Advertisement

International Journal of Computer Vision

, Volume 104, Issue 2, pp 172–197 | Cite as

SIFER: Scale-Invariant Feature Detector with Error Resilience

  • Pradip MainaliEmail author
  • Gauthier Lafruit
  • Qiong Yang
  • Bert Geelen
  • Luc Van Gool
  • Rudy Lauwereins
Article

Abstract

We present a new method to extract scale-invariant features from an image by using a Cosine Modulated Gaussian (CM-Gaussian) filter. Its balanced scale-space atom with minimal spread in scale and space leads to an outstanding scale-invariant feature detection quality, albeit at reduced planar rotational invariance. Both sharp and distributed features like corners and blobs are reliably detected, irrespective of various image artifacts and camera parameter variations, except for planar rotation. The CM-Gaussian filters are approximated with the sum of exponentials as a single, fixed-length filter and equal approximation error over all scales, providing constant-time, low-cost image filtering implementations. The approximation error of the corresponding digital signal processing is below the noise threshold. It is scalable with the filter order, providing many quality-complexity trade-off working points. We validate the efficiency of the proposed feature detection algorithm on image registration applications over a wide range of testbench conditions.

Keywords

Scale-invariant Feature Invariant Keypoint  Registration 

Notes

Acknowledgments

The authors would like to thank Rachid Deriche from INRIA, Prof. Lucas J. Van Vliet and Prof. Ian T. Young from TU/Delft for discussions and answering our emails regarding the approximation design methods for the filters. Author Bert Geelen was supported by IWT SBO-project 100021 “CHAMELEON”.

