Abstract：To remove the redundant points of shape from shading reconstructed model,a practical methods based on threshold segmentation and polygons intersecting is proposed.The image is converted into binary image through threshold segmentation technique,the defects contained in image are remedied by morphological method,and the 2D contour is extracted by using the differential operator, the binary image is divided into objective region and background region by using the polygons intersecting method; the 3D model is reconstructed by using shape from shading method,and the redundant points of shape from shading reconstructed model are removed through fusing the information of 3D profile and 2D contour.Experiment results showed that the method proposed can effectively remove redundant points of shape from shading reconstructed model,and it is helpful for improving the shape precision of shape from shading reconstructed model.
2014, Vol. 35 
