Hemalatha, NK and Brunda, RN and Prakruthi, GS and Prabhu, BVB and Shukla, A and Narasipura, OSJ (2022) Sugarcane leaf disease detection through deep learning. [Book Chapter]
Full text not available from this repository.Abstract
Plant diseases have always been a challenge to plant growth and crop production in several parts of the world and adversely impact the availability of food to humans. Sugarcane cultivation is the most organized division of farming. Due to the favorable conditions for its growth, it is the first choice of cultivation for farmers. It is directly linked to the sugar industry and plays a major role in the economy of several countries, like Brazil, India, China, and so on. Sugarcane crop holds the largest production value among all the commercially grown crops. Contradictorily, there are multifarious diseases that affect the crop in yield and quality. Some of these are detected by farmers when they visually inspect the leaves. However, most of the diseases go undetected leading to huge losses to farmers. Therefore, it is crucial to identify the type of infestation to aid in controlling its damage. To address this issue, we propose a deep learning neural network architecture in which the type of disease afflicting the sugarcane crop is predicted by training the model on images of affected leaves. The following diseases are detected: rust spots, yellow leaf disease, Helmanthospura leaf spot, Cercospora leaf spot, and red rot. The approach involves a convolutional neural network that is trained as an image classifier with around 3000 leaf images. The model is tested for about 1000 images. The proposed model has achieved 96% accuracy. An Android application is developed as a user interface for this model. Using this application, farmers can capture the images through a phone camera or select images from the gallery. In the server, the image is fed to the model, which will process the image and predict the disease. This prediction will be displayed on the farmer’s phone in the application, so that they can take the necessary precautionary measures to mitigate losses. © 2022 Elsevier Inc. All rights reserved.
| Item Type: | Book Chapter |
|---|---|
| Publication: | Deep Learning for Sustainable Agriculture |
| Publisher: | Elsevier |
| Additional Information: | The copyright for this article belongs to Elsevier |
| Keywords: | Android application; Cercospora leaf spot; Convolutional neural network; Deep learning; Helmanthospura leaf spot; Plant disease detection; Red rot; Rust spots; Sugarcane disease detection; Yellow leaf disease |
| Department/Centre: | Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering) |
| Date Deposited: | 27 May 2022 05:46 |
| Last Modified: | 31 May 2022 04:57 |
| URI: | https://eprints.iisc.ac.in/id/eprint/72755 |
Actions (login required)
 |
View Item |
