Shape from SEM Image Using Fast Marching Method and Intensity Modification by Neural Network
This chapter proposes a new approach to recover 3-D shape from a Scanning Electron Microscope (SEM) image. When an SEM image is used to recover 3-D shape, one can apply the algorithm based on the solving the Eikonal equation with Fast Marching Method (FMM). However, when the oblique light source image is observed, the correct shape cannot be obtained by the usual one-pass FMM. The approach proposes a method to modify the original SEM image with intensity modification by introducing a Neural Network (NN). Correct 3-D shape could be obtained using FMM and NN learning without iterations. The proposed approach is demonstrated through computer simulation and validate through experiment.
KeywordsScanning Electron Microscope Intensity Modification RBF Neural Network Fast Marching Method
Iwahori’s research is supported by Japan Society for the Promotion of Science (JSPS) Grant-in-Aid for Scientific Research (C23500228) and Chubu University Grant. Woodham’s research is supported by the Natural Sciences and Engineering Research Council (NSERC). The authors also thank Ryo Maeda and Seiya Tsuda in the experimental help.
- 5.Iwahori, Y., Woodham, R.J., Ozaki, M., Tanaka, H., Ishii, N.: Neural network based photometric stereo with a nearby rotational moving light source. IEICE Trans. Info. Syst. E80-D(9), 948–957 (1997)Google Scholar
- 7.Hopfield, J.J., Tank, D.W.: “Neural” computation of decisions in optimization problems. Biol. Cybern. 52, 141–152 (1985)Google Scholar
- 8.Iwahori, Y., Nakagawa, T., Woodham, R.J., Kawanaka, H., Fukui, S.: Shape from self-calibration and fast marching method. In: 19th International Conference on Pattern Recognition (ICPR 2008), pp. 1–4 (2008)Google Scholar
- 9.Ojima, H., Murakami, Y., Otsuka, H., Sasamoto, Y., Zhou, L., Shimizu, J., Eda, H.: 3D data acquisition and reconstruction from SEM stereo pairs (in Japanese), J. Jpn. Soc. Precis Eng. 75(6), 773–777 (2009)Google Scholar
- 10.Jiang, J., Sakai, S.: 3-Dimensional measurement of fracture surface using SEM via the combination of stereo matching and integrating secondary electron intensity (in Japanese). J. Jpn. Soc. Mech. Eng. 68(666), 300–306 (2002)Google Scholar
- 11.Kamata, K.: 3D Shape Recovery From SEM Image Using Shading Information (in Japanese), 21st Sens. Forum. C, pp. 279–284 (2004)Google Scholar
- 12.Ding, Y., Iwahori, Y., Nakamura, T., Lifeng He, Woodham, R.J., Itoh, H.: Neural network implementation of image rendering via self-calibration. J. Adv. Comput. Intell. Intell. Inform. 14(4) 344–352 (2010)Google Scholar
- 13.Tankus, A., Sochen. N., Yeshurun. Y.: Shape-from-Shading By Iterative Fast Marching For Vertical and Oblique Light Sources. Geom. Prop. Incomplete Data, pp. 237–258 (2005)Google Scholar
- 14.Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Proc. Nat. Acad. Sci. 93(1), 5–28 (1998)Google Scholar