التفاصيل البيبلوغرافية
| العنوان: |
Early Detection of Powdery Mildew in Faba Beans. |
| المؤلفون: |
A, Mahalakshmi, M, Harini, A, Madumitha, V, Nivetha |
| المصدر: |
Grenze International Journal of Engineering & Technology (GIJET); Jan Part 1, Vol. 10 Issue 1, p209-214, 6p |
| مصطلحات موضوعية: |
MACHINE learning, POWDERY mildew diseases, AGRICULTURAL productivity, IMAGE segmentation, FAVA bean, DEEP learning, RANDOM forest algorithms |
| مستخلص: |
Powdery mildew, caused by the fungal pathogen Erysiphe, is a widespread and economically important disease affecting broad beans (Viciafaba). This paper addresses the detection and treatment of powdery mildew in fava beans, covering various aspects such as symptomology, pathogen identification, disease surveillance techniques, and integrated management strategies. In this paper, we propose a mathematical model for broad bean powdery mildew detection and deep learning-based detection that improves accuracy and training efficiency. First, a conversion from the RGB format to his HSV format is performed and image segmentation is done. Then apply a random forest classifier to derive the results. The segmented leaves are then sent into a transfer learning model that has been trained on a dataset of sick leaves on a simple background. Additionally, the model is examined to identify the developmental stage of the Erysiphe family. By understanding the complexity of this disease, farmers and researchers can improve disease management and promote sustainable broad bean production. Therefore, for intelligent agriculture, environmental preservation, and agricultural productivity, the deep learning algorithms proposed in this article are crucial. [ABSTRACT FROM AUTHOR] |
|
Copyright of Grenze International Journal of Engineering & Technology (GIJET) is the property of GRENZE Scientific Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
