A Shape from Shading Approach for the Reconstruction of Polyhedral Objects using Genetic Algorithm

This paper presents a robust approach for the reconstruction of polyhedral objects from linedrawings. Minimization technique has been used in this approach by exploiting the shading informationcontained in the image. The minimization energy function has been formulated between observed andcalculated value of image intensity under the Lambertian reflectance model. Various constraints e.g. thesurface normal coplanarity and edge length proportionality constraints are used to get the unique solutionfor the depth values. The minimization problem is nonlinear with nonlinear constraints, which is solvedby using Genetic Algorithm. The proposed algorithm produces satisfactory results even in the case ofslight error in computation of vertex positions caused in image processing. The algorithm has been testedon synthetic images and the results are shown