Object recognition using appearance-based parts and relations

The recognition of general three-dimensional objects in cluttered scenes is a challenging problem. In particular, the design of a good representation suitable to model large numbers of generic objects that is also robust to occlusion has been a stumbling block in achieving success. In this paper, we propose a representation using appearance-based parts and relations to overcome these problems. Appearance-based parts and relations are defined in terms of closed regions and the union of these regions, respectively. The regions are segmented using the MDL principle, and their appearance is obtained from collection of images and compactly represented by parametric manifolds in the two eigenspaces spanned by the parts and the relations.

[1]  Erkki Oja,et al.  Subspace methods of pattern recognition , 1983 .

[2]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  David J. Kriegman,et al.  Representations for Recognizing Complex Curved 3D Objects , 1994, Object Representation in Computer Vision.

[4]  Martial Hebert,et al.  Object Representation in Computer Vision , 1994, Lecture Notes in Computer Science.

[5]  Thomas O. Binford.  Body-Centered Representation and Perception , 1994, Object Representation in Computer Vision.

[6]  Martial Hebert,et al.  Report on the 1995 Workshop on 3-D Object Representations in Computer Vision , 1994, Object Representation in Computer Vision.

[7]  Octavia I. Camps.  Towards a Robust Physics-Based Object Recognition System , 1994, Object Representation in Computer Vision.

[8]  Tapas Kanungo,et al.  A fast algorithm for MDL-based multi-band image segmentation , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Kanungo,et al.  A fast algorithm for MDL-based multi-band image segmentation , 1994, CVPR 1994.

[10]  M. S. Costa,et al.  Scene analysis using appearance-based models and relational indexing , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[11]  John Krumm,et al.  Eigenfeatures for planar pose measurement of partially occluded objects , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Horst Bischof,et al.  Dealing with occlusions in the eigenspace approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.