Cocoa Care - An Android Application for Cocoa Disease Identification

Abstract

India is an agricultural country. The correct and timely identification of diseases in crops is very much essential in agriculture. To obtain more valuable products, a product quality control is basically mandatory. Cocoa is an economically important crop that nowadays enlarges its production in southern India. To assist the farmers growing cocoa, we developed an android application Cocoa-Care. This application automatically identifies the diseases of cocoa crops, thereby helps the farmers who have little or no information about the disease. This application is developed by applying digital image processing techniques on the diseased cocoa images. Our approach replaces the manual disease inspection by the android application that identifies the cocoa disease from the captured image and suggests the possible remedies for the farmer. We used moment based texture features for the image representation and description. The matching is performed by nearest neighbor classifier. The results obtained are promising and this application can be used in the real time.