Abstract
For the reason that the conventional illumination models are empirical and non-linear, the traditional shape from shading (SFS) methods with conventional illumination models are always divergent in the process of iteration and are difficult to initialize the parameters of the illumination model. To overcome these disadvantages, a new approach based on the neural network for indirect SFS is proposed in this paper. The new proposed approach applies a series of standard sphere pictures, in which the gradients of the sphere can be calculated, to train a neural network model. Then, the gradients of the reconstructed object pictures, which are taken in the similar circumstances as that of the standard sphere pictures, can be obtained from the network model. Finally, the height of the surface points can be calculated. The results show that the new proposed method is effective, accurate and convergent.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Torrance, K., Sparrow, E.: Theory for Off-specular Reflection from Rough Surfaces. Journal of the Optical Society of America 57, 1105–1114 (1967)
Cook, R.L., Torrance, K.E.: A Reflection Model for Computer Graphics. ACM Transactions on Graphics 1, 7–24 (1982)
Zhang, R., Tsai, P.S., Cryer, J.E., Shah, M.: Shape from Shading: A Survey. IEEE Trans. On PAMI 21, 690–705 (1999)
Horn, B.K.P., Brooks, M.J.: Shape from Shading. MIT Press, Cambridge (1989)
Wei, G.Q., Hirzinger, G.: Learning Shape from Shading by A Multiplayer Network. IEEE Trans Neural Network 4, 985–995 (1996)
Cho, S.Y., Chow, T.W.S.: Neural Computation Approach for Developing A 3-D Shape Reconstruction Model. IEEE Trans Neural Network 5, 1204–1214 (2001)
Cheung, W.P., Lee, C.K.: Application of Self-Organization Neural Network for Direct Shape from Shading. Neural Computing & Applications 10, 206–213 (2001)
Jiang, T., Liu, B., Lu, Y.L., Evans, D.J.: A Neural Network Approach to Shape from Shading. Intern. J. Computer Math. 4, 433–439 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hao, P., Guo, D., Kang, R. (2004). A Neural Network Approach for Indirect Shape from Shading. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks - ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3174. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28648-6_118
Download citation
DOI: https://doi.org/10.1007/978-3-540-28648-6_118
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22843-1
Online ISBN: 978-3-540-28648-6
eBook Packages: Springer Book Archive