Abstract
Several domains are based on image processing and analysis. One of them is the radiographic inspection which is used in Non Destructive Testing (NDT). Active contours, snakes or deformable models are powerful techniques in image segmentation and restoration. According to the term related to the input data (image to be treated) those functionals are ranked on two categories: edge-based models and region-based models. Previous studies point out the advantages of the regionbased models over edge-based models. In this paper, we discuss and we summarize the strengths and weaknesses of four implicit region-based active contour models named: Piecewise Constant PC, Piecewise Smooth PS, Local Binary Fitting LBF and Global Local fitting energy GLF. After performing several experiments, we have concluded that all the models perform well with homogeneous images. On the contrary when images are strongly inhomogeneous, the models based on global (PC) or local (LBF) statistic intensity fail to segment such images. The PS model with its great advantage in preserving the contours has, as a drawback, the high CPU time consuming. The combination of local and global statistic image intensity gives to the GLF model the ability to better deal with such images in less CPU time.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Kass, M., Witkin, A., and Terzopoulos, D., Snakes: active contour models, Int. J. Comput. Vision, 1988, pp. 321–331.
Caselles, V., Kimmel, R., and Sapiro, G., Geodesic active contours, Int. J. Comput. Vision, 1997, vol. 22, pp. 61–79.
Paragios, N. and Deriche, R., Geodesic active contours and level sets for detection and tracking of moving objects, IEEE Trans. Pattern Anal. Mach. Intell., 2000, vol. 22, pp. 1–15.
Vasilevskiy, A. and Siddiqi, K., Flux-maximizing geometric flows, IEEE Trans. Pattern Anal. Mach. Intell., 2000, vol. 24, pp. 1565–1578.
Li, C., Xu, C., Gui., and Fox, M.D., Level set evolution without re-initialization: a new variational formulation, in: IEEE Conf. Comput. Vision Pattern Recognit., San Diego, 2005.
Zhu, G., Zhang, S., Zeng, Q., and Wang, C., Boundary-based image segmentation using binary level set method, SPIE OE Lett., 2007, vol. 46.
Chan, T.F. and Vese, L.A., Active contour without edges, IEEE Trans. Image Process., 2000, vol. 10, pp. 266–277.
Ronfard, R., Region-based strategies for active contour models, Int. J. Comput. Vision, 2002, vol. 46, pp. 223–247.
Lie, J., Lysaker, M., and Tai, X.C., A binary level set model and some application to Mumford-Shah image segmentation, IEEE Trans. Image Process., 2006, vol. 15, pp. 1171–1181.
Tsai, A., Yezzi, A., and Willsky, A.S., Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification, IEEE Trans. Image Process., 2001, vol. 10, pp. 1169–1186.
Vese, L.A. and Chan, T.F., A multiphase level set framework for image segmentation using the Mumford-Shah model, Int. J. Comput. Vision, 2002, vol. 50, pp. 271–29.
Liu, H., Chen, Y., Chen, Y., and Chen, W., Neighborhood aided implicit active contours, IEEE Conf. Comp. Vision Pattern Recognit., 2006, pp. 841–848.
Wang, Z. and Vemuri, B.C., Tensor field segmentation using region based active contour model, Proc. Eighth Eur. Conf. Comput. Vision (ECCV’04), Springer Lecture, 2004, pp. 304–315.
Mumford, D. and Shah, J., Optimal approximation by piecewise smooth function and associated variational problems, Comm. Pure Appl. Math., 1989, vol. 42, pp. 577–685.
Wang, L., He, L., Mishra, A., and Li, C., Active contours driven by local Gaussian distribution fitting energy, Sci. Direct Signal Process., 2009, vol. 89, pp. 2435–2447.
Li, C., Kao, C., Gore, J., and Ding, Z., Minimization of region-scalable fitting energy for image segmentation, IEEE Trans. Image Process., 2008, vol. 17, pp. 1940–1949.
Li, C., Kao, C., Gore, J., and Ding, Z., Implicit active contour driven by local binary fitting energy, Proc. IEEE Conf. Comput. Vision Pattern Recognit. (CVPR), 2007, pp. 1–7.
Wang, Y. and He, C., Image segmentation algorithm by piecewise smooth approximation, EURASIP J. Image Video Process., 2012, pp. 1687–5281.
Zhang, H.S.K. and Zhang, L., Active contours driven by local image fitting energy, Pattern Recognit., 2010, vol. 43, pp. 1199–1206.
Wang, X.F., Huang, D., and Xu, H., An efficient local Chan-Vese model for image segmentation, Pattern Recognit., 2010, vol. 43, pp. 603–618.
Wang, H., Huang, T.Z., Xu, Z., and Wang, Y., An active contour model and its algorithms with local and global Gaussian distribution fitting energies, Inf. Sci., 2014, vol. 263, pp. 43–59.
Osher, S. and Sethian, J.A., Front propagating with curvature dependent speed: algorithm based on Hamilton- Jacobi formulations, J. Comput. Phys., 1988, vol. 79, pp. 12–49.
Aubert, G. and Kornprobst, P., Mathematical problems in image processing partial differential equations and the calculus of variations, Appl. Math. Sci., p. 147.
Nacereddine, N., Tridi, M., Hamami, L., and Ziou, D., Statistical tools for weld defect evaluation in radiographic testing, J. Nondestr. Test. Ultrason. ECNDT, 2006, pp. 1–21.
Al-Najjar, Y.A.Y. and Soong, D.C., Comparison of image quality assessment: PSNR, HVS, SSIM, UIQI, Int. J. Sci. Eng. Res., 2012, pp. 1–5.
Wang, Z. and Bovik, A., A universal image quality index, IEEE Signal Process. Lett., 2002, vol. 9, p. 81.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Rights and permissions
About this article
Cite this article
Boutiche, Y., Halimi, M. The performance of some implicit region-based active contours in segmenting and restoring welding radiographic images. Russ J Nondestruct Test 53, 731–743 (2017). https://doi.org/10.1134/S1061830917100035
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1061830917100035