CROP DISEASE DETECTION USING CNN
Abstract & Details
Research Area
COMPUTER SCIENCE AND ENGINEERING
Keywords
Crop disease
Deep learning
Transfer Learning
MobileNet
InceptionV3
Image classification.
Abstract
For smallholder farmers, plant diseases are a constant problem that put their livelihood and food security at danger. The prospect for picture categorization in agriculture has been made possible by the current revolution in smartphone adoption and computer vision models. State-of-the-art in image recognition, convolutional neural networks (CNNs) have the capacity to quickly and accurately diagnose a condition. The effectiveness of a pre-trained ResNet34 model for spotting crop disease is examined in this research. The created model can identify seven plant illnesses from healthy leaf tissue and is executed as a web application. For the reason of validating and training the model, a dataset of 8,685 greenery images that were taken in a organised setting is established. The planned may reach an exactness of 97.2%, according to validation data. on top of an F1 total of as a minimum 96.5%. This shows that CNNs can classify plant illnesses technically, and it points the way to AI results for small-scale farmers. Crop illnesses have grown significantly in recent years as a outcome of severe climate changes and a lack of immunity in plants. This results in extensive agricultural destruction,reduces crop production, which eventually costs farmers money. Identification and treatment of the illness have convert a significant difficulty as a outcome of the rapid expansion of a variability of diseases and the farmer's adequate knowledge. The leaves have a similar texture and appearance, which are characteristics for identifying the disease kind. Hence, deep learning combined with computer vision offers a solution to this problem.
License
This work is licensed under a Creative
Commons
Attribution-ShareAlike 4.0 International License.
Author Information
| # | Name | Institute / Affiliation |
|---|---|---|
| 1 | E.Angel Anna Prathiba | ERODE SENGUNTHAR ENGINEERING COLLEGE |
| 2 | S.Gobika | ERODE SENGUNTHAR ENGINEERING COLLEGE |
| 3 | S.Kanishka | ERODE SENGUNTHAR ENGINEERING COLLEGE |
| 4 | S.Mohanapriya | ERODE SENGUNTHAR ENGINEERING COLLEGE |
How to Cite
Use the following formats to cite this article in your research.
APA Style
Prathiba, E.Angel Anna, S.Gobika, S.Kanishka, & S.Mohanapriya (2023). CROP DISEASE DETECTION USING CNN. International Journal of Advance Research and Innovative Ideas In Education, 9(2), 402-410.
MLA Style
Prathiba, E.Angel Anna, et al. "CROP DISEASE DETECTION USING CNN." International Journal of Advance Research and Innovative Ideas In Education, vol. 9, no. 2, 2023, pp. 402-410.
IEEE Style
E.Angel Anna Prathiba, S.Gobika, S.Kanishka, and S.Mohanapriya, "CROP DISEASE DETECTION USING CNN," International Journal of Advance Research and Innovative Ideas In Education, vol. 9, no. 2, pp. 402-410, 2023.
Vancouver Style
Prathiba E.Angel Anna, S.Gobika, S.Kanishka, S.Mohanapriya. CROP DISEASE DETECTION USING CNN. International Journal of Advance Research and Innovative Ideas In Education. 2023;9(2):402-410.
Harvard Style
Prathiba, E.Angel Anna, S.Gobika, S.Kanishka, & S.Mohanapriya (2023) 'CROP DISEASE DETECTION USING CNN', International Journal of Advance Research and Innovative Ideas In Education, 9(2), pp. 402-410.
Chicago Style
Prathiba, E.Angel Anna, et al. "CROP DISEASE DETECTION USING CNN." International Journal of Advance Research and Innovative Ideas In Education 9, no. 2 (2023): 402-410.
Turabian Style
Prathiba, E.Angel Anna, et al. "CROP DISEASE DETECTION USING CNN." International Journal of Advance Research and Innovative Ideas In Education 9, no. 2 (2023): 402-410.
Related Research
EduQuest AI: A Gamified Learning Platform for Interactive and Personalized Digital Education
Download PDF
Distributed Real-Time Stream Analytics and Ingestion Engine for High-Velocity Big Data Architectures
Download PDF