It is well known that all images of the surface (from a fixed view point) under varying illuminations span a 3-D space (or illumination cone) defined by the three images (axes of the cone) b1, b2, b3 [1]. With  the texton model by wavelet bases, we can decompose the axes images b1, b2, b3 into a triplet of coupled 2D textons, which is defined as "lighton".

Example 1:

input images under varying illuminations

Three image bases computed by SVD from the above input images.

 

Example 2:

input images under varying illuminations

Three image bases computed by SVD from the above input images.

References:

  1. Belhumeur, P.N. and Kriegman, D.  ''What is the set of images of an object under all possible illumination conditions?'', IJCV 28(3), 1998.
  2. Song-chun Zhu, Cheng-en Guo, Yingnian Wu and  Yizhou Wang, "What are Textons?" (.pdf 767K), Proc. of 7th European Conference on Computer Vision, Copenhagen, Denmark, 2002.
  3. Song-Chun Zhu, Cheng-en Guo, Yizhou Wang, and Zijian Xu, "What are Textons?" (.pdf 1.7M), International Journal of Computer Vision. (accepted).