Recognition of Concrete Surface Cracks Using ART2-Based Radial Basis Function Neural Network

  • Kwang-Baek Kim
  • Hwang-Kyu Yang
  • Sang-Ho Ahn
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3982)


In this paper, we proposed the image processing techniques for extracting the cracks in a concrete surface crack image and the ART2-based radial basis function neural network for recognizing the directions of the extracted cracks. The image processing techniques used are the closing operation of morphological techniques, the Sobel masking used to extract edges of the cracks, and the iterated binarization for acquiring the binarized image from the crack image. The cracks are extracted from the concrete surface image after applying two times of noise reduction to the binarized image. We proposed the method for automatically recognizing the directions (horizontal, vertical, -45 degree, 45 direction degree) of the cracks with the ART2-based RBF(Radial Basis Function) neural network. The proposed ART2-based RBF neural network applied ART2 to the learning between the input layer and the middle layer and the Delta learning method to the learning between the middle layer and the output layer. The experiments using real concrete crack images showed that the cracks in the concrete crack images were effectively extracted and the proposed ART2-based RBF neural network was effective in the recognition of the extracted cracks directions.


Middle Layer Radial Basis Function Neural Network Image Processing Technique Concrete Surface Crack Detection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lee, B.Y., Kim, Y.Y., Kim, J.K.: Development of Image Processing for Concret Surface Cracks by Employing Enhanced Binarization and Shape Analysis Technique. Journal of the Korea Concrete Institute 17(3), 361–368 (2005)CrossRefGoogle Scholar
  2. 2.
    Lee, B.Y., Park, Y.D., Kim, J.K.: A Technique for Pattern Recognition of Concrete Surface Cracks. Journal of the Korea Concrete Institute 17(3), 369–374 (2005)CrossRefGoogle Scholar
  3. 3.
    Kim, Y.S., Haas, C.T.: An Algorithm for Automatic Crack Detection, Mapping and Representation. KSCE Journal of Civil Engineering 4(2), 103–111 (2000)Google Scholar
  4. 4.
    Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital Image Processing. Pearson Prentice Hall, London (2004)Google Scholar
  5. 5.
    Pitas, I.: Digital Image Processing Algorithms and Applications. John Wiley & Sons INC, Chichester (2000)Google Scholar
  6. 6.
    Panchapakesan, C., Ralph, D., Palaniswami, M.: Effects of Moving the Centers in an RBF Network. In: Proceedings of IJCNN, vol. 2, pp. 1256–1260 (1998)Google Scholar
  7. 7.
    Kim, K.B., Joo, Y.H., Cho, J.H.: An enhanced fuzzy neural network. In: Liew, K.-M., Shen, H., See, S., Cai, W. (eds.) PDCAT 2004. LNCS, vol. 3320, pp. 176–179. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Pandya, A.S., Macy, R.B.: Neural Networks for Pattern Recognition using C++. IEEE Press and CRC Press (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kwang-Baek Kim
    • 1
  • Hwang-Kyu Yang
    • 2
  • Sang-Ho Ahn
    • 3
  1. 1.Department of Computer EngineeringSilla UniversityBusanKorea
  2. 2.Department of Multimedia EngineeringDongseo UniversityBusanKorea
  3. 3.Department of Architectural EngineeringSilla UniversityBusanKorea

Personalised recommendations