3D human face reconstruction with three images based on constrained ICA

In this paper, we propose an improved photometric stereo scheme based on the Lambertian reflectance model and the constrained independent component analysis (CICA) method. When we obtain the objectpsilas surface normal vector on each point of an image by ICA model to reconstruct 3D shape, we will find the normal vectorpsilas coordinates whose x-axis, y-axis and z-axis value are not arranged in turn. So we use CICA method to solve the problem. Then we obtain correct normal vectorpsilas sequence form surface, and using the enforcing integrability method to reconstruct 3D object. Finally, we test our algorithm on a number of real images captured from the Yale Face Database B. The experimental results demonstrate that the proposed CICA method is work to find the order of normal vector.