Deformation and illumination invariant feature point descriptor

Recent advances in 3D shape recognition have shown that kernels based on diffusion geometry can be effectively used to describe local features of deforming surfaces. In this paper, we introduce a new framework that allows using these kernels on 2D local patches, yielding a novel feature point descriptor that is both invariant to non-rigid image deformations and illumination changes. In order to build the descriptor, 2D image patches are embedded as 3D surfaces, by multiplying the intensity level by an arbitrarily large and constant weight that favors anisotropic diffusion and retains the gradient magnitude information. Patches are then described in terms of a heat kernel signature, which is made invariant to intensity changes, rotation and scaling. The resulting feature point descriptor is proven to be significantly more discriminative than state of the art ones, even those which are specifically designed for describing non-rigid image deformations.

[1]  Nanning Zheng,et al.  A deformable local image descriptor , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[3]  Francesc Moreno-Noguer,et al.  Simultaneous pose, correspondence and non-rigid shape , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[5]  Ron Kimmel,et al.  A general framework for low level vision , 1998, IEEE Trans. Image Process..

[6]  Minsu Cho,et al.  Feature correspondence and deformable object matching via agglomerative correspondence clustering , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  I. Chavel.  Eigenvalues in Riemannian geometry , 1984 .

[8]  Guoliang Xu.  Discrete Laplace-Beltrami operators and their convergence , 2004, Comput. Aided Geom. Des..

[9]  Longin Jan Latecki,et al.  Balancing Deformability and Discriminability for Shape Matching , 2010, ECCV.

[10]  Haibin Ling,et al.  Deformation invariant image matching , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[11]  Vincent Lepetit,et al.  DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Raif M. Rustamov,et al.  Laplace-Beltrami eigenfunctions for deformation invariant shape representation , 2007 .

[13]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[14]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[15]  Ulrich Pinkall,et al.  Computing Discrete Minimal Surfaces and Their Conjugates , 1993, Exp. Math..

[16]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[17]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .

[18]  Iasonas Kokkinos,et al.  Scale-invariant heat kernel signatures for non-rigid shape recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Anthony J. Yezzi,et al.  Modified curvature motion for image smoothing and enhancement , 1998, IEEE Trans. Image Process..

[20]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[21]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[22]  Alfred M. Bruckstein,et al.  Analysis of Two-Dimensional Non-Rigid Shapes , 2008, International Journal of Computer Vision.

[23]  Bruno Lévy,et al.  Laplace-Beltrami Eigenfunctions Towards an Algorithm That "Understands" Geometry , 2006, IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06).

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

[25]  S. D. Yanowitz,et al.  A new method for image segmentation , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[26]  Stefano Soatto,et al.  Features for recognition: viewpoint invariance for non-planar scenes , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[27]  Haibin Ling,et al.  Shape Classification Using the Inner-Distance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Niklas Peinecke,et al.  Laplace-Beltrami spectra as 'Shape-DNA' of surfaces and solids , 2006, Comput. Aided Des..

[29]  Vladimir Kolmogorov,et al.  Feature Correspondence Via Graph Matching: Models and Global Optimization , 2008, ECCV.