New anisotropic diffusion method to improve radiographic image quality
Keywords:
weld radiography, anisotropic diffusion, image enhancement, adaptive diffusion flow, gradient vector flowAbstract
In non destructive testing NDT area radiography imaging is widely used for defect inspection, due to the low contrast and the high level of noise, analysis of this kind of images becomes a difficult task. In the last decade anisotropic diffusion methods are extensively studied in image processing for noise reduction and image enhancement however, problem of eliminating noise without blurring important image structures remains difficult particularly for low contrasted images. This paper presents a new non linear diffusion method based on adaptive diffusion flow ADF, this model remove noise while preserving weak image boundaries. Experimental results on different synthetic and welding radiography images confirm the efficiency and robustness in comparison with other methods.
References
D. Mery and M. A. Berti, “Automatic detection of welding defects using texture features,” Insight, X-Ray Image Processing, vol. 45, pp. 676-681, October 2003.
Carrasco M.A., Mery, D. (2004): Segmentation of welding defects using a robust algorithm. Materials Evaluation, 62(11):1142-1147, 2004.
Ben Mhamed I, Abid S and Fnaiech F : “Weld defect detection using a modified anisotropic diffusion model” Journal on Advances in Signal Processing vol. 46 2012.
Perona A. Malik J.: Scale-space and edge detection using anisotropic diffusion, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.12, no.7, 629 – 639. (1990).
Osher S. J., Rudin L. I.: Feature-oriented image enhancement using shock filters, SIAM Journal of Numerical Analysis, vol.27, no.4, 919–940. (1990).
Rudin L. I., Osher S., Fatemi E.: Nonlinear total variation based noise removal algorithms, Physical D, vol.60, 259–268, (1992).
Alvarez L., Lions P. L., Morel J.M.: Image selective smoothing and edge detection by nonlinear diffusion. II, SIAM Journal on Numerical Analysis, vol.29, no.3. 845–846. (1992).
Alvarez L., Mazora L.: Signal and image restoration using shock filters and anisotropic diffusion, SIAM Journal of Numerical Analysis, vol.31, no.2, 590-605. (1994).
J. Weickert. Coherence-enhancing diffusion of colour images. Image and Vision Computing, 17(3–4):199–210, Mar. 1999.
J. Weickert. Coherence-enhancing diffusion filtering. International Journal of Computer Vision, 31(2/3):111–127, Apr. 1999.
Xu C., Prince J. L.: Snakes, shapes, and gradient vector flow, IEEE Trans. On Image Processing, vol.7, no.3, 359-69. (1998)
Yu H., Chua C.S.: GVF-based anisotropic diffusion models, IEEE Trans. on Image Processing, vol.15, no.6, 1517–1524. (2006)
Ghita O., Whelan P. F.: A new GVF-based image enhancement formulation for use in the presence of mixed noise, Pattern Recognition, vol.43, 2646-2658. (2010).
Y. Wu, Y. Wang, Y. Jia : Adaptive diffusion flow active contours for image segmentation. Computer Vision and Image Understanding 117 (2013) 1421–1435.
J. Sauvola and M. Pietikainen, Adaptive document image binarization, Pattern Recognition 33, 2000.
