YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano
When it comes to growing lettuce, specific nutrients play vital roles in its growth and development. These essential nutrients include full nutrients (FN), nitrogen (N), phosphorus (P), and potassium (K). Insufficient or excess levels of these nutrients can have negative effects on lettuce plants, r...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/58/1/31 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850261444359094272 |
|---|---|
| author | Jordane Sikati Joseph Christian Nouaze |
| author_facet | Jordane Sikati Joseph Christian Nouaze |
| author_sort | Jordane Sikati |
| collection | DOAJ |
| description | When it comes to growing lettuce, specific nutrients play vital roles in its growth and development. These essential nutrients include full nutrients (FN), nitrogen (N), phosphorus (P), and potassium (K). Insufficient or excess levels of these nutrients can have negative effects on lettuce plants, resulting in various deficiencies that can be observed in the leaves. To better understand and identify these deficiencies, a deep learning approach is employed to improve these tasks. For this study, YOLOv8 Nano, a lightweight deep network, is chosen to classify the observed deficiencies in lettuce leaves. Several enhancements to the baseline algorithm are made, the backbone is replaced with VGG16 to improve the classification accuracy, and depthwise convolution is incorporated into it to enrich the features while keeping the head unchanged. The proposed network, incorporating these modifications, achieved superior classification results with a top-1 accuracy of 99%. This method outperformed other state-of-the-art classification methods, demonstrating the effectiveness of the approach in identifying lettuce deficiencies. The objective of this research was to improve the baseline algorithm to complete the classification task with a top-1 accuracy above 85%, a FLOP inferior to 10G, and classification latency below 170 ms per image. |
| format | Article |
| id | doaj-art-ece2c31e8a0249ad864e062ae3856f93 |
| institution | OA Journals |
| issn | 2673-4591 |
| language | English |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj-art-ece2c31e8a0249ad864e062ae3856f932025-08-20T01:55:26ZengMDPI AGEngineering Proceedings2673-45912023-11-015813110.3390/ecsa-10-16256YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 NanoJordane Sikati0Joseph Christian Nouaze1R&D Center, Guinee Biomedical Maintenance, Bentourayah, Conakry 3137, GuineaDepartment of Electronics Engineering, Pusan National University, Busan 46241, Republic of KoreaWhen it comes to growing lettuce, specific nutrients play vital roles in its growth and development. These essential nutrients include full nutrients (FN), nitrogen (N), phosphorus (P), and potassium (K). Insufficient or excess levels of these nutrients can have negative effects on lettuce plants, resulting in various deficiencies that can be observed in the leaves. To better understand and identify these deficiencies, a deep learning approach is employed to improve these tasks. For this study, YOLOv8 Nano, a lightweight deep network, is chosen to classify the observed deficiencies in lettuce leaves. Several enhancements to the baseline algorithm are made, the backbone is replaced with VGG16 to improve the classification accuracy, and depthwise convolution is incorporated into it to enrich the features while keeping the head unchanged. The proposed network, incorporating these modifications, achieved superior classification results with a top-1 accuracy of 99%. This method outperformed other state-of-the-art classification methods, demonstrating the effectiveness of the approach in identifying lettuce deficiencies. The objective of this research was to improve the baseline algorithm to complete the classification task with a top-1 accuracy above 85%, a FLOP inferior to 10G, and classification latency below 170 ms per image.https://www.mdpi.com/2673-4591/58/1/31lettuce nutrient deficiencyclassificationdeep learningYOLOV8 Nano |
| spellingShingle | Jordane Sikati Joseph Christian Nouaze YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano Engineering Proceedings lettuce nutrient deficiency classification deep learning YOLOV8 Nano |
| title | YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano |
| title_full | YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano |
| title_fullStr | YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano |
| title_full_unstemmed | YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano |
| title_short | YOLO-NPK: A Lightweight Deep Network for Lettuce Nutrient Deficiency Classification Based on Improved YOLOv8 Nano |
| title_sort | yolo npk a lightweight deep network for lettuce nutrient deficiency classification based on improved yolov8 nano |
| topic | lettuce nutrient deficiency classification deep learning YOLOV8 Nano |
| url | https://www.mdpi.com/2673-4591/58/1/31 |
| work_keys_str_mv | AT jordanesikati yolonpkalightweightdeepnetworkforlettucenutrientdeficiencyclassificationbasedonimprovedyolov8nano AT josephchristiannouaze yolonpkalightweightdeepnetworkforlettucenutrientdeficiencyclassificationbasedonimprovedyolov8nano |