Automatic detection and diagnosis of cocoa diseases using mobile tech and deep learning

Cocoa is a cash crop that contributes about 3% to the gross domestic product (GDP) of Ghana's economy and makes up about 20% of total export receipts according to the Ghana statistical service. However, revenue has been hampered recently by the outbreak of cocoa diseases such as Swollen shoot and black pod thereby causing up to 11% loss of the crop. There is, therefore, a need for urgent intervention by all stakeholders within the cocoa production sector. In this research, we aim to employ mobile technology and machine learning (ML) techniques to enhance the early detection and diagnosis of the two major diseases that affect cocoa production namely - swollen shoot and black pod. Specifically, a distributed mobile application is developed that enables farmers to take a picture or video of the cocoa and the app will analyse and automatically detect the specific disease. The app consequently suggests the best treatment to undertake using an inbuilt-information guide. The automatic detection and diagnosis of diseases are based on deep convolutional neural networks (CNN) for image analysis, classification, and detection. The research analysed 2,828 cocoa images spread across three class labels. We built and trained four CNN models, namely CentreNet ResNet50 V2, EfficientDet D0, SSD MobileNet V2, and SSD ResNet50 V1 FPN. We found the best generalised and fastest model to be the SSD MobileNet V2 with a detection confidence score of approximately 88.0%.