Example-based learning method for 3D face reconstruction under varying lighting
Xia Dai · Computer Engineering and Applications Journal · 2008
Illumination changing from picture to picture is main barrier toward full automatic face recognition.In this paper,a novel method to handle lighting conditions is proposed,which can construct an of human face in database under arbitrary illumination conditions and also can relight the probe to no shadow of human face.We carry out the method by decomposing thetexture image and the3D based on the photometric stereo technology,and then using the model of polyhedron to get 3D shape of human face by least-squares-fitting.The 3D shape can be used to update the texture to conquer the influence of cast shadow.When the probe is inputted,the linear combine of normal vector field and texture in example-database can be used to fit the probe and then relight the or reconstruct the 3D shape of human face in probe image.Experimental results on YaleB database show that this method can reconstruct the 3D shape of human face surface in probe effectively,and synthesize the probe human face under arbitrary illumination conditions.