Automatic thresholding of SIFT descriptors

We introduce a method to perform automatic thresholding of SIFT descriptors that improves matching performance by at least 15.9% on the Oxford image matching benchmark. The method uses a contrario methodology to determine a unique bin magnitude threshold. This is done by building a generative uniform background model for descriptors and determining when bin magnitudes have reached a sufficient level. The presented method, called meaningful clamping, contrasts from the current SIFT implementation by efficiently computing a clamping threshold that is unique for every descriptor.

[1]  Jean-Michel Morel,et al.  From Gestalt Theory to Image Analysis: A Probabilistic Approach , 2007 .

[2]  Michel Couprie,et al.  Building the Component Tree in Quasi-Linear Time , 2006, IEEE Transactions on Image Processing.

[3]  E. Slud.  Distribution Inequalities for the Binomial Law , 1977 .

[4]  Julien Rabin,et al.  A Statistical Approach to the Matching of Local Features , 2009, SIAM J. Imaging Sci..

[5]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[6]  Thomas Brox,et al.  Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT , 2014, ArXiv.

[7]  Julie Delon,et al.  A Nonparametric Approach for Histogram Segmentation , 2007, IEEE Transactions on Image Processing.

[8]  A. Tamhane,et al.  Multiple Comparison Procedures , 1989 .

[9]  Rafael Grompone von Gioi,et al.  LSD: A Fast Line Segment Detector with a False Detection Control , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Ives Rey-Otero,et al.  Anatomy of the SIFT Method , 2014, Image Process. Line.

[11]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[13]  Stefano Soatto,et al.  Domain-size pooling in local descriptors: DSP-SIFT , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Emmanuel Bertin,et al.  Effective Component Tree Computation with Application to Pattern Recognition in Astronomical Imaging , 2007, 2007 IEEE International Conference on Image Processing.

[15]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[16]  Jean-Michel Morel,et al.  Computational gestalts and perception thresholds , 2003, Journal of Physiology-Paris.

[17]  Arjuna Flenner,et al.  A Helmholtz Principle Approach to Parameter Free Change Detection and Coherent Motion Using Exchangeable Random Variables , 2011, SIAM J. Imaging Sci..

[18]  Julien Rabin.  Approches robustes pour la comparaison d'images et la reconnaissance d'objets , 2009 .

[19]  Agnès Desolneux,et al.  Vanishing Point Detection without Any A Priori Information , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Lionel Moisan,et al.  Meaningful Alignments , 2000, International Journal of Computer Vision.

[21]  Rafael Grompone von Gioi,et al.  On computational Gestalt detection thresholds , 2009, Journal of Physiology-Paris.

[22]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[23]  Jean-Michel Morel,et al.  A Theory of Shape Identification , 2008 .

[24]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[25]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[26]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[27]  Wolfgang Förstner,et al.  Detecting interpretable and accurate scale-invariant keypoints , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[28]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[29]  Lionel Moisan,et al.  Edge Detection by Helmholtz Principle , 2001, Journal of Mathematical Imaging and Vision.

[30]  Charles Kenney,et al.  Two dimensional histogram analysis using the Helmholtz principle , 2008 .

[31]  H. Keselman,et al.  Multiple Comparison Procedures , 2005 .

[32]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..