Detecting Edges from Non-uniform Fourier Data via Sparse Bayesian Learning

Abstract

In recent investigations, the problem of detecting edges given non-uniform Fourier data was reformulated as a sparse signal recovery problem with an \(\ell _1\)-regularized least squares cost function. This result can also be derived by employing a Bayesian formulation. Specifically, reconstruction of an edge map using \(\ell _1\) regularization corresponds to a so-called type-I (maximum a posteriori) Bayesian estimate. In this paper, we use the Bayesian framework to design an improved algorithm for detecting edges from non-uniform Fourier data. In particular, we employ what is known as type-II Bayesian estimation, specifically a method called sparse Bayesian learning. We also show that our new edge detection method can be used to improve downstream processes that rely on accurate edge information like image reconstruction, especially with regards to compressed sensing techniques.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Notes

  1. 1.

    Note that while here we only explicitly consider non-uniform Fourier samples, all methods described here apply to uniform Fourier samples as well.

  2. 2.

    Although ideally the \(\ell _0\) semi-norm should be used to regularize this problem, the resulting optimization problem is NP-hard. Hence the \(\ell _1\) norm has become a popular convex surrogate that makes the problem computationally tractable and also offers theoretical guarantees for exact reconstruction [8], as well as a variety of other benefits related to compressed sensing [14].

  3. 3.

    A complete derivation explaining how approximating periodic piecewise smooth functions as sums of scaled and shifted ramp functions can be effectively used to design concentration factors from uniform Fourier coefficients can be found in [36].

  4. 4.

    This is not generally the case given the definition of \({\mathbf {y}}\) in (38). However by construction of (14), if \(\lambda _k\) is close to k, that is, our samples are nearly uniform in the Fourier domain, \({\mathbf B}\) will be diagonally dominant. Hence adopting the probabilistic approach seems reasonable. We also note that it is discussed in [25] that this assumption may not hold. Future investigations will consider the covariance structure in \({\mathbf y}\).

  5. 5.

    All computations were performed on a MacBook Air with a 1.7 GHz Intel Core i5 processor and 4 GB of memory.

References

  1. 1.

    Archibald, R., Gelb, A., Platte, R.B.: Image reconstruction from undersampled Fourier data using the polynomial annihilation transform. J. Sci. Comput. 67(2), 432–452 (2016)

    MathSciNet  Article  MATH  Google Scholar 

  2. 2.

    Archibald, R., Gelb, A., Yoon, J.: Polynomial fitting for edge detection in irregularly sampled signals and images. SIAM J. Numer. Anal. 43(1), 259–279 (2005)

    MathSciNet  Article  MATH  Google Scholar 

  3. 3.

    Babacan, S.D., Molina, R., Katsaggelos, A.K.: Parameter estimation in TV image restoration using variational distribution approximation. IEEE Trans. Image Process. 17(3), 326–339 (2008)

    MathSciNet  Article  Google Scholar 

  4. 4.

    Babacan, S.D., Molina, R., Katsaggelos, A.K.: Bayesian compressive sensing using laplace priors. IEEE Trans. Image Process. 19(1), 53–63 (2010)

    MathSciNet  Article  MATH  Google Scholar 

  5. 5.

    Berger, J.O.: Statistical Decision Theory and Bayesian Analysis. Springer, Berlin (2013)

    Google Scholar 

  6. 6.

    Bernardo, J.M., Smith, A.F.: Bayesian theory (2001)

  7. 7.

    Bishop, C.: Pattern Recognition and Machine Learning. Springer, Berlin (2006)

    Google Scholar 

  8. 8.

    Candès, E.J., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52(2), 489–509 (2006)

    MathSciNet  Article  MATH  Google Scholar 

  9. 9.

    Candes, E.J., Wakin, M.B., Boyd, S.P.: Enhancing sparsity by reweighted \(\ell _1\) minimization. J. Fourier Anal. Appl. 14(5), 877–905 (2008)

    MathSciNet  Article  MATH  Google Scholar 

  10. 10.

    Chartrand, R., Yin, W.: Iteratively reweighted algorithms for compressive sensing. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008, pp. 3869–3872. IEEE, New York (2008)

  11. 11.

    Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM Rev. 43(1), 129–159 (2001)

    MathSciNet  Article  MATH  Google Scholar 

  12. 12.

    Churchill, V., Archibald, R., Gelb, A.: Edge-adaptive \(\ell _2\) regularization image reconstruction from non-uniform Fourier data. Preprint. arXiv:1811.08487 (2018)

  13. 13.

    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodol.) 39, 1–38 (1977)

    MathSciNet  MATH  Google Scholar 

  14. 14.

    Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)

    MathSciNet  Article  MATH  Google Scholar 

  15. 15.

    Faul, A.C., Tipping, M.E.: Analysis of sparse Bayesian learning. In: Advances in Neural Information Processing Systems, pp. 383–389 (2002)

  16. 16.

    Gelb, A., Hines, T.: Detection of edges from nonuniform Fourier data. J. Fourier Anal. Appl. 17(6), 1152–1179 (2011)

    MathSciNet  Article  MATH  Google Scholar 

  17. 17.

    Gelb, A., Song, G.: A frame theoretic approach to the nonuniform fast Fourier transform. SIAM J. Numer. Anal. 52(3), 1222–1242 (2014)

    MathSciNet  Article  MATH  Google Scholar 

  18. 18.

    Gelb, A., Song, G.: Detecting edges from non-uniform Fourier data using Fourier frames. J. Sci. Comput. 71(2), 737–758 (2017)

    MathSciNet  Article  MATH  Google Scholar 

  19. 19.

