Optimizing MobileNetV3 Using Particle Swarm Optimization Algorithm for the Recognition of Bean Leaf Diseases

Abstract

Crops play a vital role in human nutrition and overall well-being. Beans are an economically significant type of crops that not only provide a rich source of protein but also offers substantial health benefits. However, beans are susceptible to bacterial and fungal infections. If left uncontrolled, these diseases could result in severe consequences. Diagnosis of the affected leaves can be done by plant pathologists, which is not readily available in local and remote areas. Using deep learning algorithms, an accurate classification of bean leaf diseases can offset this problem from an early stage. This research introduces a framework for optimizing MobileNetV3 using Particle Swarm Optimization that can accurately identify healthy or diseased bean leaves from images captured in real-world conditions. With having only 2.9M parameters, the best model achieved a high degree of accuracy at 98.44% on unseen data, outperforming the models proposed by other researchers on the same classification task. Results suggest that the model can be adopted in the field to increase the efficiency in the early identification of bean leaf diseases. Lastly, the same methodology can also be applied in solving plant leaf diseases from other economically significant crops.