Deep learning model for detection and classification of banana diseases based on leaf images

Abstract

Fungal diseases are among the main reasons for low productivity in banana farming. Early detection of fungal diseases is essential. One possible approach is using machine vision. Due to its high accuracy, deep learning is the most widely used algorithm in machine vision for many solutions. Its ability to model the data into multiple levels of abstraction makes it suitable for many agricultural solutions. However, deep learning requires a high computational resource, challenging many agricultural solutions implemented on low-computing devices. This study proposes lightweight deep-learning algorithms for detecting and classifying banana diseases based on leaf images. The study used a dataset of images representing three classes: black Sigatoka disease, fusarium wilt race 1 disease, and healthy tree. The algorithms used are mobileNetv2, mobileNetv3-small, shuffleNetv2, and squeezeNet. The results showed that squeezeNet outperforms all other models with 97.12% accuracy, 97.14% precision, 97.1% recall, and 97.12% f1-score. MobileNetv3-small results in the heaviest model, which is 14 MB, but it has the shortest training time of 2.465 minutes. MobileNetv2 results in the lightest model, 2.51 MB, while squeezeNet has the longest training time, 14.76 minutes. Overall, the lightweight deep learning algorithms performed well, and this method can be used for other banana diseases and abnormalities.