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

Article English OPEN
Shin, Dongjoe ; Tjahjadi, Tardi (2010)
  • Publisher: Pergamon
  • Related identifiers: doi: 10.1016/j.patcog.2010.04.010
  • Subject: TK | QA76
    arxiv: Computer Science::Computer Vision and Pattern Recognition
    acm: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION

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.
  • References (19)
    19 references, page 1 of 2

    [1] T. Tuytelaars, L. J. V. Gool, Wide baseline stereo matching based on local, affinely invariant regions, in: Proc. Brit. Machine Vision Conf., 2000, pp. 42-56.

    [2] D. G. Lowe, Distinctive image features from scale-invariant keypoints, Int. J. Compt. Vis. 60 (2) (2004) 91-110.

    [3] K. Mikolajczyk, C. Schmid, A performance evaluation of local descriptors, IEEE Trans. Pattern Anal. Machine Intell. 27 (10) (2005) 1615-1630.

    [4] K. Mikolajczyk, C. Schmid, Scale and affine invariant interest point detectors, Int. J. Compt. Vis. 60 (1) (2004) 63-86.

    [5] T. Tuytelaars, L. J. V. Gool, Matching widely separated views based on affine invariant regions, Int. J. Compt. Vis. 59 (1) (2004) 61-85.

    [6] J. Matas, O. Chum, M. Urban, T. Pajdla, Robust wide baseline stereo from maximally stable extremal regions, Image Vision Compt. 22 (10) (2004) 761-767.

    [7] P. E. Forssen, Maximally stable colour regions for recognition and matching, in: Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007, pp. 1-8.

    [8] P. Meer, D. Mintz, D. Y. Kim, A. Rosenfeld, Robust regression methods for computer vision: A review, Int. J. Compt. Vis. 6 (1) (1991) 59-70.

    [9] R. Hartley, A. Zisserman, Multiple view geometry, 1st Edition, Cambridge, 2000.

    [10] F. Schaffalitzky, A. Zisserman, Viewpoint invariant texture matching and wide baseline stereo, in: Proc. IEEE Int. Conf. Computer Vision, 2001, pp. 636-643.

  • Similar Research Results (3)
  • Metrics
    0
    views in OpenAIRE
    0
    views in local repository
    49
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    Warwick Research Archives Portal Repository - IRUS-UK 0 49
Share - Bookmark