Scale & Affine Invariant Interest Point Detectors

In this paper we propose a novel approach for detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: (1) Interest points extracted with the Harris detector can be adapted to affine transformations and give repeatable results (geometrically stable). (2) The characteristic scale of a local structure is indicated by a local extremum over scale of normalized derivatives (the Laplacian). (3) The affine shape of a point neighborhood is estimated based on the second moment matrix.Our scale invariant detector computes a multi-scale representation for the Harris interest point detector and then selects points at which a local measure (the Laplacian) is maximal over scales. This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. We extend the scale invariant detector to affine invariance by estimating the affine shape of a point neighborhood. An iterative algorithm modifies location, scale and neighborhood of each point and converges to affine invariant points. This method can deal with significant affine transformations including large scale changes. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point.We present a comparative evaluation of different detectors and show that our approach provides better results than existing methods. The performance of our detector is also confirmed by excellent matching results; the image is described by a set of scale/affine invariant descriptors computed on the regions associated with our points.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  J. Crowley.  A representation for visual information with application to machine vision , 1982 .

[3]  James L. Crowley,et al.  A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[5]  Radu Horaud,et al.  Finding Geometric and Relational Structures in an Image , 1990, ECCV.

[6]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Olaf Kübler,et al.  Simulation of neural contour mechanisms: from simple to end-stopped cells , 1992, Vision Research.

[8]  Wolfgang Förstner,et al.  A Framework for Low Level Feature Extraction , 1994, ECCV.

[9]  Tony Lindeberg,et al.  Direct Estimation of Local Surface Shape in a Fixating Binocular Vision System , 1994, ECCV.

[10]  Roger Mohr,et al.  Accuracy in image measure , 1994, Other Conferences.

[11]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Tony Lindeberg,et al.  Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure , 1997, Image Vis. Comput..

[13]  Andrew Zisserman,et al.  Wide baseline stereo matching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[14]  Lars Bretzner,et al.  Feature Tracking with Automatic Selection of Spatial Scales , 1998, Comput. Vis. Image Underst..

[15]  Luc Van Gool,et al.  Content-Based Image Retrieval Based on Local Affinely Invariant Regions , 1999, VISUAL.

[16]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[17]  Tony Lindeberg,et al.  Fingerprint enhancement by shape adaptation of scale-space operators with automatic scale selection , 2000, IEEE Trans. Image Process..

[18]  Cordelia Schmid,et al.  Matching images with different resolutions , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[19]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[20]  Luc Van Gool,et al.  Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions , 2000, BMVC.

[21]  James L. Crowley,et al.  Local Scale Selection for Gaussian Based Description Techniques , 2000, ECCV.

[22]  Ivan Laptev,et al.  Tracking of Multi-state Hand Models Using Particle Filtering and a Hierarchy of Multi-scale Image Features , 2001, Scale-Space.

[23]  Terry Caelli,et al.  On the Representation of Visual Information , 2001, IWVF.

[24]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[25]  Bill Triggs,et al.  Joint feature distributions for image correspondence , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[26]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[28]  Matthew A. Brown,et al.  Invariant Features from Interest Point Groups , 2002, BMVC.

[29]  Andrew Zisserman,et al.  Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" , 2002, ECCV.

[30]  Stefan Carlsson,et al.  Combining Appearance and Topology for Wide Baseline Matching , 2002, ECCV.

[31]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

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

[33]  Cordelia Schmid,et al.  3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[34]  Sparse Texture Representation Using Affine-Invariant Neighborhoods CVPR Paper , 2003 .

[35]  Cordelia Schmid,et al.  Shape recognition with edge-based features , 2003, BMVC.

[36]  Luis Álvarez,et al.  Affine Morphological Multiscale Analysis of Corners and Multiple Junctions , 1997, International Journal of Computer Vision.

[37]  Kenichi Kanatani,et al.  Geometric Information Criterion for Model Selection , 1998, International Journal of Computer Vision.

[38]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[39]  Cordelia Schmid,et al.  Evaluation of Interest Point Detectors , 2000, International Journal of Computer Vision.

[40]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[41]  Rachid Deriche,et al.  A computational approach for corner and vertex detection , 1993, International Journal of Computer Vision.

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

[43]  Tony Lindeberg,et al.  Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention , 1993, International Journal of Computer Vision.