PDF version of this entire document

Similar Work

The http://www.ceremade.dauphine.fr/ peyre/teaching/manifold/tp3.htmlMatlab toolbox for fast marching does something relevant, but nothing that involves diffusion. Having browsed several recent papers that adopt an approach similar to ours, I found one paper from 5 years ago [1] where the idea was similar and the results inferior to ours. In other papers, Elad and Kimmel incidentally get cited, but there are no results, just analytical writing [26].

We spent a few hours browsing through anything which overlaps our lines of research. Along the way I also found and read/skimped [25]. Its abstract says: The performance of automatic 3-D face recognition can be significantly improved by coping with the nonrigidity of the facial surface. In this paper, we propose a geodesic polar parameterization of the face surface. With this parameterization, the intrinsic surface attributes do not change under isometric deformations and, therefore, the proposed representation is appropriate for expression-invariant 3-D face recognition. We also consider the special case of an open mouth that violates the isometry assumption and propose a modified geodesic polar parameterization that also leads to invariant representation. Based on this parameterization, 3-D face recognition is reduced to the classification of expression-compensated 2-D images that can be classified with state-of-the-art algorithms. Experimental results verify theoretical assumptions and demonstrate the benefits of the geodesic polar parameterization on 3-D face recognition.

Also of relevance we have [42,35,27]. The latter says that [f]ace recognition based on spatial features has been widely used for personal identity verification for security-related applications. Recently, near-infrared spectral reflectance properties of local facial regions have been shown to be sufficient discriminants for accurate face recognition. In this paper, we compare the performance of the spectral method with face recognition using the eigenface method on single-band images extracted from the same hyperspectral image set. We also consider methods that use multiple original and PCA-transformed bands. Lastly, an innovative spectral eigenface method which uses both spatial and spectral features is proposed to improve the quality of the spectral features and to reduce the expense of the computation. The algorithms are compared using a consistent framework.

Those last two are not so relevant, but they consider an approach other than geodesic metrics (ish).

Roy Schestowitz 2012-01-08