Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification
Dragonfly classification is crucial for biodiversity conservation. Traditional taxonomic approaches require extensive training and experience, limiting their efficiency. Computer vision offers promising solutions for dragonfly taxonomy. In this study, we adapt the face recognition algorithms for the...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7598 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319991624597504 |
|---|---|
| author | Zhong Li Shaoyan Pu Jingsheng Lu Ruibin Song Haomiao Zhang Xuemei Lu Yanan Wang |
| author_facet | Zhong Li Shaoyan Pu Jingsheng Lu Ruibin Song Haomiao Zhang Xuemei Lu Yanan Wang |
| author_sort | Zhong Li |
| collection | DOAJ |
| description | Dragonfly classification is crucial for biodiversity conservation. Traditional taxonomic approaches require extensive training and experience, limiting their efficiency. Computer vision offers promising solutions for dragonfly taxonomy. In this study, we adapt the face recognition algorithms for the classification of dragonfly species, achieving efficient recognition of categories with extremely small differences between classes. Meanwhile, this method can also reclassify data that were incorrectly labeled. The model is mainly built based on the classic face recognition algorithm (ResNet50+ArcFace), and ResNet50 is used as the comparison algorithm for model performance. Three datasets with different inter-class data distributions were constructed based on two dragonfly image data sources: Data1, Data2 and Data3. Ultimately, our model achieved Top1 accuracy rates of 94.3%, 85.7%, and 90.2% on the three datasets, surpassing ResNet50 by 0.6, 1.5, and 1.6 percentage points, respectively. Under the confidence thresholds of 0.7, 0.8, 0.9, and 0.95, the Top1 accuracy rates on the three datasets were 96.0%, 97.4%, 98.7%, and 99.2%, respectively. In conclusion, our research provides a novel approach for species classification. Furthermore, it can calculate the similarity between classes while predicting categories, thereby offering the potential to provide technical support for biological research on the similarity between species. |
| format | Article |
| id | doaj-art-09cdcb6a2f0d459b872913f942a9085b |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-09cdcb6a2f0d459b872913f942a9085b2025-08-20T03:50:16ZengMDPI AGApplied Sciences2076-34172025-07-011513759810.3390/app15137598Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly ClassificationZhong Li0Shaoyan Pu1Jingsheng Lu2Ruibin Song3Haomiao Zhang4Xuemei Lu5Yanan Wang6Key Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKey Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKey Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKunming Zoological Museum of Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKey Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKey Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaKey Laboratory of Genetic Evolution & Animal Models, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming 650201, ChinaDragonfly classification is crucial for biodiversity conservation. Traditional taxonomic approaches require extensive training and experience, limiting their efficiency. Computer vision offers promising solutions for dragonfly taxonomy. In this study, we adapt the face recognition algorithms for the classification of dragonfly species, achieving efficient recognition of categories with extremely small differences between classes. Meanwhile, this method can also reclassify data that were incorrectly labeled. The model is mainly built based on the classic face recognition algorithm (ResNet50+ArcFace), and ResNet50 is used as the comparison algorithm for model performance. Three datasets with different inter-class data distributions were constructed based on two dragonfly image data sources: Data1, Data2 and Data3. Ultimately, our model achieved Top1 accuracy rates of 94.3%, 85.7%, and 90.2% on the three datasets, surpassing ResNet50 by 0.6, 1.5, and 1.6 percentage points, respectively. Under the confidence thresholds of 0.7, 0.8, 0.9, and 0.95, the Top1 accuracy rates on the three datasets were 96.0%, 97.4%, 98.7%, and 99.2%, respectively. In conclusion, our research provides a novel approach for species classification. Furthermore, it can calculate the similarity between classes while predicting categories, thereby offering the potential to provide technical support for biological research on the similarity between species.https://www.mdpi.com/2076-3417/15/13/7598dragonflyclassificationface recognitionArcFaceResNet50 |
| spellingShingle | Zhong Li Shaoyan Pu Jingsheng Lu Ruibin Song Haomiao Zhang Xuemei Lu Yanan Wang Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification Applied Sciences dragonfly classification face recognition ArcFace ResNet50 |
| title | Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification |
| title_full | Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification |
| title_fullStr | Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification |
| title_full_unstemmed | Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification |
| title_short | Transferring Face Recognition Techniques to Entomology: An ArcFace and ResNet Approach for Improving Dragonfly Classification |
| title_sort | transferring face recognition techniques to entomology an arcface and resnet approach for improving dragonfly classification |
| topic | dragonfly classification face recognition ArcFace ResNet50 |
| url | https://www.mdpi.com/2076-3417/15/13/7598 |
| work_keys_str_mv | AT zhongli transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT shaoyanpu transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT jingshenglu transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT ruibinsong transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT haomiaozhang transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT xuemeilu transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification AT yananwang transferringfacerecognitiontechniquestoentomologyanarcfaceandresnetapproachforimprovingdragonflyclassification |