Abstract
Radial basis function (RBF) neural network has excellent local mapping and function approximation ability, which is suitable for achieving the optimal solution of nonlinear equations. Due to the direction of the light source is not being estimated accurately by the traditional shape from shading algorithm, in this paper, the RBF neural network is introduced to optimize the classic problem. A RBF reflection model is established to replace the ideal Lambertian reflection model. Then the classic images and two real images are processed using this model without the need of the initial information of the light source. The restored 3D results show that the improved algorithm works better in the details than the traditional algorithm. The errors are much smaller. By adjusting the relevant parameters in RBF reflection model automatically, the training process has been shortened and the convergence rate is improved at the same time.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
