise and efficient system for detecting a rhizome rot infection in turmeric. A substantive image dataset is prepared by capturing images of turmeric plant leaves and labeling them as infected and healthy based on rhizome rot infection. The selected algorithms are trained for classifying healthy and diseased plants using the leaf image dataset. The performance of these models is assessed, and it is found that the hybrid CNN-SVM algorithm shows superior performance in recognizing rhizome rot infection in turmeric plants.
Author: Ms. Sneha Arun Patil
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W4406536159