Development of a mobile-based application for leaf disease recognition in abaca (Musa textilis)

Abaca is a significant crop valued for its durable fibers, widely used in various industries. However, abaca cultivation is threatened by diseases that can severely impact yields and quality. Hence, timely detection and accurate diagnosis of these diseases are crucial for effective management. Thus, this research tries to develop a tool that can detect and diagnose leaf diseases to aid farmers in disease mitigation. This research utilized the Waterfall model in the development of the application. Ten types of disease image datasets were collected from Kaggle. Three testing strategies namely benchmark, alpha, and beta tests were conducted to evaluate the application using ISO/IEC 25010 software quality metrics. During these tests, the application gained an overall mean of 3.49, 3.76, and 4.52 respectively. The findings revealed that the application is already usable and functional. Additional features may be included for easy mitigation in the widespread of the disease in future studies.