Coupled Sparse Dictionary for Depth-Based Cup Segmentation from Single Color Fundus Image

  • Arunava Chakravarty
  • Jayanthi Sivaswamy
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)


We present a novel framework for depth based optic cup boundary extraction from a single 2D color fundus photograph per eye. Multiple depth estimates from shading, color and texture gradients in the image are correlated with Optical Coherence Tomography (OCT) based depth using a coupled sparse dictionary, trained on image-depth pairs. Finally, a Markov Random Field is formulated on the depth map to model the relative depth and discontinuity at the cup boundary. Leave-one-out validation of depth estimation on the INSPIRE dataset gave average correlation coefficient of 0.80. Our cup segmentation outperforms several state-of-the-art methods on the DRISHTI-GS dataset with an average F-score of 0.81 and boundary-error of 21.21 pixels on test set against manual expert markings. Evaluation on an additional set of 28 images against OCT scanner provided groundtruth showed an average rms error of 0.11 on Cup-Disk diameter and 0.19 on Cup-disk area ratios.


Optical Coherence Tomography Ground Truth Sparse Code Optical Coherence Tomography Scanner Stereo Image Pair 
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.
    Xu, J., Chutatape, O., Sung, E., Zheng, C., Kuan, P.C.T.: Optic disk feature extraction via modified deformable model technique for glaucoma analysis. Pattern Recognition 40(7), 2063–2076 (2007)CrossRefzbMATHGoogle Scholar
  2. 2.
    Joshi, G.D., Sivaswamy, J., Krishnadas, S.R.: Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment. IEEE Trans. on Medical Imaging 30(6), 1192–1205 (2011)CrossRefGoogle Scholar
  3. 3.
    Cheng, J., Liu, J., Tao, D., Yin, F., Wong, D.W.K., Xu, Y., Wong, T.Y.: Superpixel classification based optic cup segmentation. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part III. LNCS, vol. 8151, pp. 421–428. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  4. 4.
    Hu, Z., Niemeijer, M., Lee, K., Abràmoff, M.D., Sonka, M., Garvin, M.K.: Automated segmentation of the optic disc margin in 3-d optical coherence tomography images using a graph-theoretic approach. In: SPIE Med. Imaging (2009)Google Scholar
  5. 5.
    Tang, L., Garvin, M.K., Lee, K., Alward, W.L., Kwon, Y.H., Abràmoff, M.D.: Robust multiscale stereo matching from fundus images with radiometric differences. IEEE Pattern Anal. Mach. Intel. 33(11), 2245–2258 (2011)CrossRefGoogle Scholar
  6. 6.
    Zheng, Y., Stambolian, D., O’Brien, J., Gee, J.C.: Optic disc and cup segmentation from color fundus photograph using graph cut with priors. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 75–82. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  7. 7.
    Saxena, A., Chung, S., Ng, A.: 3-d depth reconstruction from a single still image. Intl. Journal of Computer Vision 76(1), 53–69 (2008)CrossRefGoogle Scholar
  8. 8.
    Agrawal, H., Namboodiri, A.: Shape reconstruction from single relief image. In: Asian Conf. on Pattern Recognition, pp. 527–531 (2013)Google Scholar
  9. 9.
    Kruizinga, P., Petkov, N.: Nonlinear operator for oriented texture. IEEE Trans. on Image Processing 8(10), 1395–1407 (1999)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: Cue integration in image segmentation. In: ICCV. vol. 2, pp. 918–25 (1999)Google Scholar
  11. 11.
    Funt, B., Drew, M., Brockington, M.: Recovering shading from color images. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 124–132. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  12. 12.
    Tsai, P., Shah, M.: Shape from shading using linear approximation. Image and Vision Computing 12, 487–498 (1994)CrossRefGoogle Scholar
  13. 13.
    Weenink, D.: Canonical correlation analysis. In: Inst. of Phonetic Science, Univ. of Amsterdam, vol. 25, pp. 81–99 (2003)Google Scholar
  14. 14.
    Tang, Y., Yuan, Y., Yan, P., Li, X.: Single-image super-resolution via sparse coding regression. In: Intl. Conf. on Image and Graphics. pp. 267–272 (2011)Google Scholar
  15. 15.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Intl. Conf. on Machine Learning, pp. 689–696 (2009)Google Scholar
  16. 16.
    Vondrick, C., Khosla, A., Malisiewicz, T., Torralba, A.: Hoggles: Visualizing object detection features. In: Intenl. Conf. on Computer Vision, pp. 1–8 (2013)Google Scholar
  17. 17.
    Sivaswamy, J., Krishnadas, K., Joshi, G.D., Jain, M., Ujjwal, Abbas, T.S.: Drishti-GS: retinal image dataset for optic nerve head(ONH) segmentation. In: Int. Symp. on Biomed. Eng. (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Arunava Chakravarty
    • 1
  • Jayanthi Sivaswamy
    • 1
  1. 1.Center for Visual Information TechnologyInternational Institute of Information TechnologyHyderabadIndia

Personalised recommendations