Improvement of Recovering Shape from Endoscope Images Using RBF Neural Network

Yuji Iwahori, Seiya Tsuda, Robert J. Woodham, M. K. Bhuyan, Kunio Kasugai


The VBW (Vogel-Breuß-Weickert) model is proposed as a method to recover 3-D shape under point light source illumination and perspective projection. However, the VBW model recovers relative, not absolute, shape. Here, shape modification is introduced to recover the exact shape. Modification is applied to the output of the VBW model. First, a local brightest point is used to estimate the reflectance parameter from two images obtained with movement of the endoscope camera in depth. After the reflectance parameter is estimated, a sphere image is generated and used for Radial Basis Function Neural Network (RBF-NN) learning. The NN implements the shape modification. NN input is the gradient parameters produced by the VBW model for the generated sphere. NN output is the true gradient parameters for the true values of the generated sphere. Depth can then be recovered using the modified gradient parameters. Performance of the proposed approach is confirmed via computer simulation and real experiment.


  1. Benton, S. H. (1977). The Hamilton- Jacobi Equation: A Global Approach. In Academic Press, Volume 131.
  2. Ding, Y., Iwahori, Y., Nakamura, T., He, L., Woodham, R. J., and Itoh, H. (2010). Shape Recovery of Color Textured Object Using Fast Marching Method via Self-Caribration. In EUVIP 2010, pp. 92-96.
  3. Ding, Y., Iwahori, Y., Nakamura, T., Woodham, R. J., He, L., and Itoh, H. (2009). Self-calibration and Image Rendering Using RBF Neural Network. In KES 2009, Volume 5712, pp. 705-712.
  4. Horn, B. K. P. (1975). Obtaining Shape from Shading Information. In The Psychology of Computer Vision, Winston, P. H. (Ed.), Mc Graw- Hill, pp. 115-155. Mc Graw- Hill.
  5. Iwahori, Y., Iwai, K., Woodham, R. J., Kawanaka, H., Fukui, S., and Kasugai, K. (2010). Extending Fast Marching Method under Point Light Source Illumination and Perspective Projection. In ICPR2010, pp. 1650-1653.
  6. Iwahori, Y., Shibata, K., Kawanaka, H., Funahashi, K., Woodham, R. J., and Adachi, Y. (2014). Shape from SEM Image Using Fast Marching Method and Intensity Modification by Neural Network. In Recent Advances in Knowledge-based Paradigms and Applications, Advances in Intelligent Systems and Computing 234, Springer, Chapter 5, pp.73-86.
  7. Iwahori, Y., Sugie, H., and Ishii, N. (1990). Reconstructing Shape from Shading Images under Point Light Source Illumination. In ICPR 1990, Vol.1, pp. 83-87.
  8. Iwahori, Y., Woodham, R. J., Ozaki, M., Tanaka, H., and Ishii, N. (1997). Neural Network based Photometric Stereo with a Nearby Rotational Moving Light Source. In IEICE Trans. Info. and Syst., Vol. E80-D, No. 9, pp. 948-957.
  9. Kimmel, R. and Sethian, J. A. (2001). Optimal Algorithm for Shape from Shading and Path Planning. In Journal of Mathematical Imaging and Vision (JMIV) 2001, Vol. 14, No. 3, pp. 237-244.
  10. Mourgues, F., Devernay, F., and Coste-Maniere, E. (2001). 3D reconstruction of the operating field for image overlay in 3D-endoscopic surgery. In Proceedings of the IEEE and ACM International Symposium on Augmented Reality (ISAR), pp. 191-192.
  11. Nakatani, H., Abe, K., Miyakawa, A., and Terakawa, S. (2007). Three-dimensional measuremen endoscope system with virtual rulers. In Journal of Biomedical Optics, 12(5):051803.
  12. Neog, D. R., Iwahori, Y., Bhuyan, M. K., Woodham, R. J., and Kasugai, K. (2011). Shape from an Endoscope Image Using Extended Fast Marching Method. In Proc. of IICAI-11, pp. 1006-1015.
  13. Prados, E. and Faugeras, O. (2003). A mathematical and algorithmic study of the Lambertian SFS problem for orthographic and pinhole cameras. In Technical Report 5005, INRIA 2003.
  14. Prados, E. and Faugeras, O. (2005). Shape From Shading: a well-posed problem? In CVPR 2005, pp. 870-877.
  15. Prados, E. and Faugeras, O. D. (2004). Unifying Approaches and Removing Unrealistic Assumptions in Shape from Shading: Mathematics Can Help. In ECCV04.
  16. Sethian, J. A. (1996). A Fast Marching Level Set Method for Monotonically Advancing Fronts. In Proceedings of the National Academy of Sciences of the United States of America (PNAS U.S.), Vol. 93, No. 4, pp. 1591-1593.
  17. Shimasaki, Y., Iwahori, Y., Neog, D. R., Woodham, R. J., and Bhuyan, M. K. (2013). Generating Lambertian Image with Uniform Reflectance for Endoscope Image. In IWAIT2013, 1C-2 (Computer Vision 1), pp. 60-65.
  18. Tatematsu, K., Iwahori, Y., Nakamura, T., Fukui, S., Woodham, R. J., and Kasugai, K. (2013). Shape from Endoscope Image based on Photometric and Geometric Constraints. In KES 2013, Procedia Computer Science, Elsevier, Vol.22, pp. 1285-1293.
  19. Thormaehlen, T., Broszio, H., and Meier, P. N. (2001). Three-Dimensional Endoscopy. In Falk Symposium, pp. 199-212.
  20. Vogel, O., Breuß, M., and Weickert, J. (2007). A Direct Numerical Approach to Perspective Shape-fromShading. In Vision Modeling and Visualiz-ation(VMV) 2007, pp. 91-100.
  21. Yuen, S. Y., Tsui, Y. Y., and Chow, C. K. (2007). A fast marching formulation of perspective shape from shading under frontal illumination. In Pattern Recognition Letters, Vol. 28, No.7, pp. 806-824.

Paper Citation

in Harvard Style

Iwahori Y., Tsuda S., Woodham R., Bhuyan M. and Kasugai K. (2015). Improvement of Recovering Shape from Endoscope Images Using RBF Neural Network . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-758-077-2, pages 62-70. DOI: 10.5220/0005206800620070

in Bibtex Style

author={Yuji Iwahori and Seiya Tsuda and Robert J. Woodham and M. K. Bhuyan and Kunio Kasugai},
title={Improvement of Recovering Shape from Endoscope Images Using RBF Neural Network},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},

in EndNote Style

JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - Improvement of Recovering Shape from Endoscope Images Using RBF Neural Network
SN - 978-989-758-077-2
AU - Iwahori Y.
AU - Tsuda S.
AU - Woodham R.
AU - Bhuyan M.
AU - Kasugai K.
PY - 2015
SP - 62
EP - 70
DO - 10.5220/0005206800620070