Coffee Leaf Plant Disease Identification through Image Processing and Machine-Learning Techniques in Ethiopia.

Abstract

Abstract—Coffee plants are woody evergreens that can reach a height of up to ten meter’s in the wild with the fruit of coffee beans, which are the seeds that produce the majority of the world’s coffee. This study focuses on a variety of Arabica Coffee leaf diseases that occurs frequently in Ethiopia. The diseases which occurred primarily are Miner coffee leaf disease (MCLD), Rust coffee leaf disease (RCLD), Cercospora coffee leaf disease (CCLD), and Phoma coffee leaf disease (PCLD). The study focuses on the identification of those four a variety of diseases through image processing as well as machine learning mechanisms through Transfer learning and convolution neural network (CNN) architectures through the feed-forward model, resnet50 model, inceptionV3 model, and deep learning model through tenser flow, which are the most popular models to detect various plant diseases with high Accuracy. All the pictures used for this study were captured from the whole state of Ethiopia in every place where coffee plant exists. The total number of data sets currently used is 58,546 with 80 percent being put to use for training, while the rest 20 percent were employed for testing, with a 99.9%, 98.5%, 99%, and 99% respectively with a total success rate in classification accuracy and 99.8%, 98%, 99% and 99.7% respectively with total success rate in confusion matrix accuracy. So there is excellent performance in inferences.