3D Face Recognition with Occlusions Using Fisher Faces Projection

Abstract:

In recent years, the 3-D face has become biometric modal, for security applications. Dealing with occlusions covering the facial surface is difficult to handle. Occlusion means blocking of face images by objects such as sun glasses, kerchiefs, hands, hair and so on. Occlusions are occurred by facial expressions, poses also. Basically consider two things: i) Occlusion handling for surface registration and ii). Missing data handling for classification. For registration to use an adaptively-selected-model based registration scheme is used. After registering occlusions are detected and removed. In order to handle the missing data we use a masking strategy call masked projection technique called Fisher faces Projection. Registration based on the adaptively selected model together with the masked analysis offer an occlusion robust face recognition system.

• Periodical: Applied Mechanics and Materials (Volume 573)
• Pages: 442-446
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.573.442
• Online since: June 2014
• Authors: D. Venkatakrishnan Ragu*, C. Hariram, N. Anantharaj, A. Muthulakshmi
• Keywords: Face Recognition, Masked Projection, Occlusion

References

[1] N. Alyuz, B. Gokberk, and L. Akarun, Adaptive model based 3D face registration for occlusion invariance, in Proc. Eur. Conf. Computer Vision—Workshops— Benchmarking Facial Image Analysis Technologies (BeFIT), Florence, Italy, (2012).

DOI: 10.1007/978-3-642-33885-4_56

[2] K. Chang, W. Bowyer, and P. Flynn, Multiple nose region matching for 3D face recognition under varying facial expression, IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 10, p.1695–1700, Oct. (2006).

DOI: 10.1109/tpami.2006.210

[3] A. Colombo, C. Cusano, and R. Schettini, Detection and restoration of occlusions for 3D face recognition, in Proc. Int. Conf. Multimedia and Expo, 2006, p.1541–1544.

DOI: 10.1109/icme.2006.262837

[4] B. Gokberk, M. O. Irfanoglu, and L. Akarun, 3D shape-based face representation and feature extraction for face recognition, Image Vis. Comput., vol. 24, no. 8, p.857–869, Aug. (2006).

DOI: 10.1016/j.imavis.2006.02.009

[5] R. He, W. Zheng, and B. Hu, Maximum correntropy criterion for robust face recognition, IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 8, p.1561–1576, Aug. (2011).

DOI: 10.1109/tpami.2010.220

[6] A. A. Salah, N. Alyuz, and L. Akarun, Registration of 3D face scans with average face models, J. Electron. Imag., vol. 17, no. 1, (2008).

DOI: 10.1109/siu.2007.4298697

[7] A. Savran, N. Alyuz, H. Dibeklioglu, O. Celiktutan, B. Gokberk, B. Sankur, and L. Akarun, Bosphorus database for 3D face analysis, Biometrics Identity Manage., p.47–56, (2008).

DOI: 10.1007/978-3-540-89991-4_6

[8] A. Colombo, C. Cusano, and R. Schettini, UMB-DB: A database of partially occluded 3D faces, in Proc. Int. Conf. Computer Vision (ICCV)—Workshops, 2011, p.2113–2119.

DOI: 10.1109/iccvw.2011.6130509