Have a personal or library account? Click to login

Plant Parasitic Nematode Identification in Complex Samples with Deep Learning

Journal of Nematology
Volume 55 (2023): Issue 1 (February 2023)
By:
Open Access
|Oct 2023

Figures & Tables

Figure 1:

Representative sample image of nematodes extracted from soil samples sent to NDL. Colored boxes indicate annotations of plant parasitic nematode heads.
Representative sample image of nematodes extracted from soil samples sent to NDL. Colored boxes indicate annotations of plant parasitic nematode heads.

Model and corresponding maximum mAP_

ModelMax MAP_0.5
YOLOv5x Baseline0.787
CenterNet HourGlass104 512×5120.6929
EfficientDet D1 640×6400.6489
SSD ResNet50 V1 FPN 640×6400.6439

Modified YOLOv5 models with precision and recall_

ModelMax MAP_0.5Max PrecisionMax Recall
YOLOv5x Baseline0.7870.8360.772
YOLOv5x-Bi-FPN0.7910.8510.753
YOLO-v5x Densenet0.7690.8310.782
YOLOv5x-Deeper0.7790.8310.774
DOI: https://doi.org/10.2478/jofnem-2023-0045 | Journal eISSN: 2640-396X | Journal ISSN: 0022-300X
Journal RSS Feed
Language: English
Submitted on: Jul 7, 2023
Published on: Oct 16, 2023
Published by: Society of Nematologists, Inc.
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
detection,
diagnosis,
identification,
deep learning,
method,
technique
Related subjects:
Life sciences,
Life sciences, other

© 2023 Sahil Agarwal, Zachary C. Curran, Guohao Yu, Shova Mishra, Anil Baniya, Mesfin Bogale, Kody Hughes, Oscar Salichs, Alina Zare, Zhe Jiang, Peter DiGennaro, published by Society of Nematologists, Inc.
This work is licensed under the Creative Commons Attribution 4.0 License.

Previous articleVolume 55 (2023): Issue 1 (February 2023)Next article