Improving Height Recovery from a Single Image of a Face Using Local Shape Indicators
In this paper we propose a local-shape based method for correcting shape-from- shading information for surface height recovery of faces. The underpinning idea comes from the observation that subtle changes in the elements of a gradient field can cause notable changes in its integrated surface. One of the problems with reliable face surface reconstruction using shape-from-shading is that local errors in the needle map can cause implosion of facial features. To overcome this problem we develop a method for ensuring surface convexity. This is done by modifying the gradient orientations in accordance with critical points on the surface. We utilize a local shape indicator as a criteria to decide which surface normals are to be modified. Experiments show that altering the directions of a surface normal field of a face leads to a considerable improvement in its integrated height map.
Unable to display preview. Download preview PDF.
- 3.Forsythe, D., Ponce, J.: Computer Vision: a Modern Approach. Prentice- Hall, Englewood Cliffs (2001)Google Scholar
- 5.Georghiades, A., Belhumeur, D., Kriegman, D.: From Few to Many: Illumination Cone Models fro Face Recognition under Variable Lighting and Pose. IEEE Trans. Pattern Analysis and Machine Intelligence, 643–660 (2001)Google Scholar
- 7.Horn, B.K.P., Brooks, M.J.: Shape from Shading. MIT Press, Cambridge (1989)Google Scholar
- 10.Zhao, W., Chellapa, R.: Illumination-insensitive Face Recognition Using Symmetric Shape-from-Shading. Conference on Computer Vision and Pattern Recognition, 286–293 (2000)Google Scholar