3D Face Recognition with Reconstructed Faces from a Collection of 2D Images
Nowadays, there is an increasing need for systems that can accurately and quickly identify a person. Traditional identification methods utilize something a person knows or something a person has. This kind of methods has several drawbacks, being the main one the fact that it is impossible to detect an imposter who uses genuine credentials to pass as a genuine person. One way to solve these kinds of problems is to utilize biometric identification. The face is one of the biometric features that best suits the covert identification. However, in general, biometric systems based on 2D face recognition perform very poorly in unconstrained environments, common in covert identification scenarios, since the input images present variations in pose, illumination, and facial expressions. One way to mitigate this problem is to use 3D face data, but the current 3D scanners are expensive and require a lot of cooperation from people being identified. Therefore, in this work, we propose an approach based on local descriptors for 3D Face Recognition based on 3D face models reconstructed from collections of 2D images. Initial results show 95% in a subset of the LFW Face dataset.
KeywordsBiometrics 3D face recognition 3DLBP Face reconstruction
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES). This study utilizes a GPU granted by the NVIDIA Grant Program.
- 3.Chetverikov, D., Stepanov, D., Krsek, P.: Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm. Image Vis. Comput. 23(3), 299–309 (2005). https://doi.org/10.1016/j.imavis.2004.05.007. http://www.sciencedirect.com/science/article/pii/S0262885604001179CrossRefGoogle Scholar
- 4.Huang, Y., Wang, Y., Tan, T.: Combining statistics of geometrical and correlative features for 3D face recognition. In: Proceedings of the British Machine Vision Conference, pp. 90.1–90.10. BMVA Press (2006). https://doi.org/10.5244/C.20.90
- 6.Learned-Miller, E., Huang, G.B., RoyChowdhury, A., Li, H., Hua, G.: Labeled faces in the wild: a survey. In: Kawulok, M., Celebi, M.E., Smolka, B. (eds.) Advances in Face Detection and Facial Image Analysis, pp. 189–248. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-25958-1_8CrossRefGoogle Scholar
- 7.Li, B., Mian, A., Liu, W., Krishna, A.: Using kinect for face recognition under varying poses, expressions, illumination and disguise. In: 2013 IEEE Workshop on Applications of Computer Vision (WACV), pp. 186–192 (2013). https://doi.org/10.1109/WACV.2013.6475017
- 8.Liu, J., Deng, Y., Bai, T., Huang, C.: Targeting ultimate accuracy: face recognition via deep embedding. CoRR abs/1506.07310 (2015). http://arxiv.org/abs/1506.07310
- 9.Nguyen, V., Do, T., Nguyen, V.-T., Ngo, T.D., Duong, D.A.: How to choose deep face models for surveillance system? In: Sieminski, A., Kozierkiewicz, A., Nunez, M., Ha, Q.T. (eds.) Modern Approaches for Intelligent Information and Database Systems. SCI, vol. 769, pp. 367–376. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-76081-0_31CrossRefGoogle Scholar
- 10.Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, p. 6 (2015)Google Scholar
- 13.Roth, J., Tong, Y., Liu, X.: Unconstrained 3D face reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
- 16.Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
- 17.Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015Google Scholar
- 18.Wen, G., Chen, H., Cai, D., He, X.: Improving face recognition with domain adaptation. Neurocomputing 287, 45–51 (2018). https://doi.org/10.1016/j.neucom.2018.01.079. http://www.sciencedirect.com/science/article/pii/S0925231218301127CrossRefGoogle Scholar