"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

I agree, do not show this message again.

Improved SFS 3D measurement based on neural network

LIMEI SONG1,* , DANV WANG1, HONG SU1, XIAOXIA LI1, XIANYONG LIU1

Affiliation

  1. Information Engineering College, South West University of Science and Technology, Sichuan Mian Yang, 621010, China

Abstract

Non-contact 3D surface measurement is an important problem for modern industry. Shape from shading (SFS) is a convenient method because it can recover the 3D shape only from one image. But the conventional SFS research has a lot of restriction, such as Lambertian illumination model. If the object isn’t under this model, the precision wi l decrease quickly. We proposed an improved SFS based on neural network combining with genetic algorithm. This proposed SFS doesn’t care much about the ilumination and increased the precision. It has been used in the 3D reconstruction of synthetic vase, and also used in the online 3D measurement of work piece..

Keywords

SFS, Neural network, Genetic algorithm, Synthetic vase.

Submitted at: June 13, 2005
Accepted at: Jan. 26, 2006

Citation

LIMEI SONG, DANV WANG, HONG SU, XIAOXIA LI, XIANYONG LIU, Improved SFS 3D measurement based on neural network, Journal of Optoelectronics and Advanced Materials Vol. 8, Iss. 1, pp. 285-290 (2006)