View-based 3-D object recognition using shock graphs

The shock graph is an emerging shape representation for object recognition, in which a 2-D silhouette is decomposed into a set of qualitative parts, captured in a directed acyclic graph. Although a number of approaches have been proposed for shock graph matching, these approaches do not address the equally important indexing problem. We extend our previous work in both shock graph matching and hierarchical structure indexing to propose the first unified framework for view-based 3-D object recognition using shock graphs. The heart of the framework is an improved spectral characterization of shock graph structure that not only drives a powerful indexing mechanism (to retrieve similar candidates from a large database), but also drives a matching algorithm that can accommodate noise and occlusion. We describe the components of our system and evaluate its performance using both unoccluded and occluded queries. The large set of recognition trials (over 25,000) from a large database (over 1400 views) represents one of the most ambitious shock graph-based recognition experiments conducted to date.

[1]  Christian Böhm,et al.  Searching in high-dimensional spaces: Index structures for improving the performance of multimedia databases , 2001, CSUR.

[2]  M J Tarr,et al.  Recognizing Silhouettes and Shaded Images across Depth Rotation , 1999, Perception.

[3]  Olivier D. Faugeras,et al.  Reconciling Distance Functions and Level Sets , 1999, Scale-Space.

[4]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Philip N. Klein,et al.  Shock-Based Indexing into Large Shape Databases , 2002, ECCV.

[6]  D. Cvetkovic,et al.  Spectra of Graphs: Theory and Applications , 1997 .

[7]  Shinji Umeyama,et al.  An Eigendecomposition Approach to Weighted Graph Matching Problems , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Grégoire Malandain,et al.  Euclidean skeletons , 1998, Image Vis. Comput..

[9]  Gabriella Sanniti di Baja,et al.  Ridge points in Euclidean distance maps , 1992, Pattern Recognit. Lett..

[10]  M. F.,et al.  Bibliography , 1985, Experimental Gerontology.

[11]  I. Biederman,et al.  Recognizing depth-rotated objects: Evidence and conditions for three-dimensional viewpoint invariance. , 1993 .

[12]  D. Kozen.  A clique problem equivalent to graph isomorphism , 1978, SIGA.

[13]  Hanan Samet,et al.  Ranking in Spatial Databases , 1995, SSD.

[14]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[15]  S. Zucker,et al.  Continuous-based Heuristics for Graph and Tree Isomorphisms, with Application to Computer Vision , 2000 .

[16]  Kaleem Siddiqi,et al.  A shock grammar for recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  William T. Freeman,et al.  The generic viewpoint assumption in a framework for visual perception , 1994, Nature.

[18]  John A. Goldak,et al.  Constructing discrete medial axis of 3-D objects , 1991, Int. J. Comput. Geom. Appl..

[19]  B. Kimia,et al.  3D object recognition using shape similiarity-based aspect graph , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[20]  Horst Bunke,et al.  Subgraph Isomorphism in Polynomial Time , 1995 .

[21]  Refractor.  Vision , 2000, The Lancet.

[22]  Shin'ichi Satoh,et al.  The SR-tree: an index structure for high-dimensional nearest neighbor queries , 1997, SIGMOD '97.

[23]  Kaleem Siddiqi,et al.  Robust and efficient skeletal graphs , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[24]  I. Biederman.  Recognizing depth-rotated objects: a review of recent research and theory. , 2000, Spatial vision.

[25]  Kaleem Siddiqi,et al.  Attributed tree matching and maximum weight cliques , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[26]  Richard M. Karp,et al.  A n^5/2 Algorithm for Maximum Matchings in Bipartite Graphs , 1971, SWAT.

[27]  Ali Shokoufandeh,et al.  A Unified Framework for Indexing and Matching Hierarchical Shape Structures , 2001, IWVF.

[28]  Ali Shokoufandeh,et al.  On the Representation and Matching of Qualitative Shape at Multiple Scales , 2002, ECCV.

[29]  Robert E. Tarjan,et al.  Faster scaling algorithms for general graph matching problems , 1991, JACM.

[30]  Michael Doob,et al.  Spectra of graphs , 1980 .

[31]  Robert L. Ogniewicz,et al.  Skeleton-space: a multiscale shape description combining region and boundary information , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[32]  R. Ogniewicz.  Automatic Medial Axis Pruning by Mapping Characteristics of Boundaries Evolving under the Euclidean , 1995 .

[33]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[34]  Václav Koubek,et al.  A Reduct-and-Closure Algorithm for Graphs , 1979, MFCS.

[35]  H. Blum.  Biological shape and visual science. I. , 1973, Journal of theoretical biology.

[36]  Frederic Fol Leymarie,et al.  Simulating the Grassfire Transform Using an Active Contour Model , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[37]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[38]  Olivier Faugeras,et al.  Reconciling Distance Functions and Level Sets , 2000, J. Vis. Commun. Image Represent..

[39]  John Midgley,et al.  Probabilistic eigenspace object recognition in the presence of occlusion , 2001 .

[40]  D. Cvetkovic,et al.  Eigenspaces of graphs: Bibliography , 1997 .

[41]  Harry G. Barrow,et al.  Subgraph Isomorphism, Matching Relational Structures and Maximal Cliques , 1976, Inf. Process. Lett..

[42]  Anil K. Jain,et al.  3D object recognition using invariant feature indexing of interpretation tables , 1992, CVGIP Image Underst..

[43]  Ali Shokoufandeh,et al.  Indexing using a spectral encoding of topological structure , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[44]  Tapas Kanungo,et al.  Hierarchical organization of appearance-based parts and relations for object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[45]  Benjamin B. Kimia,et al.  3D Object Recognition Using Shape Similarity-Based Aspect Graph , 2001, ICCV.

[46]  Steven W. Reyner,et al.  An Analysis of a Good Algorithm for the Subtree Problem , 1977, SIAM J. Comput..

[47]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..

[48]  Tapas Kanungo,et al.  Object recognition using appearance-based parts and relations , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[49]  Philip N. Klein,et al.  Shape matching using edit-distance: an implementation , 2001, SODA '01.

[50]  Rakesh M. Verma,et al.  An Analysis of a Good Algorithm for the Subtree Problem, Corrected , 1989, SIAM J. Comput..

[51]  Steven Gold,et al.  A Graduated Assignment Algorithm for Graph Matching , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[52]  Yehezkel Lamdan,et al.  On recognition of 3-D objects from 2-D images , 2011, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[53]  Ali Shokoufandeh,et al.  Shock Graphs and Shape Matching , 1998, International Journal of Computer Vision.

[54]  Kenneth C. Sevcik,et al.  Quantization Techniques for Similarity Search in High-Dimensional Data Spaces , 2003, BNCOD.

[55]  Edwin R. Hancock,et al.  A robust eigendecomposition framework for inexact graph-matching , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[56]  Kaleem Siddiqi,et al.  Matching Hierarchical Structures Using Association Graphs , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[57]  Shimon Ullman,et al.  Recognizing solid objects by alignment with an image , 1990, International Journal of Computer Vision.

[58]  Kaleem Siddiqi,et al.  Ligature instabilities in the perceptual organization of shape , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[59]  PaperNo.  Recognition of shapes by editing shock graphs , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.