Real-time 3D face recognition using low-cost acquisition devices
Resumo
Biometric recognition seeks to distinguish humans by physical or behavioral characteristics, but there is not a biometric feature that solves all challenges in this problem. Face biometrics show up as a practical option, since they are well accepted and the cost is fairly low. Among different facial properties that could be used for recognition, the geometry stands out for its invariance to pose and illumination. This doctoral work proposes a complete framework for the problem of recognizing people using 3D images. What differs this work from others is that real-time performance and low-cost acquisition were added as requirements. To accomplish this, we designed a novel face detection method, which was thoroughly evaluated and compared to the state-of-the-art. In addition, we optimized the normalization, description and matching stages of the recognition process. We show the operation of our recognition framework in a recent biometric application, which consists in continuously authenticating the identity of a user to offer a more secure session for high security environments. By doing so, we developed the first continuous authentication system based on facial geometry, which is robust to a wide range of facial variations. Finally, the compatibility between 3D recognition and current forms of identification (e.g. ID photos) was addressed. In order to match 3D images to ID photos, we designed a 3D reconstruction method that uses a single or multiple 2D images of a face to retrieve its geometry. The method can effectively create realistic 3D face models, which are suitable for recognition purposes.
Referências
Colombo, A., Cusano, C., and Schettini, R. (2006). 3d face detection using curvature analysis. Pattern Recognition, 39(3):444–455.
Hietmeyer, R. (2000). Biometric identification promises fast and secure processings of airline passengers. The Internationl Civil Aviation Organization Journal, 55(9):10–11. Hole, G. and Bourne, V. (2010). Face processing: Psychological, neuropsychological, and applied perspectives. Oxford University Press.
Jain, A. K., Ross, A., and Prabhakar, S. (2004). An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology, 14(1):4–20.
Janakiraman, R., Kumar, S., Zhang, S., and Sim, T. (2005). Using continuous face verification to improve desktop security. In Proceedings of the 7th IEEE Workshops on Application of Computer Vision, volume 1, pages 501–507.
Mian, A., Bennamoun, M., and Owens, R. (2007). An efficient multimodal 2d-3d hybrid approach to automatic face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(11):1927–1943.
Pamplona Segundo, M., Sarkar, S., Goldgof, D., Silva, L., and Bellon, O. (2013a). Continuous 3d face authentication using rgb-d cameras. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 64–69.
Pamplona Segundo, M., Silva, L., and Bellon, O. R. P. (2011). Real-time scale-invariant face detection on range images. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, pages 914–919.
Pamplona Segundo, M., Silva, L., and Bellon, O. R. P. (2012). Improving 3d face reconstruction from a single image using half-frontal face poses. In Proceedings of the 19th IEEE International Conference on Image Processing, pages 1797–1800.
Pamplona Segundo, M., Silva, L., Bellon, O. R. P., and Queirolo, C. C. (2010). Automatic face segmentation and facial landmark detection in range images. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 40(5):1319–1330.
Pamplona Segundo, M., Silva, L., Bellon, O. R. P., and Sarkar, S. (2013b). Orthogonal projection images for 3d face detection. Pattern Recognition Letters.
Queirolo, C. C., Silva, L., Bellon, O. R. P., and Pamplona Segundo, M. (2010). 3d face recognition using simulated annealing and the surface interpenetration measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(2):206–219.
Shreve, M., Pamplona Segundo, M., Luguev, T., Goldgof, D., and Sarkar, S. (2014). High-resolution 3d surface strain magnitude using 2d camera and low-resolution depth sensor. Pattern Recognition Letters.
Sim, T., Zhang, S., Janakiraman, R., and Kumar, S. (2007). Continuous verification using multimodal biometrics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(4):687–700.
Viola, P. and Jones, M. J. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2):137–154.
