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 object's surface normal vector on each point of an image by ICA model to reconstruct 3-D shape, we will find the normal vector's 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 vector's sequence form surface, and using the enforcing integrability method to reconstruct 3-D object. Finally, we test our algorithm on a number of real images captured from the Vale Face Database B. The experimental results demonstrate that the proposed CICA method is work to find the order of normal vector.