Fault Detection of Ceramic Imaging using ART2 Algorithm

ART2 알고리즘을 이용한 세라믹 영상에서의 결함 검출

  • Kim, Kwang Baek (Division of Computer and Information Engineering, Silla University)
  • Received : 2013.10.01
  • Accepted : 2013.11.06
  • Published : 2013.11.30


There are invisible defects by naked eyes in ceramic material images such as internal stomata, cracks and foreign substances. In this paper we propose a method to detect and extract such defects from ceramic pipe weld zone by applying ART2 learning. In pre-processing, we apply Ends-in Search Stretching to enhance the intensity and then perform fuzzy binarization with triangle type membership function followed by enhanced ART2 that interacts with random input patterns to extract such invisible defects. The experiment verifies that this proposed method is sufficiently effective.


  1. Korea Society for Nondestructive Testing [Internet]. Available:
  2. S. W. Hwang, S. M. Lee, K. B. Kim, Y. W. Woo, "Analysis of Non-Destructive Flaws in Ceramic Images", The Korean Institute of Information and Communication Sciences, vol. 17, no. 1, pp. 361, 2013.
  3. K. B. Kim, Y. W. Woo, "Detection of Flaws in Ceramic Materials Using Non-Destructive Testing," The Institute of Electronic Communication and Sciences, vol.5, no.3, pp. 321-326, 2010.
  4. G. A. Capenter, S. Grossberg. "ART2: self-organization of stable category recognition for analog input patterns," OPTICS, vol. 26, no. 23, pp. 4919-4930, 1897.
  5. K. B. Kim, S. Park, "Passport Recognition Using Enhanced ART2-based RBF Neural Networks," International Journal of Computer Science and Network Security, vol. 6, no. 7A, pp. 12-17, 2006.
  6. H. J. Zimmerman, Fuuzy Set Theory and Its Applications, Kluwer Academic Publishers, 1991.
  7. J. H. Kim, M. S. Han, Y. W. Woo, K. B Kim, "Various Fault Detection of Ceramic Image using ART2," Proceedings of ISCI Summer Conference, vol. 21, no. 2, pp. 271-273, 2013.