GROUP-WISE SPARSE CORRESPONDENCES BETWEEN IMAGES BASED ON A COMMON LABELLING APPROACH

Albert Solé-Ribalta, Gerard Sanromà, Francesc Serratosa, René Alquézar

Abstract

Finding sparse correspondences between two images is a usual process needed for several higher-level computer vision tasks. For instance, in robot positioning, it is frequent to make use of images that the robot captures from their cameras to guide the localisation or reduce the intrinsic ambiguity of a specific localisation obtained by other methods. Nevertheless, obtaining good correspondence between two images with a high degree of dissimilarity is a complex task that may lead to important positioning errors. With the aim of increasing the accuracy with respect to the pair-wise image matching approaches, we present a new method to compute group-wise correspondences among a set of images. Thus, pair-wise errors are compensated and better correspondences between images are obtained. These correspondences can be used as a less-noisy input for the localisation process. Group-wise correspondences are computed by finding the common labelling of a set of salient points obtained from the images. Results show a clear increase in effectiveness with respect to methods that use only two images.

References

  1. Bonev, B., F. Escolano, et al. (2007). Constellations and the unsupervised learning of graphs. International conference on Graph-based representations in pattern recognition: 340-350.
  2. Cootes, T., C. Twining, et al. (2010). "Computing Accurate Correspondences across Groups of Images " Pattern Analysis and Machine Intelligence 32(11): 1994-2005.
  3. Fergus, R., P. Perona, et al. (2007). "Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition." International Journal of Computer Vision 71 (3): 273-303.
  4. Fischler, M. and R. Bolles (1981). "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography." Communications of the ACM 24(6): 381-395.
  5. Gold, S. and A. Rangarajan (1996). "A Graduated Assignment Algorithm for Graph Matching." Transaction on Pattern Analysis and Machine Intelligence 18(4): 377-388.
  6. Gold, S., A. Rangarajan, et al. (1998). "New algorithms for 2d and 3d point matchin." Pattern Recognition 31: 1019-1031.
  7. Harris, C. and M. Stephens (1988). A Combined Corner and Edge Detection. The Fourth Alvey Vision Conference.
  8. Horaud, R., F. Forbes, et al. (2011). "Rigid and articulated point registration with expectation conditional maximization." Pattern Analysis and Machine Intelligence 33: 587-602.
  9. Hummel, R. and S. Zucker (1983). "On the foundations of relaxation labling processes." Pattern Analysis and Machine Intelligence 5(3): 267-287.
  10. Jian, B. and B. Vemuri (2005). A robust algorithm for point set registration using mixture of gaussians. International Conference on Computer Vision.
  11. Jian, B. and B. Vemuri (2011). "Robust point set registration using gaussian mixture models." Pattern Analysis and Machine Intelligence 33: 1633-1645.
  12. Kovesi, P. (2009). "http://www.csse.uwa.edu.au/ pk/Research/MatlabFns/."
  13. Mikolajczyk, K. and C. Schmid (2005). "A performance evaluation of local descriptors " Transaction on Pattern Analysis and Machine Intelligence 27(10): 1615-1630.
  14. Mikolajczyk, K., T. Tuytelaars, et al. (2011). "http://www.featurespace.org/." Retrieved 23/02/2011.
  15. Myronenko, A. and X. Song (2010). "Point Set Registration: Coherent Point Drift." Pattern Analysis and Machine Intelligence 32(12): 2262-2275.
  16. Rangarajan, A., H. Chui, et al. (1997). The softassign procrustes matching algorithm. International Conference on Information Processing in Medical Imaging.
  17. Rosenfeld, A., R. A. Hummel, et al. (1976). "Scene Labeling by Relaxation Operations." Transactions on Systems, Man, and Cybernetics 6: 420-443.
  18. Sinkhorn, R. (1964). "A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices." The Annals of Mathematical Statistics 35(2): 876-879.
  19. Solé-Ribalta, A. and F. Serratosa (2010). Graduated assignment algorithm for finding the common labelling of a set of graphs. International conference on Structural, syntactic, and statistical pattern recognition 180-190.
  20. Solé-Ribalta, A. and F. Serratosa (2011). "Models and algorithms for computing the common labelling of a set of attributed graphs." Computer Vision and Image Understanding 115(7): 929-945.
  21. Wang, F., B. Vemuri, et al. (2008). "Simultaneous Nonrigid Registration of Multiple Point Sets and Atlas Construction " Pattern Analysis and Machine Intelligence 30(11): 2011-2022.
  22. Williams, M., R. Wilson, et al. (1997). "Multiple Graph Matching with Bayesian Inference." Pattern Recognition Letters 18: 1275-1281.
  23. Wong, A. and M. You (1985). "Entropy and Distance of Random Graphs with Application to Structural Pattern Recognition." Transaction on Pattern Analysis and Machine Intelligence PAMI-7(5): 599-609.
  24. Zhang, Z. (1992). "Iterative Point Matching for Registration of Free-form Curves." International Journal of Computer Vision 13(2): 119-152.
Download


Paper Citation


in Harvard Style

Solé-Ribalta A., Sanromà G., Serratosa F. and Alquézar R. (2012). GROUP-WISE SPARSE CORRESPONDENCES BETWEEN IMAGES BASED ON A COMMON LABELLING APPROACH . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 269-278. DOI: 10.5220/0003846802690278


in Bibtex Style

@conference{visapp12,
author={Albert Solé-Ribalta and Gerard Sanromà and Francesc Serratosa and René Alquézar},
title={GROUP-WISE SPARSE CORRESPONDENCES BETWEEN IMAGES BASED ON A COMMON LABELLING APPROACH},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={269-278},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003846802690278},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - GROUP-WISE SPARSE CORRESPONDENCES BETWEEN IMAGES BASED ON A COMMON LABELLING APPROACH
SN - 978-989-8565-03-7
AU - Solé-Ribalta A.
AU - Sanromà G.
AU - Serratosa F.
AU - Alquézar R.
PY - 2012
SP - 269
EP - 278
DO - 10.5220/0003846802690278