Devi Priya, Devisurya, Dharani, Geetha, Kiruthika
Cotton leaf disease detection using Faster R-CNN with Region Proposal Network
Indian agriculture consists of cultivating many crops and 70% of Indian population depend on it either for food or for commercial purpose. India is one among the largest producers of cotton in the world. But the production gets affected due to various reasons like attacks in different parts of the plant by pests, insects, nutritional deficiencies, climatic conditions etc. Detection of leaf diseases is a major problem which needs to be addressed during all stages of plant growth using computational intelligent techniques. After detection, remedy for the diseases need to be identified and suggested so that farmers can take appropriate actions.This paper provides a solution to this problem by detecting and analyzing the diseases in cotton plant and suggests suitable remedies for that disease through deep learning. Training of models was performed with the database of over 4,000 images. It uses Faster R-CNN with Region Proposal Network (RPN)which is an extension of Fast R-CNN for detection of diseases.Integrating RPN with faster R-CNN reduces the running time and enable cost-free region proposals. It has an average accuracy of 96% in identifying the disease.
Deep Learning, Cotton leaf diseases, Faster R-CNN, Region Proposal Network
Cite this paper
Devi Priya, Devisurya, Dharani, Geetha, Kiruthika. (2021) Cotton leaf disease detection using Faster R-CNN with Region Proposal Network. International Journal of Biology and Biomedicine, 6, 23-35