Classification of Bayon Faces
Digital 3D models of historic buildings or cultural heritage objects are useful for preservation. Not only can we store them permanently, but the models can supply a clear guideline for the restoration process. 3D models also provide sufficient information about geometrical characteristics that may help archaeologists to inspect and classify the objects. Currently, we are working on a 3D digital-archiving project of the Bayon Temple. It is a building of stonework that was built in the 12th century in Cambodia. It is famous for its towers with four faces at the four cardinal points. According to research by JSA (Japanese government team for Safeguarding Angkor), the faces can be classified into three groups based on subjective criteria. In this chapter, we explore a more objective way to classify the faces by using measured 3D geometrical models. After alignment of 3D faces in the same coordinate system, orientation, and normalization, we captured in-depth images of each face and then classified them by several statistics methods.
KeywordsLinear Discriminant Analysis Face Model Linear Discriminant Function Typical Face Digital Preservation
Unable to display preview. Download preview PDF.
- K. Ikeuchi, A. Nakazawa, K. Hasegawa, T. Oishi, “The Great Buddha Project: Modeling Cultural Heritage for VR Systems through Observation,” Proc. The second IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR2003), Oct. 2003.Google Scholar
- K. Ikeuchi, K. Hasegawa, A. Nakazawa, J. Takamatsu, T. Oishi and T. Masuda, “Bayon Digital Archival Project,” Proc. the Tenth International Conference on Virtual System and Multimedia, pp. 334-343, Nov. 2004.Google Scholar
- S. Umeyama, “Least-Squares Estimation of Transformation Parameters Between Two Point Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.13, no.4, Apr. 1991.Google Scholar
- P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Trans. Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, Jul. 1997.Google Scholar
- T. Heseltine, N. Pears and J. Austin, “Three-Dimensional Face Recognition: A Fishersurface Approach,” Proc. Int’l Conf. Image Analysis and Recognition, vol. 2, 2004, pp. 684-691.Google Scholar
- G. Gordon, “Face Recognition Based on Depth and Curvature Features,” IEEE Int’l Conf. Computer Vision and Pattern Recognition, pp. 808-810, 1992.Google Scholar
- W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phillips, “Face Recognition: A Literature Survey,” ACM Computing Surveys, pp. 399-458, 2003.Google Scholar
- T. Oishi, A. Nakazawa, R. Kurazume and K. Ikeuchi, “Fast Simultaneous Alignment of Multiple Range Images using Index Images,” Proc. The 5th International Conference on 3D Digital Imaging and Modeling, pp. 476-483, 2005.Google Scholar
- R. Sagawa, T. Oishi, A. Nakazawa, R. Kurazume, K. Ikeuchi, “Iterative Refinement of Range Images with Anisotropic Error Distribution,” Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 79-85, 2002.Google Scholar