Recognition with local features: the kernel recipe

Recent developments in computer vision have shown that local features can provide efficient representations suitable for robust object recognition. Support vector machines have been established as powerful learning algorithms with good generalization capabilities. We combine these two approaches and propose a general kernel method for recognition with local features. We show that the proposed kernel satisfies the Mercer condition and that it is, suitable for many established local feature frameworks. Large-scale recognition results are presented on three different databases, which demonstrate that SVMs with the proposed kernel perform better than standard matching techniques on local features. In addition, experiments on noisy and occluded images show that local feature representations significantly outperform global approaches.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[3]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[4]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[7]  Vapnik,et al.  SVMs for Histogram Based Image Classification , 1999 .

[8]  Christopher J. C. Burges,et al.  Geometry and invariance in kernel based methods , 1999 .

[9]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[10]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[11]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[12]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[13]  Thomas de Quincey.  [C] , 2000, The Works of Thomas De Quincey, Vol. 1: Writings, 1799–1820.

[14]  Jan-Olof Eklundh,et al.  A pure learning approach to background-invariant object recognition using pedagogical support vector learning , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Jitendra Malik,et al.  Matching Shapes , 2001, ICCV.

[16]  A. Leonardis,et al.  Illumination Insensitive Eigenspaces , 2001, ICCV.

[17]  Bernhard Schölkopf,et al.  Kernel machine based learning for multi-view face detection and pose estimation , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  A. Leonardis,et al.  Illumination insensitive eigenspaces , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[19]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

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

[21]  Francesca Odone,et al.  Image Kernels , 2002, SVM.

[22]  Heinrich Niemann,et al.  Robust appearance-based object recognition using a fully connected Markov random field , 2002, Object recognition supported by user interaction for service robots.

[23]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[24]  Barbara Caputo,et al.  How to Combine Color and Shape Information for 3D Object Recognition: Kernels do the Trick , 2002, NIPS.

[25]  Heinrich H. Bülthoff,et al.  View-based dynamic object recognition based on human perception , 2002, Object recognition supported by user interaction for service robots.

[26]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[27]  Bernt Schiele,et al.  Analyzing contour and appearance based methods for object categorization , 2003, CVPR 2003.

[28]  Ivan Laptev,et al.  Interest Point Detection and Scale Selection in Space-Time , 2003, Scale-Space.

[29]  Cordelia Schmid,et al.  Evaluation of Interest Point Detectors , 2000, International Journal of Computer Vision.

[30]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[31]  Bernt Schiele,et al.  Recognition without Correspondence using Multidimensional Receptive Field Histograms , 2004, International Journal of Computer Vision.