Cue integration through discriminative accumulation

Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme, which extends the idea of cue accumulation to discriminative classifiers. We derive and test the scheme for support vector machines (SVMs), but we also show that it is easily extendible to any large margin classifier. In the case of one-class SVMs the scheme can be interpreted as a new class of Mercer kernels for multiple cues. Experimental comparison with a probabilistic accumulation scheme is favorable to our method. Comparison with voting scheme shows that our method may suffer as the number of object classes increases. Based on these results, we propose a recognition algorithm consisting of a decision tree where decisions at each node are taken using our accumulation scheme. Results obtained using this new algorithm compare very favorably to accumulation (both probabilistic and discriminative) and voting scheme.

[1]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[2]  John Y. Aloimonos,et al.  Unification and integration of visual modules: an extension of the Marr Paradigm , 1989 .

[3]  James J. Clark,et al.  Data Fusion for Sensory Information Processing Systems , 1990 .

[4]  Heinrich H. Bülthoff,et al.  Bayesian Models for Seeing Shapes and Depth , 1990 .

[5]  B. Parhami.  Voting algorithms , 1994 .

[6]  Glenn Healey,et al.  Combining color and geometric information for the illumination invariant recognition of 3-D objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[7]  Jiri Matas,et al.  On representation and matching of multi-coloured objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[8]  Cordelia Schmid,et al.  Combining greyvalue invariants with local constraints for object recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Bartlett W. Mel.  SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition , 1997, Neural Computation.

[10]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[11]  Vittorio Murino,et al.  A voting-based approach for fast object recognition in underwater acoustic images , 1997 .

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

[13]  Jochen Triesch,et al.  Object Recognition with Multiple Feature Types , 1998 .

[14]  Andrea Salgian,et al.  A cubist approach to object recognition , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[15]  Henrik I. Christensen,et al.  A Model-Free Voting Approach for Integrating Multiple Cues , 1998, ECCV.

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

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

[18]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..

[19]  Song Wang,et al.  Tracking of object with SVM regression , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[20]  Jing Peng,et al.  Adaptive quasiconformal kernel metric for image retrieval , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[21]  Andrew Blake,et al.  Computationally efficient face detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[22]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

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

[24]  Jitendra Malik,et al.  Spectral Partitioning with Indefinite Kernels Using the Nyström Extension , 2002, ECCV.

[25]  Francesca Odone,et al.  Hausdorff Kernel for 3D Object Acquisition and Detection , 2002, ECCV.

[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]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[28]  Lior Wolf,et al.  Kernel principal angles for classification machines with applications to image sequence interpretation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[29]  Zhaohui Sun.  Adaptation for multiple cue integration , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[30]  Barbara Caputo,et al.  Recognition with local features: the kernel recipe , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

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

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

[33]  Jochen Triesch,et al.  Shared Features for Scalable Appearance-Based Object Recognition , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[34]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.