Title :
A shape-from-shading method based on surface reflectance component estimation
Author :
Ma, Jiquan ; Zhao, Peng ; Gong, Bing
Author_Institution :
Sch. of Comput. Sci. & Technol., Heilongjiang Univ., Harbin, China
Abstract :
Shape-from-shading (SFS) technology is used to reconstruct a 3D shape from only one gray level image. To overcome the disadvantage existing in conventional SFS method, which relies on the assumption of Lambertian reflectance model, hybrid reflectance model is introduced firstly and then is applied on SFS method. Secondly. In order to define the proportion of different reflectance components in hybrid reflectance model, we have developed a new computing method based on simulated annealing algorithm. Here, we describe the proportion as reflectance probability. Finally, Experimental results reveal that the proposed method shows better performance both on synthetic and real images. The accuracy of the shape recovery is increased.
Keywords :
computer vision; image reconstruction; probability; reflectivity; simulated annealing; 3D shape reconstruction; Lambertian reflectance model; SFS method; gray level image; hybrid reflectance model; reflectance probability; shape recovery; shape-from-shading method; simulated annealing algorithm; surface reflectance component estimation; Computational modeling; Equations; Light sources; Mathematical model; Shape; Surface treatment; Vectors;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on
Conference_Location :
Sichuan
Print_ISBN :
978-1-4673-0025-4
DOI :
10.1109/FSKD.2012.6234361