Optimizing potato leaf disease recognition: Insights DENSE-NET-121 and Gaussian elimination filter fusion
Ensuring a sustainable global food security status which necessitated by achieving an equilibrium state between the anticipated and significant rise in the global population and the projected agricultural output which is essential for their food adequacy. The absence of such a harmonious balance may...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S240584402500698X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Ensuring a sustainable global food security status which necessitated by achieving an equilibrium state between the anticipated and significant rise in the global population and the projected agricultural output which is essential for their food adequacy. The absence of such a harmonious balance may be a contributing factor to the emergence of food crises worldwide. Hence, it is imperative to proactively address and mitigate both direct and indirect factors that could potentially lead to this agricultural yield imbalance. Facilitating optimal plant growth and implementing effective measures against diseases play a fundamental role in meeting the global demand for food in terms of both quality and quantity. This article offered a hybrid model based on Deep learning called DENSE-NET-121 with 2D Gaussian elimination filters that can be effective deep learning tools to increase potato yield by early detection of the leaf. Three types of potato leaf classes called Early Blight, Healthy, and Late Blight are incorporated by Dataset which has been taken from the kaggle repository. Considering this proposed model, state-of-the-art DENSE-NET-121 has produced an unprecedented training and validation accuracy 0.9908, 0.9837 respectively furthermore model also produced extremely low training and validation loss 0.0683, 0.0796 and an error rate below then 0.1 as well. Furthermore model produced average Precision, and recall, 0.98, 0.96, and 0.97 respectively. |
|---|---|
| ISSN: | 2405-8440 |