Fruit Disease Detection Using Machine Learning

Authors: Prof. G Puranik, Tushar Paithane, Prasad Pansare, Shubham Zoting, Pranav Rajput

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: Fruit diseases significantly affect agriculture productivity and food security; hence an early and accurate detection is required to curtail losses. In this system is to develop an efficient fruit disease detection system by employing advanced image processing techniques combined with machine learning approaches. The system could classify the kind of disease accurately through specific visual symptoms by analyzing leaf images. Leverage this deep learning model trained on comprehensive datasets of both diseased and healthy Fruit images, and the system must assist in boosting the accuracy rate of detection and minimizing the rates of false diagnoses. It will utilize CNNs for feature extraction and classification, all optimized for the different types of Fruit species and diseases. Common Fruit diseases will be detected and categorized with high accuracy, even with diverse field conditions. In addition, the adaptability of the system allows for integration into mobile apps. In that system, real-time detection will be feasible to provide farmers with the in-situ information about the disease. Some of the major objectives are validation of precision of the developed system against the traditional diagnostic methods, proof of performance of the system’s ability to scale for different Fruit species, and overcoming other problems like changing environmental parameters. The successful implementation of In this system will be expected to empower farmers and agro-professionals in having the ability to use a credible tool that is accessible for the early detection of Fruit diseases, which will eventually be useful in helping them achieve sustainable agriculture practices in the relevant areas while reducing crop losses.

Keywords: Machine Learning, Image Processing, Segmentation, Deep CNN

Paper Id: 232365

Published On: 2025-04-11

Published In: Volume 13, Issue 2, March-April 2025

Share this