A Novel Technique for the Extraction of Depth Information by Gradient Analysis on Grayscale Images

Abstract

A technique specifically designed for 3D surface reconstruction of human face in a single grayscale image was developed based on the principle of Shape from Shading (SFS). Lambertian reflectance model was used to obtain the surface gradient information contained in the intensity image. The surface depth was computed by direct integration of surface gradients. The X and Y components of surface gradients were determined based on the assumption that the direction of surface gradient is parallel to the image intensity gradient. In order to determine the signs of the X and Y components of surface gradients, the analysis of image intensity and face detection technique were used to provide the position of critical points based on the 3D characteristics of human face. This algorithm has been applied to synthetic face images with light source direction along z axis, and the reconstructed 3D human face was obtained with good accuracy and high speed. The result produced by our algorithm was also compared with those of other SFS algorithms. The performance of the proposed algorithm indicates that the new concept of combining face detection with SFS will be a promising and useful technique for recovering 3D faces from grayscale images.