Probabilistic deformable models for weld defect contour estimation in radiography

• Autorzy: Nacereddine N. , Hamami L. , Ziou D. , Tridi M.
• Konferencja: International Conference on Computer Vision and Graphics ICCVG 2006 (25-27.09.2006 ; Warsaw, Poland)
• Języki publikacji: EN

Abstrakty

EN

This paper describes a novel method for segmentation of weld defect in radiographic images. Contour estimation is formulated as a statistical estimation problem, where both the contour and the observation model parameters are unknown. Our approach can be described as a region-based maximum likelihood formulation of parametric deformable contours. This formulation provides robustness against the poor image quality, and allows simultaneous estimation of the contour parameters together with other parameters of the model. Implementation is performed by a deterministic iterative algorithm with minimal user intervention. Results testify very good performance of such contour estimation approach.

Słowa kluczowe

EN

Gaussian distributions; Rayleigh distributions; contour estimation; maximum likelihood; parametric deformable contours

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2006
• Tom: Vol. 15, No. 3/4
• Strony: 547--556
• Opis fizyczny: Bibliogr. 12 poz., il., tab.

Twórcy

autor

Nacereddine N.

autor

Hamami L.

autor

Ziou D.

autor

Tridi M.

• Sign. and Imag. Proc. Laboratory, Research Center in Welding and NDT Route de Dely-Ibrahim, BP 64, Cheraga, 16600 Algiers, Algeria,

Bibliografia

• [1] Kass M., Witkin A., Terzopoulos D.: Snakes: Active contour models, Internat. Journ. Comput. And Vision, 1(4), 321-331, 1988.
• [2] Lee E. T. Y.: Choosing nodes in parametric curve interpolation, Computer-Aided Design, 21, 363-370, 1989.
• [3] Figueiredo M., Leitao J.: Bayesian Estimation of Ventricular Contours in Angiographie Images. IEEE Trans. Medical Imaging, 11(3), 416-429, 1992.
• [4] Chesnaud C., Réfégier P., Boulet V.: Statistical region snake-based segmentation adapted to different physical noise models. IEEE Trans. PAMI, 21(11), 1145-1157, 1999.
• [5] Figueiredo M., Leitao J., Jain A. K.: Unsupervised contour representation and estimation using B-Splines and a minimum description length criterion. IEEE Trans. Image Process., 9(6), 1075-1087, 2000.
• [6] Kompatsiaris I., Tzovaras D., Koutkias V., Strintzis M. G.: Deformable boundary detection of stents in angiographie images. IEEE Trans. on Medical Imaging, 19(6), 652-662.
• [7] Bentabet L., Jodouin S., Ziou D., Vaillancourt J.: Road vectors update using SAR imagery: A Snake-Based Method. IEEE Trans. on Geoscience and Remote Sensing, 41(8), 1787-1803, 2003.
• [8] De Carvalho A. et al.: Evaluation of the relevant features of welding defects in radiographie inspection. Materials Research, 6(3),427-432.
• [9] Schwartz Ch.: Automatic evaluation of welded joints using image processing on radiographs. Conference Proceedings of American Institute of Physics; 657, 689-694, 2003.
• [10] Portilla J., Simoncelli P. E.: Image restoration using gaussian scale mixtures in the wavelet domain. 9th IEEE Conference on Image Processing, Barcelona, Spain, 2003.
• [11] Jardim S. V. B., Figueiredo M.: Segmentation of fetal ultrasound images. Ultrasound in Medicine and Biology, 31(2), 243-250, 2005.
• [12] Tridi M., Nacereddine N., Oucief N.: Contour estimation in synthetic and real weld defect images based on maximum likelihood. Transactions on Enformatika, Systems Sciences and Engineering; 9, 195-198, 2005.