Abstract
We present a fast image comparison algorithm for handling variations in illumination and moderate amounts of deformation using an efficient geodesic framework. As the geodesic is the shortest path between two images on a manifold, it is a natural choice to use the length of the geodesic to determine the image similarity. Distances on the manifold are defined by a metric that is insensitive to changes in scene lighting. This metric is described in the wavelet domain where it is able to handle moderate amounts of deformation, and can be calculated extremely fast (less than 3ms per image comparison). We demonstrate the similarity between our method and the illumination insensitivity achieved by the Gradient Direction. Strong results are presented on the AR Face Database.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Beg, M., Miller, M., Trouvé, A., Younes, L.: Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms. IJCV 61, 139–157 (2005)
Bruna, J., Mallat, S.: Classification with Scattering Operators. In: CVPR (2011)
Courant, R., Hilbert, D.: Methods of Mathematical Physics, vol. I. ch. IV. Interscience Publishers, Inc. (1955)
do Carmo, M.: Riemannian Geometry. Birkhäuser (1992)
Gopalan, R., Jacobs, D.: Comparing and Combining Lighting Insensitive Approaches for Face Recognition. CVIU 114, 135–145 (2010)
James, A.P.: Pixel-Level Decisions Based Robust Face Image Recognition. In: Oravec, M. (ed.) Face Recognition, ch. 5, pp. 65–86. INTECH (2010)
Jorstad, A., Jacobs, D., Trouvé, A.: A Deformation and Lighting Insensitive Metric for Face Recognition Based on Dense Correspondences. In: CVPR (2011)
LeCun, Y., Huang, F., Bottou, L.: Learning Methods for Generic Object Recognition with Invariance to Pose and Lighting. In: CVPR (2004)
Lewis, J.: Fast Normalized Cross-Correlation. Vision Interface (1995)
Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. IJCV 60 (2004)
Mallat, S.: A Wavelet Tour of Signal Processing. Elsevier (2009)
Martinez, A., Kak, A.C.: PCA versus LDA. PAMI 23, 228–233 (2001)
Negahdaripour, S.: Revised Definition of Optical Flow: Integration of Radiometric and Geometric Cues for Dynamic Scene Analysis. PAMI 20, 961–979 (1998)
Rubner, Y., Tomasi, C., Guibas: The Earth Mover’s Distance as a Metric for Image Retrieval. IJCV (2000)
Shirdhonkar, S., Jacobs, D.: Approximate Earth Mover’s Distance in Linear Time. In: CVPR (2008)
Song, J., Chen, B., Wang, W., Ren, X.: Face Recognition by Fusing Binary Edge Feature and Second-Order Mutual Information. In: IEEE Conf. on Cybernetics and Intelligent Systems, pp. 1046–1050 (2008)
Tung, T., Matsuyama, T.: Dynamic Surface Matching by Geodesic Mapping for 3D Animation Transfer. In: CVPR (2010)
Turaga, P., Veeraraghavan, A., Chellappa, R.: Statistical Analysis on Stiefel and Grassmann Manifolds with Applications in Computer Vision. In: CVPR (2008)
Younes, L.: Shapes and Diffeomorphisms. Springer (2010)
Zhao, S., Gao, Y.: Significant Jet Point For Facial Image Representation and Recognition. In: International Conference on Image Processing, pp. 1664–1667 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jorstad, A., Jacobs, D., Trouvé, A. (2012). A Fast Illumination and Deformation Insensitive Image Comparison Algorithm Using Wavelet-Based Geodesics. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7575. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33765-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-33765-9_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33764-2
Online ISBN: 978-3-642-33765-9
eBook Packages: Computer ScienceComputer Science (R0)