Jackfruit Disease Recognition Using Image Processing in Non-Destructive Method with Alternative Treatment Recommender

Abstract

This study focuses on developing a mobile application for jackfruit disease recognition using advanced image processing techniques and hybrid algorithms. The proposed system combines Convolutional Neural Networks (CNN) with Support Vector Machines (SVM) to create a non-destructive method for accurately diagnosing jackfruit disease, particularly Rhizopus disease, through image analysis. By addressing the limitations of traditional disease detection methods, this application aims to provide a rapid, reliable, and automated solution for monitoring jackfruit health. Additionally, the study integrates an alternative treatment recommender that suggests organic and eco-friendly solutions for disease management, enhancing the sustainability and effectiveness of jackfruit cultivation. The system's performance was evaluated using metrics such as accuracy, precision, recall, and F1 score, with the goal of creating a high-quality, user-friendly application based on ISO 25010 software quality standards.