Invariant Image Matching

View and Illumination Invariant Image Matching

Yinan Yu, Kaiqi Huang, Wei Chen, Tieniu Tan

Matching results of four groups of images. Test images from top to bottom are: boat, graf, wall and leuven [1]. The results of the correct matches are drawn in blue or white lines.

Paper

  • Yinan Yu, Kaiqi Huang, Wei Chen, Tieniu Tan, "A Novel Algorithm for View and Illumination Invariant Image Matching", accepted by IEEE Trans. on Image Processing (TIP), 2011

    Datasets

    We are preparing a view invariant detector evaluation database.

    Other useful database for evaluation:
    VGG Affine Covariant Regions Datasets: http://www.robots.ox.ac.uk/~vgg/data/data-aff.html

    Major References

    [1] Yinan Yu, Kaiqi Huang, Tieniu Tan, "A Harris-Like Scale Invariant Feature Detector", The ninth Asian Conference on Computer Vision (ACCV 2009)
    [2] J.M. Morel and G.Yu, "ASIFT: A New Framework for Fully Affine Invariant Image Comparison", SIAM Journal on Imaging Sciences, vol. 2, issue 2, 2009
    [3] Lowe, D.G, "Distinctive image features from scale-invariant keypoints". Int. J. Comput. Vision 60(2) (2004) 91–110
    [4] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V. "Speeded-up robust features (surf)". Comput. Vis. Image Underst. 110(3) (2008) 346–359
    [5] Harris, C., Stephens, M. "A combined corner and edge detection". (1988) 147–151
    [6] Mikolajczyk, K., Schmid, C. "Scale & affine invariant interest point detectors". Int. J. Comput. Vision 60(1) (2004) 63–86