Semi-supervised Learning with Constraints for Multi-view Object Recognition

In this paper we present a novel approach to multi---view object recognition based on kernel methods with constraints. Differently from many previous approaches, we describe a system that is able to exploit a set of views of an input object to recognize it. Views are acquired by cameras located around the object and each view is modeled by a specific classifier. The relationships among different views are formulated as constraints that are exploited by a sort of collaborative learning process. The proposed approach applies the constraints on unlabeled data in a semi---supervised framework. The results collected on the COIL benchmark show that constraint based learning can improve the quality of the recognition system and of each single classifier, both on the original and noisy data, and it can increase the invariance with respect to object orientation.

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

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

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

[4]  Cordelia Schmid,et al.  3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints , 2006, International Journal of Computer Vision.

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

[6]  Trevor Darrell,et al.  Unsupervised feature selection via distributed coding for multi-view object recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[8]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[10]  Bernt Schiele,et al.  Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search , 2004, DAGM-Symposium.

[11]  Siwei Lyu,et al.  Mercer kernels for object recognition with local features , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[13]  Sadegh Abbasi,et al.  Automatic Selection of Optimal Views in Multi-view Object Recognition , 2000, BMVC.

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

[15]  Luc Van Gool,et al.  Towards Multi-View Object Class Detection , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  M.M. Van Hulle,et al.  View-based 3D object recognition with support vector machines , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).