ON ERROR ANALYSIS FOR SURFACE NORMALS DETERMINED BY PHOTOMETRIC STEREO

The local surface orientation of a three-dimensional object in a scene can be determined by photometric stereo. Photometric methods are susceptible to a number of errors. Ray, Birk and Kelly have identified and analysed the various error sources. Especially, a sensitivity analysis of local surface normals computed by photometric stereo with respect to major error sources is given. Unfortunately, due to the gradient space representation of reflectance maps, the derivation process is tedious and the formulas are very complicated. This paper gives a new sensitivity analysis technique using reflectance maps represented by unit surface normal vectors and vector differentiation. This new technique leads to a much simpler derivation process and substantially compacter sensitivity formulas.