A Heuristic Approaches towards Citrus Fruit and Leaves Disease Detection Using Machine Learning

Citrus fruit and foliage recognition using machine learning techniques is an emerging frontier in agricultural technology. The practical utilization using deep learning algorithms is investigated in the present paper that automated recognition and analysis of citrus fruits and leaves in agricultural sector. The primary focus is on utilizing enhanced Convolutional Neural Networks (CNNs) model to accomplish tasks of object detection. The susceptibility of citrus plants to diseases underscores the importance of effective disease management strategies. Citrus trees and their fruits can become infected with a variety of pathogens, including bacteria, viruses, and fungi. Early identification of ailments in citrus plants aids in thwarting their spread within orchards, thereby reducing financial setbacks for farmers. The dataset contains images of citrus fruits and leaves depicting both healthy specimens and plants afflicted with diseases such as Black spot, Canker, Scab, Greening, and Melanoses. We employed deep learning models including CNN, Efficient Net, VGG16, and Res Net. The primary focus was on developing our model tailored to distinguish between healthy citrus fruits and leaves and those affected by prevalent diseases such as black spot, canker, scab, greening, and melanoses. According to the experimental results, the Model excels in a variety of evaluation metrics compared to its competitors. Boasting a training accuracy of 99.66 and test accuracy of 84.40 percent and is invaluable decision support resource for farmers diagnosing citrus fruit/leaf infections.