Clique descriptor of affine invariant regions for robust wide baseline image matching

Assuming that the image distortion between corresponding regions of a stereo pair of images with wide baseline can be approximated as an affine transformation if the regions are reasonably small, recent image matching algorithms have focused on affine invariant region (IR) detection and its description to increase the robustness in matching. However, the distinctiveness of an intensity-based region descriptor tends to deteriorate when an image includes homogeneous texture or repetitive pattern. To address this problem, we investigated the geometry of a local IR cluster (also called a clique) and propose a new clique-based image matching method. In the proposed method, the clique of an IR is estimated by Delaunay triangulation in a local affine frame and the Hausdorff distance is adopted for matching an inexact number of multiple descriptor vectors. We also introduce two adaptively weighted clique distances, where the neighbour distance in a clique is appropriately weighted according to characteristics of the local feature distribution. Experimental results show the clique-based matching method produces more tentative correspondences than variants of the SIFT-based method.

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

[2]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[3]  Azriel Rosenfeld,et al.  Robust regression methods for computer vision: A review , 1991, International Journal of Computer Vision.

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

[5]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[6]  Per-Erik Forssén,et al.  Maximally Stable Colour Regions for Recognition and Matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Franz Aurenhammer,et al.  Voronoi diagrams—a survey of a fundamental geometric data structure , 1991, CSUR.

[8]  Jiri Matas,et al.  Geometric Hashing with Local Affine Frames , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[9]  D. Sheskin.  Handbook of Parametric and Nonparametric Statistical Procedures: Third Edition , 2000 .

[10]  Edwin R. Hancock,et al.  Matching delaunay graphs , 1997, Pattern Recognit..

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

[12]  Andrew Zisserman,et al.  Multiple view geometry in computer visiond , 2001 .

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

[14]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

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

[18]  Daniel P. Huttenlocher,et al.  A multi-resolution technique for comparing images using the Hausdorff distance , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[20]  David G. Lowe,et al.  Shape Descriptors for Maximally Stable Extremal Regions , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[21]  Geoffrey E. Hinton,et al.  Learning Generative Texture Models with extended Fields-of-Experts , 2009, BMVC.