Abstract
Curve and surface thinning are widely-used skeletonization techniques for modeling objects in three dimensions. In the case of disordered porous media analysis, however, neither is really efficient since the internal geometry of the object is usually composed of both rod and plate shapes. This paper presents an alternative to compute a hybrid shape-dependant skeleton and its application to porous media. The resulting skeleton combines 2D surfaces and 1D curves to represent respectively the plate-shaped and rod-shaped parts of the object. For this purpose, a new technique based on neural networks is proposed: cascade combinations of complex wavelet transform (CWT) and complex-valued artificial neural network (CVANN). The ability of the skeleton to characterize hybrid shaped porous media is demonstrated on a trabecular bone sample. Results show that the proposed method achieves high accuracy rates about 99.78%–99.97%. Especially, CWT (2nd level)-CVANN structure converges to optimum results as high accuracy rate—minimum time consumption.
Similar content being viewed by others
References
di Baja, G. S., and Thiel, E., Computing and comparing distance-driven skeletons. World Scientific, Aspects of Visual Form Processing, pp. 465–486, 1994.
Malandain, G., and Fern’andez-Vidal, S., Euclidean skeletons. Image Vis. Comput. 16(5):317–327, 1998.
Kong, T. Y., and Rosenfeld, A., Digital topology: introduction and survey. Comput. Vis. Graph. Image Process. 48(3):357–393, 1989.
Lam, L., Lee, S.-W., and Suen, C., Thinning methodologies-a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 14:869–885, 1992.
Ma, C. M., and Sonka, M., A fully parallel 3d thinning algorithm and its applications. Comp. Vis. Image Underst. 64(3):420–433, 1996.
Palagyi, K., and Kuba, A., A 3D 6-subiteration thinning algorithm for extracting medial lines. Pattern Recogn. Lett. 19(7):613–627, 1998.
Bertrand, G., A parallel thinning algorithm for medial surfaces. Pattern Recogn. Lett. 16:979–996, 1995.
Gong, W., and Bertrand, G., A simple parallel 3D thinning algorithm. in International Conference on Pattern Recognition (ICPR), pp. 188–190, 1990.
Ma, C. M., and Wan, S. Y., A medial-surface oriented 3D two-subfield thinning algorithm. Pattern Recogn. Lett. 2(13):1439–1446, 2001.
Manzanera, A., Bernard, T., Preteux, F., and Longuet, B., Medial faces from a concise 3D thinning algorithm. in IEEE International Conference on Computer Visions (ICCV‘99), pp. 337–343, 1999.
Palagyi, K., A 3-subiteration 3D thinning algorithm for extracting medial surfaces. Pattern Recogn. Lett. 23:663–675, 2002.
Tsao, Y. F., and Fu, K. S., A parallel thinning algorithm for 3D pictures". Comp. Graph. Image Process. 17(4):315–331, 1981.
Mukherjee, J., Chatterji, B. N., and Das, P. P., Thinning of 3D images using the safe point thinning algorithm (SPTA). Pattern Recogn. Lett. 10(3):167–173, 1989.
Mukherjee, J., Das, P. P., and Chatterji, B. N., On connectivity issues of ESPTA. Pat. Recogn. Lett. 11(9):643–648, 1990.
Aufort, G., Jennane, R., and Harba, R., Hybrid skeleton graph analysis of disordered porous media. Application to trabecular bone. In Proc. IEEE Int. Conf. Acou. Spee. Sig. Proc. 2007, pp. II 781–784, May 2006, Toulouse, France.
Aufort, G., Jennane, R., Harba, R., Gasser, A., Soulat, D., and Benhamou, C. L., Nouvelle approche de modélisation de milieux poreux. Application à l’os trabéculaire. In GRETSI’05, pp. 429–432, Louvain-la-Neuve, Belgium, September 2005.
Ceylan, M., Ceylan, R., Dirgenali, F., Kara, S., and Ozbay, Y., Classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network. Comput. Biol. Med. 37:28–36, 2007.
