Research Papers

Inverse Surfacelet Transform for Image Reconstruction With Constrained-Conjugate Gradient Methods

[+] Author and Article Information
Wei Huang

School of Mechanical Engineering,
Georgia Institute of Technology,
Atlanta, GA 30332
e-mail: whuang47@gatech.edu

Yan Wang

School of Mechanical Engineering,
Georgia Institute of Technology,
Atlanta, GA 30332
e-mail: yan.wang@me.gatech.edu

David W. Rosen

School of Mechanical Engineering,
Georgia Institute of Technology,
Atlanta, GA 30332
e-mail: david.rosen@me.gatech.edu

1Corresponding author.

Contributed by the Computers and Information Division of ASME for publication in the JOURNAL OF Computing AND INFORMATION SCIENCE IN ENGINEERING. Manuscript received September 11, 2013; final manuscript received December 20, 2013; published online March 7, 2014. Assoc. Editor: Charlie C.L. Wang.

J. Comput. Inf. Sci. Eng 14(2), 021005 (Mar 07, 2014) (10 pages) Paper No: JCISE-13-1176; doi: 10.1115/1.4026376 History: Received September 11, 2013; Revised December 20, 2013

Image reconstruction is the transformation process from a reduced-order representation to the original image pixel form. In materials characterization, it can be utilized as a method to retrieve material composition information. In our previous work, a surfacelet transform was developed to efficiently represent boundary information in material images with surfacelet coefficients. In this paper, new constrained-conjugate-gradient based image reconstruction methods are proposed as the inverse surfacelet transform. With geometric constraints on boundaries and internal distributions of materials, the proposed methods are able to reconstruct material images from surfacelet coefficients as either lossy or lossless compressions. The results between the proposed and other optimization methods for solving the least-square error inverse problems are compared.

Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.


Radon, J., 1986, “On the Determination of Functions from their Integral Values Along Certain Manifolds,” IEEE Trans. Med. Imaging, 5(2), pp. 170–176. [CrossRef] [PubMed]
Hough, P. V. C., 1959, “Machine Analysis of Bubble Chamber Pictures,” Proceeding of International Conference High Energy Accelerators and Instrumentation.
Duda, R. O., and Hart, P. E., 1972, “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Comm. ACM, 15, pp. 11–15. [CrossRef]
Wang, Y., and Rosen, D. W., 2010, “Multiscale Heterogeneous Modeling With Surfacelets,” Comput.-Aided Des. Appl., 7, pp. 759–776.
Tam, K. C., and Perez-Mendez, V., 1981, “Tomographical Imaging With Limited-Angle Input,” J. Opt. Soc. Amer., 71(5), pp. 582–592. [CrossRef]
Kawata, S., and Nalcioglu, O., 1985, “Constrained Iterative Reconstruction by the Conjugate Gradient Method,” IEEE Trans. Med. Imaging, 4, pp. 65–71. [CrossRef] [PubMed]
Bracewell, R. N., 1990, “Numerical Transforms,” Science, 248(4956), pp. 697–704. [CrossRef] [PubMed]
Leavers, V. F., and Boyce, J. F., 1987, “The Radon Transform and Its Application to Shape Parametrization in Machine Vision,” Image Vision Comput., 5(2), pp. 161–166. [CrossRef]
Jeong, N., Rosen, D. W., and Wang, Y., 2013, “A Comparison of Surfacelet-Based Method for Recognizing Linear Geometric Features in Material Microstructure,” Proceeding of IDETC2013, Portland, Oregon, August 4–7, DETC2013-13370.
Rosen, D. W., Jeong, N., and Wang, Y., 2013, “A Method for Reverse Engineering of Material Microstructure for Heterogeneous CAD,” Comput.-Aided Des., 45(7), pp. 1068–1078 [CrossRef]
Ballard, D. H., 1981, “Generalizing the Hough Transform to Detect Arbitrary Shapes,” Pattern Recognit., 13(2), pp. 111–122. [CrossRef]
Niezgoda, S. R., and Kalidindi, S. R., 2010, “Applications of the Phase-Coded Generalized Hough Transform to Feature Detection, Analysis, and Segmentation of Digital Microstructures,” Comput., Mater., Contin., 14(2), pp. 79–98.
Donoho, D., 1999, “Wedgelets: Nearly Minimax Estimation of Edges,” Ann. Stat., 27(3), pp. 895–897. [CrossRef]
Candèsand, E. J., and Donoho, D. L., 2002, “Recovering Edges in Ill-Posed Inverse Problems: Optimality of Curvelet Frames,” Ann. Stat., 30(3), pp. 784–842. [CrossRef]
Candès, E. J., 1998, “Ridgelets: Theory and Applications,” Ph.D. dissertation, Stanford University, Stanford, CA.
Do, M. N., and Vetterli, M., 2005, “The Contourlet Transform: An Efficient Directional Multiresolution Image Representation,” IEEE Trans. Image Process., 14(12), pp. 2091–2106. [CrossRef] [PubMed]
Donoho, D. L., and Huo, X., 2002, “Beamlets and Multiscale Image Analysis,” Multiscale and Multiresolution Methods: Theory and Applications, T. J.Barth, T.Chan, and R.Haimes, Eds., Springer, Berlin Heidelberg, pp. 149–196.
Huo, X., 2005, “Beamlets and Multiscale Modeling,” Entry for the 2nd Edition of Encyclopedia of Statistical Sciences, C. B.Read, N.Balakrishnan, and B.Vidakovic, Eds., Wiley & Sons, NJ.
Willett, R. M., and Nowak, R. D., 2003, “Platelets: A Multiscale Approach for Recovering Edges and Surfaces in Photon-Limited Medical Imaging,” IEEE Trans. Med. Imaging, 22(3), pp. 332–350. [CrossRef] [PubMed]
Ying, L., Demanet, L., and Candès, E., 2005, “3D Discrete Curvelet Transform,” Proceeding of SPIE Conference Wavelet Applications in Signal & Image Processing, San Diego, CA, p. 5914.
Lu, Y. M., and Do, M. N., 2007, “Multidimensional Directional Filter Banks and Surfacelets,” IEEE Trans. Image Process., 16(4), pp. 918–931. [CrossRef] [PubMed]
Chandrasekaran, V., Wakin, M. B., Baron, D., and Baraniuk, R. G., 2009, “Representation and Compression of Multidimensional Piecewise Functions Using Surflets,” IEEE Trans. Inf. Theory, 55(1), pp. 374–400. [CrossRef]
Scales, J. A., 1987, “Tomographic Inversion Via the Conjugate Gradient Method,” Geophysics, 52(2), pp. 179–185. [CrossRef]
Piccolomini, E. L., and Zama, F., 1999, “Conjugate Gradient Regularization Method in Computed Tomography Problems,” Appl. Math. Comput., 102(1), pp. 87–99. [CrossRef]
Qiu, W., Titley-Peloquin, D., and Soleimani, M., 2012, “Blockwise Conjugate Gradient Methods for Image Reconstruction in Volumetric CT,” Comput. Methods Program Biomed., 108(2), pp. 669–678. [CrossRef]
Arunprasath, T., Rajasekaran, M. P., Kannan, S., and Kalasalingam, V. A., 2012, “Reconstruction of PET Brain Image Using Conjugate Gradient Algorithm,” Proceedings of 2012 World Congress on Information and Communication Technologies, Oct. 30 2012-Nov. 2 2012, Trivandrum, India, pp. 73–78. [CrossRef]
Shariff, M. H. B. M., 1995, “A Constrained Conjugate Gradient Method and the Solution of Linear Equations,” Comput. Math. Appl., 30(11), pp. 25–37. [CrossRef]