References

  1. Aanæs, H., Dahl, A., & Steenstrup Pedersen, K. (2011). Interesting interest points: A comparative study of interest point performance on a unique data set. International Journal of Computer Vision, 97(1), 18–35.CrossRefGoogle Scholar
  2. Alahi, A., Ortiz, R., & Vandergheynst, P. (2012). FREAK: Fast Retina Keypoint. In IEEE conference on computer vision and pattern recognition, Providence, RI, USA.Google Scholar
  3. Bay, H. (2011). SURF implementation. http://www.vision.ee.ethz.ch/~surf/. Accessed 15 Jan 2012.
  4. Bay, H., Andreas, E., Tuytelaars, T., & Van Gool, L. (2008). Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 110(3), 346–359.CrossRefGoogle Scholar
  5. Beaudet, P. (1978). Rotational invariant image operators. In International conference on pattern recognition, Kyoto, Japan, pp. 579–583.Google Scholar
  6. Bendale, P., Triggs, B., & Kingsbury, N. (2010). Multiscale keypoint analysis based on complex wavelets. In Proceedings of the British machine vision conference, Aberystwyth, pp. 49.1–49.10.Google Scholar
  7. Brown, M., & Lowe, D. (2002). Invariant features from interest point groups. In British machine vision conference, Cardiff, pp. 656–665.Google Scholar
  8. Cornelis, N., & Van Gool, L. (2008). Fast scale invariant feature detection and matching on programmable graphics hardware. In IEEE computer society conference on computer vision and pattern recognition workshops, 2008 (CVPRW’08), Anchorage, AK, USA, pp. 1–8.Google Scholar
  9. Crete, F., Dolmiere, T., Ladret, P., & Nicolas, M. (2007). The blur effect: perception and estimation with a new no-reference perceptual blur metric. In Human vision and electronic imaging XII (Vol. 6492, p. 64920I). San Jose: Proceedings of the SPIE.Google Scholar
  10. Daugman, J. (1988). Complete discrete 2-d gabor transforms by neural networks for image analysis and compression. IEEE Transactions on Acoustics, Speech and Signal Processing, 36(7), 1169–1179.zbMATHCrossRefGoogle Scholar
  11. Deng, H., Zhang, W., Mortensen, E., Dietterich, T., & Shapiro, L. (2007). Principal curvature-based region detector for object recognition. In IEEE conference on computer vision and pattern recognition, Minneapolis, MN, USA, pp. 1–8.Google Scholar
  12. Deriche, R. (1993). Recursively implementing the gaussian and its derivatives. INRIA: Tech. rep.Google Scholar
  13. Fischler, M. A., & Bolles, R. C. (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.MathSciNetCrossRefGoogle Scholar
  14. Forstner, W. (1994). A framework for low level feature extraction. In Proceedings of the third European conference, Volume II on computer vision, Stockholm, Sweden: Springer-Verlag New York, Inc, pp. 383–394.Google Scholar
  15. Gao, X., Sattar, F., & Venkateswarlu, R. (2007). Multiscale corner detection of gray level images based on log-gabor wavelet transform. IEEE Transactions on Circuits and Systems for Video Technology, 17(7), 868–875.CrossRefGoogle Scholar
  16. Harris, C., & Stephens, M. (1988). A combined corner and edge detection. In Proceedings of the fourth alvey vision conference, Manchester, UK, pp. 147–151.Google Scholar
  17. Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. (pp. 87–127), Cambridge: Cambridge University Press.Google Scholar
  18. Horaud, R.P., Skordas, T., & Veillon, F. (1990). Finding geometric and relational structures in an image. In Proceedings of the first European conference on computer vision, Antibes, France, Vol. 427, pp. 374–384.Google Scholar
  19. Huang, F., Huang, S., Ker, J., & Chen, Y. (2012). High-performance SIFT hardware accelerator for real-time image feature extraction. Circuits and Systems for Video Technology, IEEE Transactions on, 22(3), 340–351.Google Scholar
  20. Kadir, T., Zisserman, A., & Brady, J. M. (2004). An affine invariant salient region detector. In T. Pajdla & J. Matas (Eds.), European conference on computer vision, Prague, Czech Republic: Springer Berlin Heidelberg.Google Scholar
  21. Kovesi P (2003) Phase congruency detects corners and edges. In The Australian pattern recognition society conference: DICTA 2003, Sydney, Australia, pp. 309–318.Google Scholar
  22. Lindeberg, T. (1990). Scale-space for discrete signals. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 234–254.CrossRefGoogle Scholar
  23. Lindeberg, T. (1998). Feature detection with automatic scale selection. International Journal of Computer Vision, 30, 79–116.CrossRefGoogle Scholar
  24. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110.CrossRefGoogle Scholar
  25. Mainali, P., Yang, Q., Lafruit, G., Van Gool, L., & Lauwereins, R. (2010). Robust low complexity corner detector. IEEE Transactions on Circuit and Systems for Video Technology, 21, 87–127.Google Scholar
  26. Mallat, S. (2008). A wavelet tour of signal processing (3rd ed.). San Diego: Academic Press.Google Scholar
  27. Marquardt, D. W. (1963). An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), 431–441.MathSciNetzbMATHCrossRefGoogle Scholar
  28. Matas, J., Chum, O., Martin, U., & Pajdla, T. (2002). Robust wide baseline stereo from maximally stable extremal regions. In Proceedings of British machine vision conference Vol. 1, pp. 384–393.Google Scholar
  29. Maver, J. (2010). Self-similarity and points of interest. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(7), 1211–1226. Google Scholar
  30. Mikolajczyk, K. (2007). Oxford data set. http://www.robots.ox.ac.uk/~vgg/research/affine. Accessed 15 Jan 2012.
  31. Mikolajczyk, K., & Schmid, C. (2004). Scale and affine invariant interest point detectors. International Journal of Computer Vision, 60(1), 63–86.CrossRefGoogle Scholar
  32. Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615–1630.Google Scholar
  33. Mokhtarian, F., & Suomela, R. (1998). Robust image corner detection through curvature scale space. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(12), 1376–1381.CrossRefGoogle Scholar
  34. Moreno, P., Bernardino, A., & Victor, S.J. (2005). Appearance based salient point detection with intrinsic scale-frequency descriptor. In Proc. 5th international conference on visualization, imaging and image processing (VIIP), Benidorm, Spain.Google Scholar
  35. Neubeck, A., & Van Gool, L. (2006). Efficient non-maximum suppression. In Proc. IEEE international conference on pattern recognition, Hong Kong, Vol. 3, pp. 850–855.Google Scholar
  36. Rosten, E., Porter, R., & Drummond, T. (2010). Faster and better: A machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(1), 105–119.CrossRefGoogle Scholar
  37. Schmid, C., Mohr, R., & Bauckhage, C. (2000). Evaluation of interest point detectors. International Journal of Computer Vision, 37(2), 151–172.zbMATHCrossRefGoogle Scholar
  38. Shilat, F., Werman, M., & Gdalyahn, Y. (1997). Ridge’s corner detection and correspondence. In Proc. IEEE of conference on computer vision and pattern recognition, San Juan, PR, pp. 976–981.Google Scholar
  39. Smith, S. M., & Brady, J. M. (1997). SUSAN—a new approach to low level image processing. International Journal of Computer Vision, 23(1), 45–78.CrossRefGoogle Scholar
  40. Tack, N., Lambrechts, A., Soussana, P., & Haspeslagh, L. (2012). A compact, high-speed and low-cost hyperspectral imager. In Photonics West, Proc. SPIE Vol. 8266, pp. 82,660Q–82,660Q–13.Google Scholar
  41. Tola, E., Lepetit, V., & Fua, P. (2008). A fast local descriptor for dense matching. In IEEE conference on computer vision and pattern recognition, Anchorage, AK, pp. 1–8.Google Scholar
  42. Tomasi, C., & Kanade, T. (1991). Detection and tracking of point features. Tech. Rep. CMU-CS-91-132, Carnegie Mellon University.Google Scholar
  43. Tuytelaars, T., & Van Gool, L. (2004). Matching widely separated views based on affine invariant regions. International Journal of Computer Vision, 59(1), 61–85.CrossRefGoogle Scholar
  44. Vedaldi, A. (2011). Open source SIFT implementation. http://www.vlfeat.org/~vedaldi/code/siftpp.html. Accessed 15 Jan 2012.
  45. Young, I., van Vliet, L., & van Ginkel, M. (2002). Recursive gabor filtering. IEEE Transactions on Signal Processing, 50(11), 2798–2805.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Pradip Mainali
    • 1
    • 2
    Email author
  • Gauthier Lafruit
    • 1
  • Qiong Yang
    • 1
  • Bert Geelen
    • 1
  • Luc Van Gool
    • 2
  • Rudy Lauwereins
    • 1
  1. 1.Interuniversitair Micro-Electronica Centrum VZW (IMEC)LeuvenBelgium
  2. 2.ESAT, University of LeuvenLeuvenBelgium

Personalised recommendations