Detection of cucumber and watermelon diseases based on image processing techniques using K-means algorithm

Abstract

Agriculture in Nigeria is a branch of its economy providing employment for over 70% of its population and contributing about 41% to it gross domestic production (GDP). Nigeria’s wide range of climate variations allows it to produce a variety of food and cash crops. Cucumber/watermelon is among the few varieties of fruits and vegetables produced in the country. The need for steady monitoring of the plants is necessary to detect and control the spread of its diseases. Common practices for detecting these plants diseases are mostly based on direct observation of the affected plant, which are sometimes erroneous. Laboratory analysis can also be used for plant diseases detection but mostly costly and time consuming. Digital image processing can identify and grade the diseases in cucumber/watermelon. This will aid in describing and predicting the performance of the said cultivated crops, hence increasing the production yield. Although, official disease recognition is a responsibility of professional agriculturists, low-cost observation and computational assisted diagnosis can effectively help in the recognition of a plant disease in its early stages. The application software was designed based on Object Oriented System Analysis and Design Methodology while UML was used to model the system; MATLAB was used in designing the front-end and the database is MYSQL Server. The developed system works efficiently and can successfully detect and classify the specified diseases in cucumber/watermelon with a precision between 92% and 98%.