Grahic Jump Location
Fig. 1

The process of coupled surfacelet transform and inverse surfacelet transform

Grahic Jump Location
Fig. 2

Geometric interpretation of surfacelets

Grahic Jump Location
Fig. 3

The full and down-sized images of nano-fiber composites

Grahic Jump Location
Fig. 4

The original nine parallel images of nano-fiber composites for reconstruction

Grahic Jump Location
Fig. 5

The cylinderlet overlapped with a fiber surface has the maximum integral

Grahic Jump Location
Fig. 6

Reconstruction results of soft boundary constraints with the least-square method

Grahic Jump Location
Fig. 7

Reconstruction results of soft boundary constraints with the conjugate gradient method

Grahic Jump Location
Fig. 8

Reconstruction results of soft fiber boundary and inner constraints

Grahic Jump Location
Fig. 9

Reconstruction results of rigid fiber boundary constraints

Grahic Jump Location
Fig. 10

Full reconstruction results of rigid fiber boundary constraints in the case of Q=25 × 25 × 3=1875. The error is e = 13.2.

Grahic Jump Location
Fig. 11

Reconstruction results of rigid fiber boundary and inner constraints

Grahic Jump Location
Fig. 12

Reconstruction results of semi-rigid constraints with penalty weights for boundary pixels equal to 1 × 1010 and for inner pixels equal to 10. The error is e = 13.2.

Grahic Jump Location
Fig. 13

Reconstruction results of semi-rigid constraints with penalty weights for boundary pixels equal to 1 × 1010 and for inner pixels equal to 1 × 103. The error is e = 12.9.

Grahic Jump Location
Fig. 14

Reconstruction results of semi-rigid constraints with penalty weights for both boundary and inner pixels equal to 1 × 1010. The error is e = 16.5.

Grahic Jump Location
Fig. 15

Reconstruction results of Quasi-Newton method with line search with fiber boundary constraints

Grahic Jump Location
Fig. 16

Reconstruction result (the first image only) based on the object-boundary constraint in Kawata and Nalcioglu [6]



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In