Deep Metric Learning-Based Strawberry Disease Detection With Unknowns
There has been substantial research that has achieved significant advancements in plant disease detection based on deep object detection models. However, with unknown diseases, it is difficult to find a practical solution for plant disease detection. This study proposes a simple but effective strawb...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.891785/full |
| _version_ | 1818117421400064000 |
|---|---|
| author | Jie You Kan Jiang Joonwhoan Lee |
| author_facet | Jie You Kan Jiang Joonwhoan Lee |
| author_sort | Jie You |
| collection | DOAJ |
| description | There has been substantial research that has achieved significant advancements in plant disease detection based on deep object detection models. However, with unknown diseases, it is difficult to find a practical solution for plant disease detection. This study proposes a simple but effective strawberry disease detection scheme with unknown diseases that can provide applicable performance in the real field. In the proposed scheme, the known strawberry diseases are detected with deep metric learning (DML)-based classifiers along with the unknown diseases that have certain symptoms. The pipeline of our proposed scheme consists of two stages: the first is object detection with known disease classes, while the second is a DML-based post-filtering stage. The second stage has two different types of classifiers: one is softmax classifiers that are only for known diseases and the K-nearest neighbor (K-NN) classifier for both known and unknown diseases. In the training of the first stage and the DML-based softmax classifier, we only use the known samples of the strawberry disease. Then, we include the known (a priori) and the known unknown training samples to construct the K-NN classifier. The final decisions regarding known diseases are made from the combined results of the two classifiers, while unknowns are detected from the K-NN classifier. The experimental results show that the DML-based post-filter is effective at improving the performance of known disease detection in terms of mAP. Furthermore, the separate DML-based K-NN classifier provides high recall and precision for known and unknown diseases and achieve 97.8% accuracy, meaning it could be exploited as a Region of Interest (ROI) classifier. For the real field data, the proposed scheme achieves a high mAP of 93.7% to detect known classes of strawberry disease, and it also achieves reasonable results for unknowns. This implies that the proposed scheme can be applied to identify disease-like symptoms caused by real known and unknown diseases or disorders for any kind of plant. |
| first_indexed | 2024-12-11T04:38:08Z |
| format | Article |
| id | doaj.art-c7ae8ad57e71499393138d24705a2d07 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-12-11T04:38:08Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-c7ae8ad57e71499393138d24705a2d072022-12-22T01:20:42ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-07-011310.3389/fpls.2022.891785891785Deep Metric Learning-Based Strawberry Disease Detection With UnknownsJie YouKan JiangJoonwhoan LeeThere has been substantial research that has achieved significant advancements in plant disease detection based on deep object detection models. However, with unknown diseases, it is difficult to find a practical solution for plant disease detection. This study proposes a simple but effective strawberry disease detection scheme with unknown diseases that can provide applicable performance in the real field. In the proposed scheme, the known strawberry diseases are detected with deep metric learning (DML)-based classifiers along with the unknown diseases that have certain symptoms. The pipeline of our proposed scheme consists of two stages: the first is object detection with known disease classes, while the second is a DML-based post-filtering stage. The second stage has two different types of classifiers: one is softmax classifiers that are only for known diseases and the K-nearest neighbor (K-NN) classifier for both known and unknown diseases. In the training of the first stage and the DML-based softmax classifier, we only use the known samples of the strawberry disease. Then, we include the known (a priori) and the known unknown training samples to construct the K-NN classifier. The final decisions regarding known diseases are made from the combined results of the two classifiers, while unknowns are detected from the K-NN classifier. The experimental results show that the DML-based post-filter is effective at improving the performance of known disease detection in terms of mAP. Furthermore, the separate DML-based K-NN classifier provides high recall and precision for known and unknown diseases and achieve 97.8% accuracy, meaning it could be exploited as a Region of Interest (ROI) classifier. For the real field data, the proposed scheme achieves a high mAP of 93.7% to detect known classes of strawberry disease, and it also achieves reasonable results for unknowns. This implies that the proposed scheme can be applied to identify disease-like symptoms caused by real known and unknown diseases or disorders for any kind of plant.https://www.frontiersin.org/articles/10.3389/fpls.2022.891785/fulldeep metric learningunknown disease detectionstrawberry disease detectionK-nearest neighboropen set recognition |
| spellingShingle | Jie You Kan Jiang Joonwhoan Lee Deep Metric Learning-Based Strawberry Disease Detection With Unknowns Frontiers in Plant Science deep metric learning unknown disease detection strawberry disease detection K-nearest neighbor open set recognition |
| title | Deep Metric Learning-Based Strawberry Disease Detection With Unknowns |
| title_full | Deep Metric Learning-Based Strawberry Disease Detection With Unknowns |
| title_fullStr | Deep Metric Learning-Based Strawberry Disease Detection With Unknowns |
| title_full_unstemmed | Deep Metric Learning-Based Strawberry Disease Detection With Unknowns |
| title_short | Deep Metric Learning-Based Strawberry Disease Detection With Unknowns |
| title_sort | deep metric learning based strawberry disease detection with unknowns |
| topic | deep metric learning unknown disease detection strawberry disease detection K-nearest neighbor open set recognition |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.891785/full |
| work_keys_str_mv | AT jieyou deepmetriclearningbasedstrawberrydiseasedetectionwithunknowns AT kanjiang deepmetriclearningbasedstrawberrydiseasedetectionwithunknowns AT joonwhoanlee deepmetriclearningbasedstrawberrydiseasedetectionwithunknowns |