A Deep Learning-based Detector for Brown Spot Disease in Passion Fruit Plant Leaves

Pests and diseases pose a key challenge to passion fruit farmers across and East Africa in general. They lead to loss of investment as yields and losses increases. As the majority of the farmers, including passion farmers, in the country are smallholder farmers from low-income, they do not have the sufficient information and means to combat challenges. While, passion fruits have the potential to improve the-being of these farmers as they have a short maturity period and high value , without the required knowledge about the health of their crops, cannot intervene promptly to turn the situation around. For this work, we have partnered with the Uganda National Crop Research (NaCRRI) to develop a dataset of expertly labelled passion fruit leaves and fruits, both diseased and healthy. We have made use of their service to collect images from 5 districts in Uganda, With the dataset in place, we are employing state-of-the-art techniques in learning, and specifically deep learning, techniques at scale for detection and classification to correctly determine the health status of fruit plants and provide an accurate diagnosis for positive.This work focuses on two major diseases woodiness (viral) and brown (fungal) diseases.