Deep Learning-Based Approach for Identification of Potato Leaf Diseases Using Wrapper Feature Selection and Feature Concatenation

• DOI: 10.48550/arxiv.2502.03370
• Publication Date: 2025-02-05
• Authors: Muhammad Ahtsam N...; Muhammad Asim Saleem; Muhammad Sharif; Syed F. Akber; Sajjad Saleem; Zahid Akhtar; Kamran Siddique
• Keywords: Concatenation (mathematics); Identification; Feature (linguistics)

The potato is a widely grown crop in many regions of the world. In recent decades, farming has gained incredible traction Potatoes are susceptible to several illnesses that stunt their development. This plant seems have significant leaf disease. Early Blight and Late two prevalent diseases affect plants. early detection these would be beneficial for enhancing yield this crop. ideal solution use image processing identify analyze disorders. Here, we present an autonomous method based on machine learning detect late blight disease affecting leaves. proposed comprises four different phases: (1) Histogram Equalization used improve quality input image; (2) feature extraction performed using Deep CNN model, then extracted features concatenated; (3) selection wrapper-based selection; (4) classification SVM classifier its variants. achieves highest accuracy 99% by selecting 550 features.