Plant Pulse – Apple Disease Detection

Plant Pulse – Apple Disease Detection

Authors- Rinku Badgujar, Raj Ranka, Sambhav Kothari, Abhijeet Prasad

Abstract-The agricultural sector is a cornerstone of global food security, with apples being one of the most widely cultivated and consumed fruits. However, apple farming is plagued by diseases such as Black Rot, Apple Scab, and Cedar Apple Rust, which significantly impact crop yield, quality, and profitability. Traditional disease detection methods are largely manual, requiring expert intervention, and are often error-prone, time-consuming, and susceptible to subjective biases. To address these challenges, this paper presents an AI-driven Apple Disease Detection System that leverages deep learning for automated, precise, and scalable disease identification. The system employs the EfficientNetB0 architecture for high-accuracy classification and integrates Grad-CAM (Gradient-weighted Class Activation Mapping) to enhance model interpretability by visualizing disease-affected regions. Comprehensive evaluations on a diverse dataset reveal that the system achieves an accuracy exceeding 97%, demonstrating its robustness and efficacy. This innovative solution offers farmers and agricultural experts a reliable tool for early disease detection, promoting sustainable farming practices and enhancing productivity.

DOI: /10.61463/ijset.vol.12.issue6.350