Abstract
The most popular image matching algorithm SIFT, introduced by D. Lowe a decade ago, has proven to be sufficiently scale invariant to be used in numerous applications. In practice, however, scale invariance may be weakened by various sources of error inherent to the SIFT implementation affecting the stability and accuracy of keypoint detection. The density of the sampling of the Gaussian scale-space and the level of blur in the input image are two of these sources. This article presents a numerical analysis of their impact on the extracted keypoints stability. Such an analysis has both methodological and practical implications, on how to compare feature detectors and on how to improve SIFT. We show that even with a significantly oversampled scale-space numerical errors prevent from achieving perfect stability. Usual strategies to filter out unstable detections (e.g., poorly contrasted extrema) are shown to be inefficient. We also prove that the effect of the error in the assumption on the initial blur is asymmetric and that the method is strongly degraded in the presence of aliasing or without a correct assumption on the camera blur. This analysis leads to a series of practical recommendations.
Similar content being viewed by others
Notes
Indeed, thanks to a change of variable, we have
$$\begin{aligned} G_c H_\lambda u_0 (\mathbf{x})&=\int _{\mathbb {R}^2} G_c(\mathbf{x}') u_0(\lambda \mathbf{x}- \lambda \mathbf{x}')d\mathbf{x}' \\&=\int _{\mathbb {R}^2} G_{\lambda c}(\mathbf{x}'') u_0(\lambda \mathbf{x}- \mathbf{x}'')d\mathbf{x}'' = H_\lambda G_{\lambda c} u_0 (\mathbf{x}). \end{aligned}$$
References
Agrawal, M., Konolige, K., Blas, M.: CenSurE: center surround extremas for realtime feature detection and matching. In: ECCV, pp. 102–115. Springer, Heidelberg (2008)
Ancuti, C., Bekaert, P.: SIFT-CCH: increasing the SIFT distinctness by color co-occurrence histograms. In: ISPA. 5th International Symposium on IEEE, pp. 130–135. (2007)
Bay, H., Tuytelaars, T., van Gool, L.: SURF: Speeded up robust features. In: ECCV (2006)
Brown, M., Lowe, D.: Automatic panoramic image stitching using invariant features. IJCV 74(1), 59–73 (2007)
Brown, M., Szeliski, R., Winder, S.: Multi-image matching using multi-scale oriented patches. In: CVPR (2005)
Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: Binary robust independent elementary features. In: ECCV. pp. 778–792. Springer, Heidelberg (2010)
Chen, J., Shan, S., He, C., Zhao, G., Pietikainen, M., Chen, X., Gao, W.: WLD: a robust local image descriptor. PAMI 32(9), 1705–1720 (2010)
Cordes, K., Muller, O., Rosenhahn, B., Ostermann, J.: HALF-SIFT: High-accurate Localized Features for SIFT. In: CVPR Workshops. pp. 31–38 (2009)
Delbracio, M., Musé, P., Almansa, A.: Non-parametric sub-pixel local point spread function estimation. IPOL (2012)
Dickscheid, T., Schindler, F., Förstner, W.: Coding images with local features. IJCV 94(2), 154–174 (2011)
Florack, L.: A spatio-frequency trade-off scale for scale-space filtering. IEEE Trans. Pattern Anal. Mach. Intell. 22(9), 1050–1055 (2000)
Förstner, W., Dickscheid, T., Schindler, F.: Detecting interpretable and accurate scale-invariant keypoints. In: ICCV (2009)
Grabner, M., Grabner, H., Bischof, H.: Fast approximated SIFT. In: ACCV, pp. 918–927. Springer, Heidelberg (2006)
Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: CVPR (2004)
Leutenegger, S., Chli, M., Siegwart, R.: BRISK: binary robust invariant scalable keypoints. In: ICCV (2011)
Lindeberg, T.: Scale-Space Theory in Computer Vision. Springer, New York (1993)
Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.: SIFT Flow: Dense correspondence across different scenes. In: ECCV, pp. 28–42. Springer, Heidelberg (2008)
Loncomilla, P., Ruiz-del Solar, J.: Improving sift-based object recognition for robot applications. In: Image Analysis and Processing ICIAP 2005, vol. 3617, pp. 1084–1092. Springer, Berlin (2005). http://dx.doi.org/10.1007/11553595_133
Lowe, D.: Object recognition from local scale-invariant features. In: ICCV (1999)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Mainali, P., Lafruit, G., Yang, Q., Geelen, B., Van Gool, L., Lauwereins, R.: SIFER: scale-invariant feature detector with error resilience. IJCV 104(2), 172–197 (2013)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27(10), 1615–1630 (2005)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. IJCV 65(1–2), 43–72 (2005)
Morel, J.M., Yu, G.: Is SIFT scale invariant? Inverse Probl. Imaging 5(1), 115–136 (2011)
Moreno, P., Bernardino, A., Santos-Victor, J.: Improving the SIFT descriptor with smooth derivative filters. Pattern Recognit. Lett. 30(1), 18–26 (2009)
Pele, O., Werman, M.: A linear time histogram metric for improved SIFT matching. In: ECCV. pp. 495–508. Springer, Heidelberg (2008)
Rabin, J., Delon, J., Gousseau, Y.: A statistical approach to the matching of local features. SIAM J. Imaging Sci. 2(3), 931–958 (2009)
Rey-Otero, I., Delbracio, M.: Anatomy of the SIFT method. Image Process. Line 4, 370–396 (2014)
Rey-Otero, I., Delbracio, M.: Computing an exact gaussian scale-space. Image Process. Line 6, 8–26 (2016)
Rey-Otero, I., Morel, J.M., Delbracio, M.: An analysis of scale-space sampling in SIFT. In: Image processing (ICIP), 2014 IEEE international conference. pp. 4847–4851. (2014)
Riggi, F., Toews, M., Arbel, T.: Fundamental matrix estimation via TIP-transfer of invariant parameters. In: ICPR (2006)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: ICCV (2011)
Sadek, R.: Some problems on temporally consistent video editing and object recognition. Ph.D. thesis, Universitat Pompeu Fabra (2012)
Sadek, R., Constantinopoulos, C., Meinhardt, E., Ballester, C., Caselles, V.: On affine invariant descriptors related to SIFT. SIAM 5(2), 652–687 (2012)
Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: CVPR (2008)
Tola, E., Lepetit, V., Fua, P.: A fast local descriptor for dense matching. In: CVPR (2008)
Tola, E., Lepetit, V., Fua, P.: DAISY: an efficient dense descriptor applied to wide-baseline stereo. PAMI 32(5), 815–830 (2010)
Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis. 3(3), 177–280 (2008)
Van De Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. PAMI 32(9), 1582–1596 (2010)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms. In: Proceedings of the 18th ACM international conference on multimed (2010)
Weickert, J., Ishikawa, S., Imiya, A.: Linear scale-space has first been proposed in Japan. J. Math. Imaging Vis. 10(3), 237–252 (1999)
Winder, S., Brown, M.: Learning local image descriptors. In: CVPR (2007)
Winder, S., Hua, G., Brown, M.: Picking the best DAISY. In: CVPR (2009)
Zeisl, B., Georgel, P.F., Schweiger, F., Steinbach, E.G., Navab, N., Munich, G.: Estimation of location uncertainty for scale invariant features points. In: BMVC. pp. 1–12 (2009)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rey-Otero, I., Morel, JM. & Delbracio, M. An Analysis of the Factors Affecting Keypoint Stability in Scale-Space. J Math Imaging Vis 56, 554–572 (2016). https://doi.org/10.1007/s10851-016-0657-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-016-0657-5