Aluminum CT Image Defect Detection Based on Segmentation and Feature Extraction

  • Ning He
  • Lulu Zhang
  • Ke Lu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8518)


Industrial computed tomography (CT) scanning has been used in many areas of industry for internal inspection of components. Some of the key uses for CT scanning have been flaw detection, failure analysis, metrology, assembly analysis and reverse engineering applications. In this paper we present the approach to detecting defects follows a general image processing scheme based on three steps: segmentation, feature extractions, and classification. In the first step (segmentation), potential defects are segmented using the region method. In the step of feature extraction, two main features of the potential defects are considered: geometric and intensity features. The third step, design a proper classifier. The classifier assigns a feature vector Z to one of the two classes: regular structure or defects, that are assigned “0” and “1”, respectively. A good metric defining the similarity must be established. Experiments demonstrate that proposed method is fast and accurate to defects detection in CT image, and the method has high robustness for illumination.


CT image Defect detection Feature extraction Histograms of gradients 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ghazini, M., Monadjemi, A., Jamshidi, K.: Defect detection of tiles using 2D Wavelet transform and statistical features. World Academy of Science, Engineering & Technology 49, 901–904 (2009)Google Scholar
  2. 2.
    Sobral, J.L.: Optimized filters for texture defect detection. In: IEEE International Conference on Image Processing, pp. 565–573 (2005)Google Scholar
  3. 3.
    Alimohamdi, H., Ahmady, A.: Detecting skin defect of fruits using optimal Gabor wavelet filter. In: International Conference on Digital image Processing, pp. 402–406 (2009)Google Scholar
  4. 4.
    Kumar, A., Pang, G.: Defect Detection in tex-tural materials using Gabor filters. IEEE Transactions on Industry Applications 38(2), 425–440 (2002)CrossRefGoogle Scholar
  5. 5.
    Yin, K., Yu, W.: Image processing for the use of garment production detection System. Congress on Image and Signal Processing 3, 349–352 (2008)CrossRefGoogle Scholar
  6. 6.
    Ngan, H.Y.T., Pang, G.K.H., Yung, S.P., Ng, M.K.: Wavelet based methods on patterned fabric defect detection. Pattern Recognition 38(4), 559–576 (2005)CrossRefGoogle Scholar
  7. 7.
    Xie, J., Jiang, Y., Tsai, H.-T.: Segmentation of kidney from ultra sound images based on texture and shape priors. IEEE Transactions of Medical Imaging 24(1), 45–57 (2005)CrossRefGoogle Scholar
  8. 8.
    Chen, Y., Chen, T.-W., Chien, S.-Y.: Fast texture feature extraction method based on segmentation for image retrieval. In: 13th IEEE International Symposium on Consumer Electronics, pp. 941–942 (2009)Google Scholar
  9. 9.
    Serdaroglu, A., Ertuzun, A., Ercil, A.: Defect detection in textile fabric images using wavelet transforms and independent component analysis. Pattern Recognition and Image Analysis 16(1), 61–64 (2006)CrossRefGoogle Scholar
  10. 10.
    Thilagamani, S., Shanthi, N.: Object Recognition Based on Image Segmentation and Clustering. Journal of Computer Science 7(11), 430–436 (2011)CrossRefGoogle Scholar
  11. 11.
    Usamentiaga, R., Molleda, J., Garcia, D., et al.: Real-time line scan extraction from infrared images using the wedge method in industrial environments (2010), doi:10.1117/1.3514741Google Scholar
  12. 12.
    Usamentiaga, R., Molleda, J., García, D.F., Bulnes, F.G.: Machine Vision System for Flatness Control Feedback. In: Proceedings of the Second International Conference on ICMV, Dubai, United Arab Emirates, December 28-30, pp. 105–110 (2009)Google Scholar
  13. 13.
    Chen, L., Chen, Y., Wang, K., Zhang, Z.: Research on Automatic Detection for Defect on Bearing Cylindrical Surface. In: Proceedings of International Conference on Intelligent Control andInformation Processing, Dalian, China, August 13-15, pp. 321–323 (2010)Google Scholar
  14. 14.
    Lin, Y., Lv, F., Zhu, S., Yang, M., Cour, T., Yu, K.: Large-scale image classification: Fast feature extraction and SVM training. In: CVPR (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ning He
    • 1
  • Lulu Zhang
    • 1
  • Ke Lu
    • 2
  1. 1.Beijing Key Laboratory of Information Service EngineeringBeijing Union UniversityBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations