An Improved RANSAC Algorithm of Color Image Stitching

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 256)


Image mosaic is a technique being used to stitch multiple images together to form a stitched image with higher resolution and large field of view. This paper presents an improved RANSAC algorithm of color image mosaic. Image mosaic mainly comprises two steps, namely image registration and image fusion. This algorithm comprises main modules, such as Harris corner detection, NCC rough matching, improved RANSAC exaction, estimating the projection transformation matrix, projection transformation, image smoothing. The improved RANSAC for feature points exaction based on statistical regularities can greatly support the real time of the algorithm. The experimental results show that the algorithm presented is fast and effective.


Image mosaic Feature point detection Improved RANSAC exaction Projection transformation Image smoothing 


  1. 1.
    Lowe DG (2004) Distinctive image features from scale-invariant key points. Int J Comput Vision 60(2):91–110CrossRefGoogle Scholar
  2. 2.
    Zhang Y (2007) Image engineering. Tsinghua University Press, Beijing, pp 105–107 (in Chinese)Google Scholar
  3. 3.
    Helmer EH, Ruefenacht B (2005) Cloud-free satellite image mosaics with regression trees and histogram matching. Am Soc Photogram Remote Sens 2005(9):1079–1089Google Scholar
  4. 4.
    Choi Y-S, Koo B-K, Lee J-H (2007) Template based image mosaics. Lect Notes Comput Sci 43(5):475–478Google Scholar
  5. 5.
    George P, Petros M (2008) Adaptive and constrained algorithms for inverse compositional active appearance model fitting. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR-2008), Anchorage, vol 1, pp 1–8Google Scholar
  6. 6.
    Jiang J, Tan R, Yang D (2009) Image splicing based on contour feature and wavelet transform image splicing. Comput Eng 35(3):225–229 (in Chinese)Google Scholar
  7. 7.
    Zhang Q, Liu Z, Pang Y (2008) Automatic image registration based on SUSAN algorithm. J Surv Mapp 32(3):245–250 (in Chinese)Google Scholar
  8. 8.
    Xi Y, Guo B, Zhan L, Yang Z (2009) Estimation affine parameters based on the image feature points. Comput Sci 6(36):279–281 (in Chinese)Google Scholar
  9. 9.
    Feng Y, Dai M, Sun L (2010) The optimization of automatic image mosaic. Opt Precis Eng 18(2):470–476 (in Chinese)Google Scholar
  10. 10.
    Guo S, Fang X, Luo B (2007) A video sequence stitching algorithm. Comput Appl 11(27):2786–2788 (in Chinese)Google Scholar
  11. 11.
    Kang Y, Pang C (2008) The real-time video image mosaic. Video Signal Inf Proc 5(38):26–28 (in Chinese)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.School of Information and EngineeringShenyang UniversityShenyangChina

Personalised recommendations