A Detection and Classification of Cotton Leaf Disease Using a Lightweight CNN Architecture

The classification of diseases that affect the cotton leaf can boost the amount of cotton produced. Deep learning is becoming recognized as an effective strategy in a variety of fields and has been the subject of a significant number of research projects in the agricultural industry. These investigations have focused on the real-time detection of diseases in cotton leaf samples. Although Convolution Neural Networks have been a significant contributor to the categorization of plant diseases and the identification of those diseases, there is still much more work to be done to assist farmers and pathologists in accurately detecting and categorizing diseases. Manually inspecting crops for disease requires a significant investment of time and money and is a stressful process. An erroneous diagnosis can lead to incorrect conclusions, treatment that is ineffective, and increased costs. In this paper, it is proposed to train a deep learning Faster R-CNN model using the cotton crop leaf dataset in order to identify and classify leaf diseases. The Plant Village dataset, along with VGG-16, InceptionV1, and V2, is used as a benchmark in the process of determining which feature extractor is the most effective.