Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Improving Facial Recognition Performance to Introduce a New Dog Registration Method

새로운 반려견 등록방식 도입을 위한 안면 인식 성능 개선 연구

  • Lee, Dongsu (Graduate School of Nano IT Design Fusion, Seoul National University of Science and Technology) ;
  • Park, Gooman (Graduate School of Nano IT Design Fusion, Seoul National University of Science and Technology)
  • 이동수 (서울과학기술대학교 나노IT디자인융합대학원) ;
  • 박구만 (서울과학기술대학교 나노IT디자인융합대학원)
  • Received : 2022.08.16
  • Accepted : 2022.09.01
  • Published : 2022.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Although registration of dogs is mandatory according to the revision of the Animal Protection Act, the registration rate is low due to the inconvenience of the current registration method. In this paper, a performance improvement study was conducted on the dog face recognition technology, which is being reviewed as a new registration method. Through deep learning learning, an embedding vector for facial recognition of a dog was created and a method for identifying each dog individual was experimented. We built a dog image dataset for deep learning learning and experimented with InceptionNet and ResNet-50 as backbone networks. It was learned by the triplet loss method, and the experiments were divided into face verification and face recognition. In the ResNet-50-based model, it was possible to obtain the best facial verification performance of 93.46%, and in the face recognition test, the highest performance of 91.44% was obtained in rank-5, respectively. The experimental methods and results presented in this paper can be used in various fields, such as checking whether a dog is registered or not, and checking an object at a dog access facility.

동물보호법 개정에 따라 반려견 등록이 의무화 되었음에도 불구하고, 현재 등록 방법의 불편함으로 등록율이 저조한 상태이다. 본 논문에서는 새로운 등록 방법으로 검토되고 있는 반려견 안면 인식 기술에 대한 성능 개선 연구를 진행하였다. 딥러닝 학습을 통해, 반려견의 안면 인식을 위한 임베딩 벡터를 생성하여 반려견 개체별로 식별하기 위한 방법을 실험하였다. 딥러닝 학습을 위한 반려견 이미지 데이터셋을 구축하고, InceptionNet과 ResNet-50을 백본 네트워크로 사용하여 실험하였다. 삼중항 손실 방법으로 학습하였으며, 안면 검증과 안면 식별로 나뉘어 실험하였다. ResNet-50 기반의 모델에서 최고 93.46%의 안면 검증 성능을 얻을 수 있었으며, 안면 식별 시험에서는 rank-5에서 91.44%의 최고 성능을 각각 얻을 수 있었다. 본 논문에서 제시한 실험 방법과 결과는 반려견의 등록 여부 확인, 반려견 출입시설에서의 개체 확인 등 다양한 분야로 활용이 가능하다.

Keywords

References

  1. D. Lee and G. Park, "Analysis of Transfer Learning Effect for Automatic Dog Breed Classification," Journal of Broadcasting Engineering, Vol. 27, No. 1, pp.133-145, Jan. 2022. doi : https://doi.org/10.5909/JBE.2022.27.1.133
  2. Liu, A. Kanazawa, D. Jacobs, and P. Belhumeur, "Dog Breed Classification using Part Localization," European Conference on Computer Vision(ECCV), pp.172-185, 2012. doi : https://doi.org/10.1007/978-3-642-33718-5_13
  3. X. Wang, V. Ly, S. Sorensen, and C. Kambhamettu, "Dog breed classification via landmarks," International Conference on Image Procesing(ICIP) 2014, pp. 5237-5241, January 2015. doi : https://doi.org/10.1109/ICIP.2014.7026060
  4. G. Mougeot, D. Li, and S Jia, "A Deep Learning Approach for Dog Face Verification and Recognition," PRICAI 2019: Trends in Artificial Intelligence, pp. 418-430, 2019. doi : https://doi.org/10.1007/978-3-030-29894-4_34
  5. S. Kumar and S. K. Singh, "Monitoring of pet animal in smart cities using animal biometrics," Future Generation Computer Systems, Vol. 83, pp. 553-563, 2018. https://doi.org/10.1016/j.future.2016.12.006
  6. The DogFaceNet Dataset 1, https://github.com/GuillaumeMougeot/DogFaceNet/releases (accessed Mar. 02, 2022) doi : https://doi.org/10.1016/j.future.2016.12.006
  7. D. G. Lowe, "Distinctive Image Features from ScaleInvariant Keypoints," International Journal of Computer Vision, vol.60, issue.2, pp.91~110, 2004. doi : https://doi.org/10.1023/B:VISI.0000029664.99615.94
  8. H. Bay, T. Tuytelaars, and L. Gool, "SURF: Speeded Up Robust Features," Computer Vision and Image Understanding, Vol.110, No.3, pp.346~359, 2008. doi : https://doi.org/10.1007/11744023_32
  9. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems, Vol. 2, pp.1097-1105. 2012. doi : https://doi.org/10.1145/3065386
  10. Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, "Deepface: Closing the Gap to Human-level Performance in Face Verification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701-1708, 2014.
  11. F. Schroff, D. Kalenichenko, and J. Philbin, "Facenet: A Unified Embedding for Face Recognition and Clustering," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815-823, 2015.
  12. M. D. Zeiler and R. Fergus. "Visualizing and Understanding Convolutional Networks," European Conference on Computer Vision(ECCV), pp.818-833, 2014. doi : https://doi.org/10.1007/978-3-319-10590-1_53
  13. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. "Going Deeper with Convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1-9, 2015.
  14. Y. Sun, X. Wang, and X. Tang. "Deeply Learned Face Representations are Sparse, Selective, and Robust," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2892-2900, 2015.
  15. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song. "SphereFace: Deep Hypersphere Embedding for Face Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.212-220, 2017.
  16. H. Wang, Y. Wang, Z. Zhou, X. Ji, Z. Li, D. Gong, J. Zhou, and W. Liu, "Cosface: Large margin cosine loss for deep face recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salk Lake City, US, pp. 5265-5274, 2018.
  17. M. Lee, J. Park, and J. Jeong, "An improved system of Dog Identification based on Muzzle Pattern," Proceedings of the Korean Society of Broadcast and Media Engineers Conference, pp.199-202, 2015.
  18. J. Liu, A. Kanazawa, D. Jacobs, and P. Belhumeur, "Dog Breed Classification using Part Localization," European Conference on Computer Vision(ECCV), pp.172-185, 2012. doi : https://doi.org/10.1007/978-3-642-33718-5_13
  19. Adam Klein. Pet Cat Face Verification and Identification, Stanford University, CS230 Fall 2019.