DocumentCode :
1583731
Title :
Shape recovery of hybrid reflectance surface using neural network
Author :
Kim, Tae-Eun ; Lee, Sun-Ho ; Ryu, Seok-Hyun ; Choi, Jong-Soo
Author_Institution :
Dept. of Electron. Eng., Chungang Univ., Seoul, South Korea
Volume :
3
fYear :
1997
Firstpage :
416
Abstract :
The main interest of previous researches for shape from shading was only on a Lambertian surface which consists of a diffuse reflectance surface. In practice, natural objects have hybrid reflectance, which limits the recovery of shape from intensity distribution. In this paper, we propose the method of determining shape using a neural network and diffuse illumination. The segmented region of sphere surface is used for a training set, which can be determined by shadow line and edge of surface. Diffuse illumination is used to avoid specular spike and highlight which usually cause many problems such as intensity disparities. The diffuse illumination method using flat paper allows us to reduce these phenomena with a simple scheme. The neural network and diffuse illumination method are useful for shape from shading, because it can be applied to objects of unknown reflectance properties, but it is applied only to Torrance-Sparrow style reflectance
Keywords :
image recognition; image reconstruction; image representation; image segmentation; neural nets; reflectivity; stereo image processing; Lambertian surface; Torrance-Sparrow style reflectance; diffuse illumination; diffuse reflectance surface; hybrid reflectance surface; intensity disparities; intensity distribution; natural objects; neural network; segmented region; shading; shape recovery; sphere surface; training set; Image reconstruction; Image segmentation; Light sources; Lighting; Neural networks; Optical reflection; Pixel; Reflectivity; Shape; Surface reconstruction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
Type :
conf
DOI :
10.1109/ICIP.1997.632142
Filename :
632142
Link To Document :
بازگشت