Özbay, Y., and Ceylan, M., Effects of window types on classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network. Comput. Biol. Med. 37:287–295, 2007.
Hirose, A., (Editor), Complex-valued neural networks: Theories and applications. World Scientific, 2003.
Pande, A., and Goel, V., Complex-valued neural network in image recognition: a study on the effectiveness of radial basis function. Proceedings of World Academy of Science, engineering and Technology 20:220–225, 2007.
Beylkin, G., Coifman R., and Rokhlin, V., Fast wavelet transforms and numerical algorithms. Commun. Pure Appl. Math. 141–183,1991.
Bernard, C. P., Discrete wavelet analysis for fast optic flow computation, Techical Report, Ecole Polytechnique, 1999.
Unser, M., Texture classification and segmentation using wavelet frames. IEEE Trans. Image Process. 4:1549–1560, 1995.
Neumann, J., and Steidl, G., Dual-Tree complex wavelet transform in the frequency domain and an application to signal classification, Technical Report, University of Mannheim, 2003.
Donoho, D. L., De-noising by soft-thresholding. IEEE Trans. Inf. Theory 41:613–627, 1995.
Shukla, P. D., Complex wavelet transforms and their applications, PhD Thesis, The University of Strathclyde, 2003.
Fernandes, F., Directional, shift-insensitive, complex wavelet transforms with controllable redundancy, PhD Thesis, Rice University, 2002.
Strang, G., and Hguyen, T., Wavelets and filter banks. Wellesley-Cambridge Press, 1996.
Oppenheim, A. V., and Lim, J. S., The importance of phase in signals. Proc. IEEE 69:529–541, 1981.
Lorenzetto, G. P., and Kovesi, P., A phase based image comparison technique, DICTA99, University of Western Australia, 1999.
Driesen, J., and Belmasn, R., Time-frequency analysis in power measurement using complex wavelets. IEEE Int. Sympo. On Circuits and Systems, ISCAS2002, 681–684, 2002.
Lina, J. M., Image processing with complex daubechies wavelets Journal of Math. Imaging Vis. 7:211–223, 1997.
Bulow, T., and Sommer, G., Hypercomplex signals- a novel extension of the analytic signal to the multidimensional case. IEEE Trans. Signal Process. 49:2844–2852, 2001.
Selesnick, I. W., Baraniuk, R. G., and Kingsbury, N. G., The dual-tree complex wavelet transform. IEEE Signal Process. Mag. 22:123–151, 2005.
Georgin, N., and Koutsougeras, C., Complex domain backpropagation. IEEE Trans. CAS 39:330–334, 1992.
Nitta, T., An extension of the back-propagation algorithm to complex numbers. Elsevier Science Direct Neural Network 10:1391–1415, 1997.
Nitta, T., An analysis of the fundamental structure of complex-valued neurons. Neural Process. Lett. 12:239–246, 2000.
Haykin, S., Adaptive filter theory. Prentice Hall, 2002.
Morgenthaler, D. G., Three-dimensional simple points: serial erosion, parallel thinning and skeletonization. Tech. Rep. TR-1005, 1981.
Borgefors, G., Nystrom, I., and di Baja, G. S., Computing skeletons in three dimensions. Pattern Recogn. 32(7):1225–1236, 1999.
Aufort, G., Jennane,R., Harba, R., Gasser, A., Soulat, D., and Benhamou, C. L., Mechanical assessment of porous media using hybrid skeleton graph analysis and finite elements. Application to trabecular bone. In Proc. EUSIPCO-2007, Poznan, Poland.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jennane, R., Aufort, G., Benhamou, C.L. et al. A New Method for 3D Thinning of Hybrid Shaped Porous Media Using Artificial Intelligence. Application to Trabecular Bone. J Med Syst 36, 497–510 (2012). https://doi.org/10.1007/s10916-010-9495-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-010-9495-y