Advertisement

Journal of Nondestructive Evaluation

, Volume 31, Issue 2, pp 108–116 | Cite as

Texture Analysis for Flaw Detection in Ultrasonic Images

  • Ahmed Kechida
  • Redouane Drai
  • Abderrezak Guessoum
Article

Abstract

In this paper, we present two approaches for flaw detection in TOFD (Time of Flight Diffraction) images based on texture features. Texture is one of the most important features used in recognizing patterns in an image. The paper describes texture features by two methods: Multiresolution analysis such as wavelet transforms and Gabor filters bank. The two-dimensional wavelet transform is used to decompose the input image into a multiresolution framework. The textural statistical parameters are used to allow the choice of the decomposition channel. The Gabor filter is a Gaussian kernel function modulated by a sinusoidal plane wave. All Gabor filters can be generated from one mother wavelet by dilation and rotation. These filters represent an appropriate choice for tasks requiring simultaneous measurement in both space and frequency domains. The most relevant features are optimized by Principal Components Analysis (PCA) and used as input data on a Fuzzy C-Mean clustering classifier. We use two classes: ‘defects’ or ‘no defects’. The proposed approach is tested on the TOFD image achieved in an industrial field.

Keywords

Texture analysis NDE TOFD image Wavelet transform Gabor filters Fuzzy logic PCA 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Silk, M.G.: Sizing crack like defects by ultrasonic means. In: Sharpe, R.S. (ed.) Research Techniques in Non-destructive Testing, vol. III. Academic Press, New York (1977) Google Scholar
  2. 2.
    Silk, M.G.: The use of diffraction based time-of-flight measurements to locate and size defects. Brit. J. Nondestr. Test. 26, 208–213 (1984) Google Scholar
  3. 3.
    Carter, P.: Experience with the time-of-flight diffraction technique and an accompanying portable and versatile ultrasonic digital recording system. Brit. J. Nondestr. Test. 26, 354–361 (1984) Google Scholar
  4. 4.
    Verkooijen, J.: TOFD used to replace radiography. INSIGHT, 37(6), 433–435 (1995) Google Scholar
  5. 5.
    Lawson, S.W., Parker, G.A.: Automatic detection of defects in industrial ultrasound images using neural networks. In: Proceeding of SPIE, vol. 2786, pp. 37–47. SPIE, Bellingham (1996) CrossRefGoogle Scholar
  6. 6.
    da Silva, I.C., Siqueira, M.H.S.: Automatic inspection using the TOFD technique and neural networks. In: 8th European Conference in Non Destructive Testing, ECNDT, Barcelona (2002) Google Scholar
  7. 7.
    Shekhar, C., Shitole, N.: Combining fuzzy logic and neural networks in classification of weld defects using ultrasonic time of flight diffraction. In: 45th Annual British Conference on NDT, NDT 2006, Stratford-upon-Avon, UK, September (2006) Google Scholar
  8. 8.
    Meksen, T.M., Boudraa, B., Drai, R., Boudraa, M.: Automatic crack detection and characterization during ultrasonic inspection. J. Nondestruct. Eval. 29, 169–174 (2010) CrossRefGoogle Scholar
  9. 9.
    Mallat, S.G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 11, 674–693 (1989) MATHCrossRefGoogle Scholar
  10. 10.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC-3(6), 610–621 (1973) CrossRefGoogle Scholar
  11. 11.
    Kumar, A., Pang, G.K.H.: Defect detection in textured materials using Gabor filters. IEEE Trans. Ind. Appl. 38(2), 425–440 (2002) CrossRefGoogle Scholar
  12. 12.
    Sophian, A., Sian, G., Taylor, D., Rudlin, J.: Feature extraction technique based on principal component analysis for pulsed eddy current NDT. NDT E Int. 36, 37–41 (2003) CrossRefGoogle Scholar
  13. 13.
    Friedman, M., Kandel, A.: Introduction to the Pattern Recognition, Statistical, Structural, Neural and Fuzzy Logic Approaches. Imperial College Press, London (1999) Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Ahmed Kechida
    • 1
  • Redouane Drai
    • 1
  • Abderrezak Guessoum
    • 2
  1. 1.Image and Signal Processing LaboratoryCentre de Recherche Scientifique et Technique en Soudage et Contrôle (CSC)ChéragaAlgeria
  2. 2.Département d’Electronique, Faculté des sciences de l’ingénieurUniversité Sâad Dahlab de BlidaBlidaAlgeria

Personalised recommendations