LSR-YOLO: A high-precision lightweight model for sheep face recognition on mobile end
Open Science Framework, 2023
Online
unknown
Zugriff:
Compared with YOLOv5s, the FLOPs of the LSR-YOLO decreased by 25.5%, and the model parameters decreased by 33.4%. The weight of LSR-YOLO is only 9.5MB. The experimental results demonstrate that the LSR-YOLO achieved the best performance on sheep face dataset, and the mAP@0.5 reached 97.8%. The lightweight recognition model proposed in the study contributes to the development of mobile end recognition systems and provides technical support for sheep facial biometric recognition.
Titel: |
LSR-YOLO: A high-precision lightweight model for sheep face recognition on mobile end
|
---|---|
Autor/in / Beteiligte Person: | Zhang, Xiwen |
Link: | |
Veröffentlichung: | Open Science Framework, 2023 |
Medientyp: | unknown |
DOI: | 10.17605/osf.io/5ynhw |
Schlagwort: |
|
Sonstiges: |
|