An Interactive Image Inpainting Method Based on RBF Networks

  • Peizhi Wen
  • Xiaojun Wu
  • Chengke Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)


A simple and efficient inpaiting algorithm is proposed based on radial basis function network in this paper. Using the user defined areas, a neighborhood narrow band of the needing fixed pixels are computed by an erosion operator of mathematical morphology technique. Then the weights of RBF network are estimated and a continuous function is constructed, from which the needy inpainted pixels can be filled in.


Mean Square Error Radial Basis Function Radial Basis Function Network Damage Area Cellular Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Oliveira, M., Bowen, B., McKenna, R., Chang, Y.S.: Fast Digital Image Inpainting. In: Proceedings of the Visualization, Imaging, and Image Processing IASTED Conference, Marbella, Spain, September 2001, pp. 261–266 (2001)Google Scholar
  2. 2.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image Inpainting. In: SIGGRAPH 2000, pp. 417–424 (2000)Google Scholar
  3. 3.
    Chan, T., Shen, J.: Mathematical Models for Local Deterministic Inpaintings. UCLA CAM TR 00-11 (March 2000)Google Scholar
  4. 4.
    Chan, T., Shen, J.: Non-texture Inpainting by Curvature-driven Diffusions (CCD). UCLA CAM TR 00-35 (September 2000)Google Scholar
  5. 5.
    Cairo, L., Nascimento Jr: Artificial Neural Networks for Control and Optimization, University of Manchester Institute of Science and Technology (UMIST), Control Systems Centre, Manchester, United Kingdom (1994). In:Google Scholar
  6. 6.
    Sankar, K.P., Bhandari, D.: Cellular Neural Networks, Genetic Algorithms and Object Extraction. In: Far East Journal of Mathematical Sciences, pp. 139–155 (1993)Google Scholar
  7. 7.
    Vellido, A., Lisboa, P.J.G., Vaughan, J.: Neural Networks in Business: a Survey of Applications (1992-1998). Expert Systems with Applications (17), 51–70 (1999)CrossRefGoogle Scholar
  8. 8.
    Mitra, S., Pal, S.K., Kundu, M.K.: Finger Print Classification Using Fuzzy Multi-layer Perceptron. Neural Computing and Applications 2, 227–233 (1994)CrossRefGoogle Scholar
  9. 9.
    Kumaran, K., Geiger, D., Gurvits, L.: Illusory Surface Perception and Visual Organization, Network. Computation in Neural Systems 1(7), 33–60 (1996)CrossRefGoogle Scholar
  10. 10.
    Park, J., Sandberg, J.W.: Universal Approximation Using Radial Basis Functions Network. Neural Computation (3), 246–257 (1991)CrossRefGoogle Scholar
  11. 11.
    Dougherty, E.R.: Mathematical Morphology in Image Processing. Marcel Dekker, Inc., New York (1993)Google Scholar
  12. 12.
    Zhou, T., Tang, F., Wang, J., Wang, Z., Peng, Q.: Digital Image Inpainting with Radial Basis Functions. Journal of Image and Graphics (In Chinese) 10(9), 1190–1196 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Peizhi Wen
    • 1
    • 3
  • Xiaojun Wu
    • 2
  • Chengke Wu
    • 3
  1. 1.Department of Computer ScienceGuilin University of Electronic TechnologyGuilinP.R. China
  2. 2.Harbin Institute of Technology Shenzhen Graduate School, HIT Campus, Shenzhen University TownXiliP.R. China
  3. 3.School of Telecommunication Engineering Xidian UniversityXi’anP.R. China

Personalised recommendations