Abstract
In the environment of the Scanning Electron Microscope (SEM), it is necessary to establish the technology of recovering the 3D shape of a target object from the observed 2D shading image. SEM has the function to rotate the object stand to some extent. This paper uses this principle and proposes a new method to recover the object shape using two shading images taken during the rotation. The proposed method uses the optimization of the energy function using Hopfield neural network, which is based on the standard regularization theory. It is also important to give the initial vector that is close to the true optimal solution vector. Computer simulation evaluates the essential ability of the proposed method. Further, the real experiments for the SEM images are also demonstrated and discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. J. Hopfield D. W. Tank (1985) ArticleTitle“Neural” computation of decisions in optimization problems Biological Cybernetics 52 141–152 Occurrence Handle4027280
Horn B. K. P. (1975). Obtaining shape from shading in formation, in The Psychology of Computer Vision. P. H. Winston, (ed.), McGrawHill, pp. 115–155.
B. K. P. Horn (1990) ArticleTitleHeight and gradient from shading International Journal of Computer Vision 5 IssueID1 584–595 Occurrence Handle10.1007/BF00056771
K. Ikeuchi B. K. P. Horn (1981) ArticleTitleNumerical shape from shading and occluding boundaries Artificial Intelligence 17 IssueID1–3 141–184 Occurrence Handle10.1016/0004-3702(81)90023-0
Iwahori, Y., Watanabe, Y., Woodham, R. J. and Iwata, A. (2002). Self-calibration and neural network implementation of photometric stereo. Proceedings of the 16th International Conference on Pattern Recognition (ICPR2002), Vol. IV, pp. 359–362.
Y. Iwahori R. J. Woodham M. Ozaki H. Tanaka N. Ishii (1997) ArticleTitleNeural network based photometric stereo with a nearby rotational moving light source IEICE Trans. Inf. and Syst. E80-D IssueID9 948–957
A. Laurentini (1995) ArticleTitleHow far 3D shapes can be understood from 2D Silhouettes IEEE Transactions on Pattern Analysis and Machine Intelligence 17 IssueID2 188–195 Occurrence Handle10.1109/34.368170
J. Lu J. Little (1999) ArticleTitleSurface reflectance and shape from images using a Collinear light source International Journal of Computer Vision 32 IssueID3 213–240 Occurrence Handle10.1023/A:1008157029424
K. Omata H. Saito S. Ozawa (2000) ArticleTitleEstimation of shape and reflectance property based on relative rotation of light source (in Japanese) Trans. of IEICE J83-D-II IssueID3 927–937
A. Pentland (1990) ArticleTitleLinear shape from shading International Journal of Computer Vision 4 153–162 Occurrence Handle10.1007/BF00127815
A. Pentland (1991) ArticleTitlePhotometric motion IEEE Transactions on Pattern Analysis and Machine Intelligence 13 IssueID9 879–890 Occurrence Handle10.1109/34.93807
Y. Sato K. Ikeuchi (1994) ArticleTitleTemporal-color space analysis of reflection Journal of Optical Society of America, A 11 IssueID11 2990–3002
Y. Takefuji K. C. Lee (1990) ArticleTitleA super parallel sorting algorithm based on neural networks IEEE Transactions on Circuits and Systems CAS-37 1425–1429 Occurrence Handle10.1109/31.62417
R. J. Woodham (1980) ArticleTitlePhotometric method for determining surface orientation from multiple images Optical Engineering 19 IssueID1 139–144
Woodham, R. J. (1994). Gradient and curvature from the photometric stereo method, including local confidence estimation. Journal of the Optical Society of America, A, 3050–3068.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Iwahori, Y., Kawanaka, H., Fukui, S. et al. Obtaining Shape from Scanning Electron Microscope using Hopfield Neural Network. J Intell Manuf 16, 715–725 (2005). https://doi.org/10.1007/s10845-005-4374-y
Issue Date:
DOI: https://doi.org/10.1007/s10845-005-4374-y