Combining CNN and SVM for Accurate Identification of Ridge Gourd Leaf Diseases
Deepak Banerjee, Vinay Kukreja, Amit Gupta, Vijay Singh, Tejinder Pal Singh Brar
Abstract
This study proposes a method for identifying and classifying ridge gourd leaf illnesses using a network of convolutional neural networks (CNN) models. Two layers using convolution, two maximally combined layers, and one completely linked layer are included in the proposed model. The goal is to forecast the existence of five diseases in the ridge gourd leaves: Powdery Mildew, Downy Fibre Mildew, Anthracnose, Bacteria Leaf Spot, and Cucumbers Mosaic Virus. For training and evaluation, a large dataset of gourd ridge leaf photos labeled with illness classifications is used. The CNN model uses its capacity to collect and extract key information from input photos to accurately classify and predict diseases. The results show that the proposed approach is effective, with high accuracy in diagnosing specific diseases. This study provides important insights into the early detection and handling of ridge gourd leaves diseases, which will be useful to farmers and researchers. By diagnosing and addressing these diseases as soon as possible, farmers can undertake focused prevention and control methods, enhancing crop health, decreasing yield losses, and assuring sustainable agricultural practices. The suggested CNN model provides a low-cost and efficient approach for automated illness detection, removing the need for inspection by humans and expert assistance. This model's excellent classification for the ridge gourd illnesses of the leaves has considerable promise for optimizing agricultural practices and boosting yields in the environment of ridges gourd farming.