Redundant Points Removing of SFS Reconstructed Surface

Abstract

To remove the redundant points of image background in SFS reconstructed surface, a novel approach which combines the advantages of polygon scan and intersection algorithm and improves contour extraction method is proposed. In one hand, according to the gray scale level of pixels, the 3D profile of object is reconstructed by Shape from Shading method. In the other hand, firstly, the image is transformed into binary image through single-threshold segmentation method, the defects in image are remedied by morphological method, and the 2D contour of image is extracted through differential operator method; secondly, the image is divided into two parts using the polygon scan and intersection algorithm, that is the objective region and the background region; finally, the redundant points of image background in SFS reconstructed surface are removed through the fusing of 3D profile and 2D contour. Experiments shown that the proposed method can effectively remove the redundant points of SFS reconstructed surface, and it not only ensure the shape precision of SFS reconstructed surface, but also improve the universal of Shape from Shading technique.