    Gelb, A., Tadmor, E.: Detection of edges in spectral data. Appl. Comput. Harm. Anal. 7(1), 101–135 (1999)

    MathSciNet  Article  MATH  Google Scholar 

  20. 20.

    Gelman, A., Carlin, J.B., Stern, H.S., Dunson, D.B., Vehtari, A., Rubin, D.B.: Bayesian Data Analysis, vol. 2. CRC Press, Boca Raton (2014)

    Google Scholar 

  21. 21.

    Giri, R., Rao, B.D.: Type I and type II Bayesian methods for sparse signal recovery using scale mixtures. IEEE Trans. Signal Process. 64(13), 3418–3428 (2016)

    MathSciNet  Article  MATH  Google Scholar 

  22. 22.

    Grant, M., Boyd, S.: Graph implementations for nonsmooth convex programs. In: Blondel, V., Boyd, S., Kimura, H. (eds.) Recent Advances in Learning and Control, Lecture Notes in Control and Information Sciences, pp. 95–110. Springer, Berlin (2008). http://stanford.edu/~boyd/graph_dcp.html

  23. 23.

    Grant, M., Boyd, S.: CVX: Matlab software for disciplined convex programming, version 2.1. http://cvxr.com/cvx (2014)

  24. 24.

    Guo, W., Yin, W.: Edge guided reconstruction for compressive imaging. SIAM J. Imaging Sci. 5(3), 809–834 (2012)

    MathSciNet  Article  MATH  Google Scholar 

  25. 25.

    Ji, S., Xue, Y., Carin, L.: Bayesian compressive sensing. IEEE Trans. Signal Process. 56(6), 2346–2356 (2008)

    MathSciNet  Article  MATH  Google Scholar 

  26. 26.

    Jiménez-Alaniz, J.R., Medina-Bañuelos, V., Yáñez-Suárez, O.: Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information. IEEE Trans. Med. Imaging 25(1), 74–83 (2006)

    Article  Google Scholar 

  27. 27.

    Martinez, A., Gelb, A., Gutierrez, A.: Edge detection from non-uniform Fourier data using the convolutional gridding algorithm. J. Sci. Comput. 61(3), 490–512 (2014)

    MathSciNet  Article  MATH  Google Scholar 

  28. 28.

    Rao, B.D., Wipf, D.P.: Comparing the effects of different weight distributions on finding sparse representations. In: Advances in Neural Information Processing Systems, pp. 1521–1528 (2006)

  29. 29.

    Shattuck, D.W., Sandor-Leahy, S.R., Schaper, K.A., Rottenberg, D.A., Leahy, R.M.: Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13(5), 856–876 (2001)

    Article  Google Scholar 

  30. 30.

    Song, G., Gelb, A.: Approximating the inverse frame operator from localized frames. Appl. Comput. Harm. Anal. 35(1), 94–110 (2013)

    MathSciNet  Article  MATH  Google Scholar 

  31. 31.

    Stefan, W., Viswanathan, A., Gelb, A., Renaut, R.: Sparsity enforcing edge detection method for blurred and noisy Fourier data. J. Sci. Comput. 50(3), 536–556 (2012)

    MathSciNet  Article  MATH  Google Scholar 

  32. 32.

    Tadmor, E., Zou, J.: Three novel edge detection methods for incomplete and noisy spectral data. J. Fourier Anal. Appl. 14(5–6), 744 (2008)

    MathSciNet  Article  MATH  Google Scholar 

  33. 33.

    Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B (Methodol.) 58, 267–288 (1996)

    MathSciNet  MATH  Google Scholar 

  34. 34.

    Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 1(Jun), 211–244 (2001)

    MathSciNet  MATH  Google Scholar 

  35. 35.

    Tipping, M.E., Faul, A.C., et al.: Fast marginal likelihood maximisation for sparse Bayesian models. In: AISTATS (2003)

  36. 36.

    Viswanathan, A., Gelb, A., Cochran, D.: Iterative design of concentration factors for jump dection. J. Sci. Comput. 51, 631–649 (2012)

    MathSciNet  Article  MATH  Google Scholar 

  37. 37.

    Viswanathan, A., Gelb, A., Cochran, D.: Iterative design of concentration factors for jump detection. J. Sci. Comput. 51(3), 631–649 (2012)

    MathSciNet  Article  MATH  Google Scholar 

  38. 38.

    Wipf, D.P., Rao, B.D.: Sparse Bayesian learning for basis selection. IEEE Tran. Signal Process. 52(8), 2153–2164 (2004)

    MathSciNet  Article  MATH  Google Scholar 

  39. 39.

    Wipf, D.P., Rao, B.D.: \(\ell _0\)-norm minimization for basis selection. In: Advances in Neural Information Processing Systems, pp. 1513–1520 (2005)

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Victor Churchill.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This work is supported in part by the Grants NSF-DMS 1502640, NSF-DMS 1732434, and AFOSR FA9550-18-1-0316.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Churchill, V., Gelb, A. Detecting Edges from Non-uniform Fourier Data via Sparse Bayesian Learning. J Sci Comput 80, 762–783 (2019). https://doi.org/10.1007/s10915-019-00955-w

Download citation

Keywords

  • Edge detection
  • Non-uniform Fourier data
  • Sparse Bayesian learning
  • Signal reconstruction
  • Regularization

Mathematics Subject Classification

  • 94A12
  • 62F15
  • 62J05
  • 65F22