Sensitivity analysis for object recognition from large structural libraries

The paper studies the structural sensitivity of line pattern recognition using shape graphs. We compare the recognition performance for four different algorithms. Each algorithm uses a set of pairwise geometric attributes and a neighbourhood graph to represent the structure of the line patterns. The first algorithm uses a pairwise geometric histogram, the second uses a relational histogram on the edges of the shape graph, the third compares the set of attributes on the edges of the shape graph and the final algorithm compares the arrangement of line correspondences using graph matching. The different algorithms are compared under line deletion, line addition, line fragmentation and line end point measurement errors. It is the graph matching algorithm which proves to be the most effective.

[1]  Josef Kittler,et al.  A weighted combination of classifiers employing shared and distinct representations , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[2]  Edwin R. Hancock,et al.  Structural Matching by Discrete Relaxation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

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

[4]  Tyng-Luh Liu,et al.  Visual Deconstruction: Recognizing Articulated Objects , 1997, EMMCVPR.

[5]  Benoit Huet,et al.  Graph Matching for Shape Retrieval , 1998, NIPS.

[6]  Michael Leyton,et al.  A Process-Grammar for Shape , 1988, Artif. Intell..

[7]  Yali Amit,et al.  Graphical Templates for Model Registration , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  William Rucklidge,et al.  Locating objects using the Hausdorff distance , 1995, Proceedings of IEEE International Conference on Computer Vision.

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

[10]  Benoit Huet,et al.  Relational histograms for shape indexing , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[11]  Linda G. Shapiro,et al.  Interesting patterns for model-based machine vision , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[12]  Edwin R. Hancock,et al.  An Energy Function and Continuous Edit Process for Graph Matching , 1998, Neural Computation.

[13]  Benoit Huet,et al.  Fuzzy relational distance for large-scale object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[14]  King-Sun Fu,et al.  A distance measure between attributed relational graphs for pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  Robert M. Haralick,et al.  A Metric for Comparing Relational Descriptions , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Edwin R. Hancock,et al.  Matching Delaunay Graphs , 1995, ICIAP.

[17]  Neil A. Thacker,et al.  Assessing the completeness properties of pairwise geometric histograms , 1995, Image Vis. Comput..

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

[19]  Benoit Huet,et al.  Cartographic indexing into a database of remotely sensed images , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.