EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Aging-Invariant Sheep Face Recognition Through Feature Decoupling

Suhui Liu, Chuanzhong Xuan iD, Zhaohui Tang, Guangpu Wang, Xinyu Gao iD, Zhipan Wang iD

Animals · 06.08.2025 · 15 (15) · 2299

DOI: 10.3390/ani15152299 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Animals, online erschienen am 06.08.2025. Verfasst von Suhui Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China, The First Class Disciplines Research Special Project, The Fundamental Research Funds for Inner Mongolia Directly Affiliated Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precise recognition of individual ovine specimens plays a pivotal role in implementing smart agricultural platforms and optimizing herd management systems. With the development of deep learning technology, sheep face recognition provides an efficient and contactless solution for individual sheep identification. However, with the growth of sheep, their facial features keep changing, which poses challenges for existing sheep face recognition models to maintain accuracy across the dynamic changes in facial features over time, making it difficult to meet practical needs. To address this limitation, we propose the lifelong biometric learning of the sheep face network (LBL-SheepNet), a feature decoupling network designed for continuous adaptation to ovine facial changes, and constructed a dataset of 31,200 images from 55 sheep tracked monthly from 1 to 12 months of age. The LBL-SheepNet model addresses dynamic variations in facial features during sheep growth through a multi-module architectural framework. Firstly, a Squeeze-and-Excitation (SE) module enhances discriminative feature representation through adaptive channel-wise recalibration. Then, a nonlinear feature decoupling module employs a hybrid channel-batch attention mechanism to separate age-related features from identity-specific characteristics. Finally, a correlation analysis module utilizes adversarial learning to suppress age-biased feature interference, ensuring focus on age-invariant identifiers. Experimental results demonstrate that LBL-SheepNet achieves 95.5% identification accuracy and 95.3% average precision on the sheep face dataset. This study introduces a lifelong biometric learning (LBL) mechanism to mitigate recognition accuracy degradation caused by dynamic facial feature variations in growing sheep. By designing a feature decoupling network integrated with adversarial age-invariant learning, the proposed method addresses the performance limitations of existing models in long-term individual identification.

Schlagwörter

Stichwörter der Autor:innen

agricultural engineeringbiometric recognitiondeep learningfeature decouplingsheep facial features

Autor:innen und Institutionen

  • College of Electromechanical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China.
  • Inner Mongolia Engineering Research Center for Intelligent Facilities in Prataculture and Livestock Breeding, Hohhot 010018, China.
  • Shenzhen Key Laboratory of Intelligent licrosatellite Constellation, Shenzhen Campus of Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen 518107, China.
  • School of Aeronautical Engineering, Changsha University of Science & Technology, Changsha 410004, China.

ORCID-Profile: Chuanzhong Xuan, Xinyu Gao, Zhipan Wang

Förderung

  • The National Natural Science Foundation of China
  • The First Class Disciplines Research Special Project
  • The Fundamental Research Funds for Inner Mongolia Directly Affiliated Universities
  • National Natural Science Foundation of China
  • First Class Disciplines Research Special Project
  • Fundamental Research Funds for Inner Mongolia Directly Affiliated Universities

Zitieren

APA

Liu, S., Xuan, C., Tang, Z., Wang, G., Gao, X., & Wang, Z. (2025). Aging-Invariant Sheep Face Recognition Through Feature Decoupling. Animals, 15(15), 2299. https://doi.org/10.3390/ani15152299

Vancouver

Liu S, Xuan C, Tang Z, Wang G, Gao X, Wang Z. Aging-Invariant Sheep Face Recognition Through Feature Decoupling. Animals. 2025;15(15):2299. doi:10.3390/ani15152299

BibTeX
@article{Liu2025,
  author = {Liu, Suhui and Xuan, Chuanzhong and Tang, Zhaohui and Wang, Guangpu and Gao, Xinyu and Wang, Zhipan},
  title = {Aging-Invariant Sheep Face Recognition Through Feature Decoupling},
  journal = {Animals},
  year = {2025},
  volume = {15},
  number = {15},
  pages = {2299},
  doi = {10.3390/ani15152299}
}
Kostenlos starten →