10 September 2015 Expression-invariant face recognition using three-dimensional weighted walkthrough and centroid distance
Author Affiliations +
Three-dimensional (3-D) face recognition provides a potential to handle challenges caused by illumination and pose variations. However, extreme expression variations still complicate the task of recognition. An accurate and robust method for expression-invariant 3-D face recognition is proposed. A 3-D face is partitioned into a set of isogeodesic stripes and the spatial relationships of the stripes are described by 3-D weighted walkthrough and the centroid distance. Moreover, the method of the similarity measure is given. Experiments are performed on the CASIA dataset and the FRGC v2.0 dataset. The results show that our method has advantages for recognition performance despite large expression variations.
© 2015 SPIE and IS&T
Yan Liang, Yun Zhang, "Expression-invariant face recognition using three-dimensional weighted walkthrough and centroid distance," Journal of Electronic Imaging 24(5), 053007 (10 September 2015). https://doi.org/10.1117/1.JEI.24.5.053007 . Submission:


Discrete and continuous curvature computation for real data
Proceedings of SPIE (February 03 2014)
3D face recognition via conformal representation
Proceedings of SPIE (March 06 2014)
Learning a statistical 3D geometric head model
Proceedings of SPIE (January 10 2003)
Face recognition security entrance
Proceedings of SPIE (June 28 2000)

Back to Top