An evaluation of lightweight facial recognition models available in the DeepFace library in clustering tasks
Resumo
This work investigates the use of Deep Learning-based facial recognition models to automatically organize images through unsupervised clustering. We evaluated the FaceNet and ArcFace models using the DeepFace library on a dataset of 100 images of five celebrities. The results show an average accuracy of 92.6%, demonstrating that the choice of model and the clustering algorithm configuration significantly influence performance and enable high accuracy in automatic image organization.
Referências
Chen, S., Liu, Y., Gao, X., and Han, Z. (2018). Mobilefacenets: Efficient cnns for accurate real-time face verification on mobile devices. In Chinese conference on biometric recognition, pages 428–438. Springer.
Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019). Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4690–4699.
Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD), pages 226–231.
He, L., He, L., and Peng, L. (2023). Cformerfacenet: Efficient lightweight network merging a cnn and transformer for face recognition. Applied Sciences, 13(11):6506.
Khalifa, A. A. A. (2025). Efficient and robust face recognition in the wild. PhD thesis.
Setyawan, N., Sun, C.-C., Hsu, M.-H., Kuo, W.-K., and Hsieh, J.-W. (2025). Facelivt: Face recognition using linear vision transformer with structural reparameterization for mobile device. In IEEE International Conference on Image Processing (ICIP), pages 1720–1725. IEEE.
Xiao, J., Wang, W., Zhang, L., and Liu, H. (2024). A mobilefacenet-based face antispoofing algorithm for low-quality images. Electronics, 13(14):2801.
Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019). Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4690–4699.
Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD), pages 226–231.
He, L., He, L., and Peng, L. (2023). Cformerfacenet: Efficient lightweight network merging a cnn and transformer for face recognition. Applied Sciences, 13(11):6506.
Khalifa, A. A. A. (2025). Efficient and robust face recognition in the wild. PhD thesis.
Setyawan, N., Sun, C.-C., Hsu, M.-H., Kuo, W.-K., and Hsieh, J.-W. (2025). Facelivt: Face recognition using linear vision transformer with structural reparameterization for mobile device. In IEEE International Conference on Image Processing (ICIP), pages 1720–1725. IEEE.
Xiao, J., Wang, W., Zhang, L., and Liu, H. (2024). A mobilefacenet-based face antispoofing algorithm for low-quality images. Electronics, 13(14):2801.
Publicado
22/04/2026
Como Citar
FRANCISCO, Leandro Barbosa da Silva; MARCON, Marlon; ORTONCELLI, André Roberto.
An evaluation of lightweight facial recognition models available in the DeepFace library in clustering tasks. In: ESCOLA REGIONAL DE BANCO DE DADOS (ERBD), 21. , 2026, Dois Vizinhos/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 149-152.
ISSN 2595-413X.
DOI: https://doi.org/10.5753/erbd.2026.20306.
