Evaluation of 3-D Shape Reconstruction of Retinal Fundus

  • Tae Eun Choe
  • Isaac Cohen
  • Gerard Medioni
  • Alexander C. Walsh
  • SriniVas R. Sadda
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4190)


We present a method for the 3-D shape reconstruction of the retinal fundus from stereo paired images. Detection of retinal elevation plays a critical role in the diagnosis and management of many retinal diseases. However, since the shape of ocular fundus is nearly planar, its 3-D depth range is very narrow. Therefore, we use the location of vascular bifurcations and a plane+parallax approach to provide a robust estimation of the epipolar geometry. Matching is then performed using a mutual information algorithm for accurate estimation of the disparity maps. To validate our results, in the absence of camera calibration, we compared the results with measurements from the current clinical gold standard, optical coherence tomography (OCT).


Optical Coherence Tomography Mutual Information Fundamental Matrix Stereo Image Stereo Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Choe, T.E., Cohen, I.: Registration of Multimodal Fluorescein Images Sequence of the Retina. In: ICCV 2005, pp. 106–113 (2005)Google Scholar
  2. 2.
    Choe, T.E., Cohen, I., Medioni, G.: 3-D Shape Reconstruction of Retinal Fundus. In: CVPR 2006 (2006)Google Scholar
  3. 3.
    Gluckman, J., Nayar, S.K.: Rectifying transformations that minimize resampling effects. In: IEEE Proceedings of Computer Vision and Pattern Recognition, Kauai (December 2001)Google Scholar
  4. 4.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. Alvey Vision Conf., Univ., Manchester, pp. 147–151 (1988)Google Scholar
  5. 5.
    Hirschmüller, H.: Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information. In: CVPR 2005, June 20-26, vol. 2, pp. 807–814 (2005)Google Scholar
  6. 6.
    Kim, J., Kolmogorov, V., Zabih, R.: Visual correspondence using energy minimization and mutual information. In: Proceedings of Ninth IEEE International Conference on Computer Vision, October 13-16, vol. 2, pp. 1033–1040 (2003)Google Scholar
  7. 7.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: International Conference on Computer Vision (2001)Google Scholar
  8. 8.
    Kumar, R., Anandan, P., Hanna, K.: Shape Recovery From Multiple Views: A Parallax Based Approach. In: DARPA IU Workshop, Monterey, Calif. (November 1994)Google Scholar
  9. 9.
    Longuet-Higgins, H.C.: A computer algorithm for reconstructing a scene from two projections. Nature 293, 133–135 (1981)CrossRefGoogle Scholar
  10. 10.
    Lowe, D.: Distinctive image features from scale invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  11. 11.
    Podoleanu, A.G., Rogers, J.A., Jackson, D.A.: Three dimensional images from retina and skin. Optic Express 7(9) (October 2000)Google Scholar
  12. 12.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47(1–3), 7–42 (2002)zbMATHCrossRefGoogle Scholar
  13. 13.
    Sun, J., Zheng, N.N., Shum, H.: Stereo Matching Using Belief Propagation. IEEE Trans. on PAMI 25(7) (July 2003)Google Scholar
  14. 14.
    Viola, P.A., Wells III., W.M.: Alignment by maximization of mutual information. International Journal of Computer Vision 24(2), 137–154 (1997)CrossRefGoogle Scholar
  15. 15.
    Webpage of Middlebury stereo database and source code,

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tae Eun Choe
    • 1
  • Isaac Cohen
    • 1
  • Gerard Medioni
    • 1
  • Alexander C. Walsh
    • 2
  • SriniVas R. Sadda
    • 2
  1. 1.IRISUniversity of Southern CaliforniaLos AngelesUSA
  2. 2.Doheny Eye InstituteLos AngelesUSA

Personalised recommendations