Deep Learning based Mango Leaf Disease Detection for Classifying and Evaluating Mango Leaf Diseases

Abstract

Mango is one of the important commercial crop in the world. It provides nutritional and financial support to human life. Different diseases of leaves impact the health of the mango crops. The early and proper pest control measurement can prevent large output losses. We propose an automated inspection and classification of disease-affected mango leaves that uses Deep Learning (DL) model. Our DL model-empowered Convolutional Neural Network (CNN) architecture is trained with an extensive image dataset of mango leaves portraying a variety of disease indications at both low and high-resolution images. The objective is to be able to identify accurately the disease type on mango leaves including Bacterial Canker, Powdery mildew, Anthracnose, Gall midge, and Sooty mould. Crops can develop gradual immunity with reasonable pest control and can purposively shaped them against constantly evolving environment. The proposed system will be effective and it will definitely prove a facile system to be used as a key component of a novel precision agriculture system as will be presented in our future work. The performance of the proposed system is augmented through the utilization of transfer learning techniques and pre-trained models, including VGG-16, MobileNet, Googlenet, YoloV8, and EfficientNet. These Deep Learning models not only offer an accurate and efficient approach for classifying diseases in mango leaves but also provide valuable insights into the severity of the identified diseases. Utilizing this information to support farmers and agricultural professionals in making informed decisions pertaining to disease management and treatment strategies can significantly contribute to the sustainable growth of mango crops. The development and implementation of such automated technologies have the potential to revolutionize the monitoring of mango crop health, enabling early disease detection and enhancing crop yields.