Skip to main content
SpringerLink
Log in

An Evaluation of Affine Invariant-Based Classification for Image Matching

  • Conference paper
Advances in Visual Computing (ISVC 2009)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 5876))

Included in the following conference series:

Abstract

This paper presents a detailed evaluation of a new approach that uses affine invariants for wide baseline image matching. Previously published work presented a new approach to classify tentative feature matches as inliers or outliers during wide baseline image matching. After typical feature matching algorithms are run and tentative matches are created, the approach is used to classify matches as inliers or outliers to a transformation model. The approach uses the affine invariant property that ratios of areas of shapes are constant under an affine transformation. Thus, by randomly sampling corresponding shapes in the image pair a histogram of ratios of areas can be generated. The matches that contribute to the maximum histogram value are then candidate inliers. This paper evaluates the robustness of the approach under varying degrees of incorrect matches, localization error and perspective rotation often encountered during wide baseline matching. The evaluation shows the affine invariant approach provides similar accuracy as RANSAC under a wide range of conditions while maintaining an order of magnitude increase in efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)

    Article  Google Scholar 

  2. Fleck, D., Duric, Z.: Affine invariant-based classication of inliers and outliers for image matching. In: Image Analysis and Recognition, International Conference ICIAR 2009. Springer, London (2009)

    Google Scholar 

  3. Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)

    Article  MathSciNet  Google Scholar 

  4. Trucco, E., Verri, A.: Introductory Techniques for 3-D Computer Vision. Prentice Hall PTR, Upper Saddle River (1998)

    Google Scholar 

  5. Chum, O., Matas, J.: Randomized ransac with td,d test. In: Proceedings of the 13th British Machine Vision Conference (BMVC), pp. 448–457 (2002)

    Google Scholar 

  6. Nister, D.: Preemptive ransac for live structure and motion estimation. MVA 16(5), 321–329 (2005)

    Article  Google Scholar 

  7. Chum, O., Matas, J., Kittler, J.: Locally optimized ransac. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 236–243. Springer, Heidelberg (2003)

    Google Scholar 

  8. Torr, P.H.S., Zisserman, A.: Mlesac: a new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. 78(1), 138–156 (2000)

    Article  Google Scholar 

  9. Tordoff, B., Murray, D.W.: Guided sampling and consensus for motion estimation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 82–96. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  10. Wang, H.: Robust adaptive-scale parametric model estimation for computer vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1459–1474 (2004) Senior Member-Suter, David.

    Article  Google Scholar 

  11. Zhang, W., Kosecka, J.: Ensemble method for robust motion estimation. In: 25 Years of RANSAC, Workshop in conjunction with CVPR (2006)

    Google Scholar 

  12. Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2004)

    MATH  Google Scholar 

  13. Ma, Y., Soatto, S., Kosecka, J., Sastry, S.S.: An Invitation to 3-D Vision: From Images to Geometric Models. Springer, Heidelberg (2003)

    Google Scholar 

  14. Morris, D.D., Kanade, T.: Feature localization error in 3d vision. In: Winkler, J., Niranjan, M. (eds.) Uncertainty in geometric computations, July 2001, pp. 107–117. Kluwer Academic Publishers, Dordrecht (2001)

    Google Scholar 

  15. Griesser, A.: Zurich building database, http://www.vision.ee.ethz.ch/showroom/zubud/index.en.html

  16. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)

    Article  Google Scholar 

  17. Cheng, Y.: Analysis of affine invariants as approximate perspective invariants. Computer Vision and Image Understanding 63(2), 197–207 (1996)

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, George Mason University, Fairfax, VA, 22030, USA

    Daniel Fleck & Zoran Duric

Authors
  1. Daniel Fleck
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zoran Duric
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science and Engineering, University of Nevada, Reno, USA

    George Bebis

  2. NASA Ames Research Center, Moffett Field, CA, USA

    Richard Boyle

  3. Lawrence Berkeley National Laboratory, Berkeley, CA, USA

    Bahram Parvin

  4. Desert Research Institute, Reno, NV, USA

    Darko Koracin

  5. Graduate School of Science and Engineering, Saitama University, 255 Shimo-Okubo, Sakura-ku, Saitama-shi, 338-8570, 338-8570, Japan

    Yoshinori Kuno

  6. Microsoft Research, Redmond, WA, USA

    Junxian Wang

  7. Univ. of Zurich, Department of Informatics, Winterthurerstr. 190, P.O. Box, 8057, Zurich, Switzerland

    Renato Pajarola

  8. Lawrence Livermore National Laboratory, 94550, Livermore, CA, USA

    Peter Lindstrom

  9. University of Applied Sciences Bonn-Rhein-Sieg, 53754, Sankt Augustin, Germany

    André Hinkenjann

  10.  ,  

    Miguel L. Encarnação

  11. SCI Institute & School of Computing, University of Utah, 84112, Salt Lake City, UT, USA

    Cláudio T. Silva

  12. Desert Research Institute, 89512, Reno, NV, USA

    Daniel Coming

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fleck, D., Duric, Z. (2009). An Evaluation of Affine Invariant-Based Classification for Image Matching. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2009. Lecture Notes in Computer Science, vol 5876. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10520-3_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-10520-3_39

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-10519-7

  • Online ISBN: 978-3-642-10520-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation