Adaptive and Statistical Polygonal Curve for Multiple Weld Defects Detection in Radiographic Images

With the advances in computer science and artificial intelligence techniques, the opportunity to develop computer aided technique for radiographic inspection in Non Destructive Testing arose. This paper presents an adaptive probabilistic region-based deformable model using an explicit representation that aims to extract automatically defects from a radiographic film. To deal with the height computation cost of such model, an adaptive polygonal representation is used and the search space for the greedy-based model evolution is reduced. Furthermore, we adapt this explicit model to handle topological changes in presence of multiple defects.

[1]  Jerry L. Prince,et al.  Snakes, shapes, and gradient vector flow , 1998, IEEE Trans. Image Process..

[2]  Rémi Ronfard,et al.  Region-based strategies for active contour models , 1994, International Journal of Computer Vision.

[3]  Mário A. T. Figueiredo,et al.  Segmentation of fetal ultrasound images. , 2005, Ultrasound in medicine & biology.

[4]  Thierry Blu,et al.  Efficient energies and algorithms for parametric snakes , 2004, IEEE Transactions on Image Processing.

[5]  Hadj Batatia,et al.  Robust B-spline Snakes For Ultrasound Image Segmentation , 2004, Computers in Cardiology, 2004.

[6]  John Porrill,et al.  Active region models for segmenting medical images , 1994, Proceedings of 1st International Conference on Image Processing.

[7]  Wael Abd-Almageed,et al.  Kernel snakes: non-parametric active contour models , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[8]  Subhasis Chaudhuri,et al.  On Stabilisation of Parametric Active Contours , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  R Halmshaw,et al.  Introduction to the Non-Destructive Testing of Welded Joints , 1997 .

[10]  Christophe Collewet,et al.  Polar snakes: A fast and robust parametric active contour model , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[11]  Aicha-Baya Goumeidane,et al.  Bayesian Pressure Snake for Weld Defect Detection , 2009, ACIVS.

[12]  Bing Li,et al.  Active Contour External Force Using Vector Field Convolution for Image Segmentation , 2007, IEEE Transactions on Image Processing.

[13]  Jean-Christophe Olivo-Marin,et al.  Coupled parametric active contours , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Wael Abd-Almageed,et al.  Mixture models for dynamic statistical pressure snakes , 2002, Object recognition supported by user interaction for service robots.

[15]  Latifa Hamami,et al.  Region-based active contour with adaptive B-spline. Application in radiographic weld inspection , 2010 .

[16]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[17]  J.M.B. Dias,et al.  Adaptive Bayesian Contour Estimation: A Vector Space Representation Approach , 1999 .

[18]  Bing Li,et al.  Automatic Active Model Initialization via Poisson Inverse Gradient , 2008, IEEE Transactions on Image Processing.

[19]  Hua Zhang,et al.  Image Segmentation Using Active Contours With Normally Biased GVF External Force , 2010, IEEE Signal Processing Letters.

[20]  Christophe Chesnaud,et al.  Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models , 1999, IEEE Trans. Pattern Anal. Mach. Intell..