SIFER: Scale-Invariant Feature Detector with Error Resilience
- 3.3k Downloads
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.
KeywordsScale-invariant Feature Invariant Keypoint Registration
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”.
- 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
- Bay, H. (2011). SURF implementation. http://www.vision.ee.ethz.ch/~surf/. Accessed 15 Jan 2012.
- Beaudet, P. (1978). Rotational invariant image operators. In International conference on pattern recognition, Kyoto, Japan, pp. 579–583.Google Scholar
- 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
- Brown, M., & Lowe, D. (2002). Invariant features from interest point groups. In British machine vision conference, Cardiff, pp. 656–665.Google Scholar
- 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
- 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
- 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
- Deriche, R. (1993). Recursively implementing the gaussian and its derivatives. INRIA: Tech. rep.Google Scholar
- 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
- 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
- Hartley, R., & Zisserman, A. (2000). Multiple view geometry in computer vision. (pp. 87–127), Cambridge: Cambridge University Press.Google Scholar
- 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
- 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
- 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
- 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
- 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
- Mallat, S. (2008). A wavelet tour of signal processing (3rd ed.). San Diego: Academic Press.Google Scholar
- 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
- Maver, J. (2010). Self-similarity and points of interest. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(7), 1211–1226. Google Scholar
- Mikolajczyk, K. (2007). Oxford data set. http://www.robots.ox.ac.uk/~vgg/research/affine. Accessed 15 Jan 2012.
- 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
- 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
- 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
- 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
- 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
- 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
- Tomasi, C., & Kanade, T. (1991). Detection and tracking of point features. Tech. Rep. CMU-CS-91-132, Carnegie Mellon University.Google Scholar
- Vedaldi, A. (2011). Open source SIFT implementation. http://www.vlfeat.org/~vedaldi/code/siftpp.html. Accessed 15 Jan 2012.