Bidirectional Encoder representation from Image Transformers for recognizing sunflower diseases from photographs
This paper proposes a modern system for recognizing sunflower diseases based on Bidirectional Encoder representation from Image Transformers (BEIT). The proposed system is capable of recognizing various sunflower diseases with high accuracy. The presented research results demonstrate the advantages...
保存先:
| 主要な著者: | , , , , , , , |
|---|---|
| フォーマット: | Статья |
| 言語: | English |
| 出版事項: |
Institution of Russian Academy of Sciences
2025
|
| 主題: | |
| オンライン･アクセス: | https://dspace.ncfu.ru/handle/123456789/30407 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | This paper proposes a modern system for recognizing sunflower diseases based on Bidirectional Encoder representation from Image Transformers (BEIT). The proposed system is capable of recognizing various sunflower diseases with high accuracy. The presented research results demonstrate the advantages of the proposed system compared to known methods and contempo-rary neural networks. The proposed visual diagnostic system for sunflower diseases achieved 99.57 % accuracy on the sunflower disease dataset, which is higher than that of known methods. The approach described in the work can serve as an auxiliary tool for farmers, assisting them in promptly identifying diseases and pests and taking timely measures to treat plants. This, in turn, helps in preserving and enhancing the yield. This work can have a significant impact on the de-velopment of agriculture and the fight against the global food shortage problem. |
|---|