A Graph Labelling Approach for Connected Feature Selection
Many authors have already proposed linear feature extraction algorithms. In most cases, these algorithms can not guarantee the extraction of adjacency relations between extracted features. Object contours appearing in the analyzed images are often fragmented into non-connected features. Nevertheless, the use of some topological information enables to reduce substantially the complexity of matching and registration algorithms.
Here, we formulate the problem of linear feature extraction as an optimal labelling problem of a topological map obtained from low level operations. The originality of our approach is the maintaining of this data structure during the extraction process and the formulation of the problem of feature extraction as a global optimization problem.
keywordsContour map feature extraction model selection MDL
- 2.Brunn, A., Weidner, U., Forstner, W., Model-based 2D Shape Recovery, in: Mustererkennung 1995, G. Sagerer et al. (eds.), Springer-Verlag, 260–268Google Scholar
- 3.Danuser, G., Stricker, M., Parametric Model Fitting: From Inlier Characterization to Outlier Detection, IEEE Trans. on PAMI, 20(2) (1998) 263–280Google Scholar
- 4.Dickinson, S.J., Pentland, A. P., Rosenfeld, A., 3-D Shape Recovery Using Aspect Matching, IEEE Trans. on PAMI, 14(2) (1992) 174–198Google Scholar
- 5.Fiorio, C., A topologically Consistent Representation for Image Analysis: the Frontiers Topological Graph, DGCI’96, Lectures Notes in Computer Sciences, no. 1176, (1996) 151–162Google Scholar
- 6.Fuchs, C., Frostner, W., Polymorphic Grouping for Image Segmentation, Proc. 5th ICCV, (1995) 175–182Google Scholar
- 8.Harris, C., Stephens, M., Combined Corner and Edge Detector, Alvey88, (1998) 147–152Google Scholar
- 12.Lindenbaum, M., Bruckstein, A., On recursive, O(N) Partitioning of Digitized Curve into Digital Straight Segments, IEEE Trans. on PAMI, 15(9) (1993) 949–953Google Scholar
- 13.Lindeberg, T., Li, M.-X., Segmentation and Classification of Edges Using Minimum Description Length Approximation and Complementary Junction Cues, Tech. Rep. ISRN KTH/NA/P-96/01-SE, Jan. 1996.Google Scholar
- 14.McLean, G.F., Kotturi, D., Vanishing Point Detection by Line Clustering, IEEE Trans. on PAMI, 17(11) (1995) 1090–1095Google Scholar
- 15.Mohan, R., Nevatia, R., Using Perceptual Organization to Extract 3-D Structures, IEEE Trans. on PAMI 11(11) (1989) 1121–1139Google Scholar
- 16.Pierrot Deseilligny, M., Stamon, G., Suen, C., Veinerization: A New Shape Description for Flexible Skeletonization, IEEE Trans. on PAMI, 20(5) (1998) 505–521Google Scholar
- 18.Torr, P. H. S., Geometric Motion Segmentation and Model Selection, Philosophical Transactions of the Royal Society A, J. Lasenby. and A. Zisserman. and R. Cipolla. and H. Longuet-Higgins editors, pp. 1321Google Scholar