Journal of Intelligent Manufacturing

, Volume 16, Issue 6, pp 715–725 | Cite as

Obtaining Shape from Scanning Electron Microscope using Hopfield Neural Network

  • Yuji Iwahori
  • Haruki Kawanaka
  • Shinji Fukui
  • Kenji Funahashi


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.


Shape recovery Hopfield neural network optimization scanning electron microscope 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Hopfield, J. J., Tank, D. W. 1985“Neural” computation of decisions in optimization problemsBiological Cybernetics52141152PubMedGoogle Scholar
  2. 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.Google Scholar
  3. Horn, B. K. P. 1990Height and gradient from shadingInternational Journal of Computer Vision5584595CrossRefGoogle Scholar
  4. Ikeuchi, K., Horn, B. K. P. 1981Numerical shape from shading and occluding boundariesArtificial Intelligence17141184CrossRefGoogle Scholar
  5. 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.Google Scholar
  6. Iwahori, Y., Woodham, R. J., Ozaki, M., Tanaka, H., Ishii, N. 1997Neural network based photometric stereo with a nearby rotational moving light sourceIEICE Trans. Inf. and Syst.E80-D948957Google Scholar
  7. Laurentini, A. 1995How far 3D shapes can be understood from 2D SilhouettesIEEE Transactions on Pattern Analysis and Machine Intelligence17188195CrossRefGoogle Scholar
  8. Lu, J., Little, J. 1999Surface reflectance and shape from images using a Collinear light sourceInternational Journal of Computer Vision32213240CrossRefGoogle Scholar
  9. Omata, K., Saito, H., Ozawa, S. 2000Estimation of shape and reflectance property based on relative rotation of light source (in Japanese)Trans. of IEICEJ83-D-II927937Google Scholar
  10. Pentland, A. 1990Linear shape from shadingInternational Journal of Computer Vision4153162CrossRefGoogle Scholar
  11. Pentland, A. 1991Photometric motionIEEE Transactions on Pattern Analysis and Machine Intelligence13879890CrossRefGoogle Scholar
  12. Sato, Y., Ikeuchi, K. 1994Temporal-color space analysis of reflectionJournal of Optical Society of America, A1129903002Google Scholar
  13. Takefuji, Y., Lee, K. C. 1990A super parallel sorting algorithm based on neural networksIEEE Transactions on Circuits and SystemsCAS-3714251429CrossRefGoogle Scholar
  14. Woodham, R. J. 1980Photometric method for determining surface orientation from multiple imagesOptical Engineering19139144Google Scholar
  15. 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.Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • Yuji Iwahori
    • 1
  • Haruki Kawanaka
    • 2
  • Shinji Fukui
    • 3
  • Kenji Funahashi
    • 2
  1. 1.Chubu UniversityKasugaiJapan
  2. 2.Nagoya Institute of TechnologyGokiso-choJapan
  3. 3.Aichi University of EducationHirosawaJapan

Personalised recommendations