Abstract
This paper deals with the problem of automatic reconstruction of contour lines out of scanned maps. Our approach is essentially based on the global topology of the contour lines (i.e. a set of nonintersecting closed lines), but we use also some local and geometrical informations to guide the reasoning.
Our proposed method starts from a map scanned in RGB. The image is first segmented by a colour classification process, and the objects are skeletonized end vectorized. Then, by a local analysis, we weight and add some hypothetical edges. By a relaxation process, we try to orientate the elevation curves, and so we could re-adjust the weight. Finally, we found a topologycally correct solution by resolving the dual problem (i.e. a bi-colouring problem).
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
A. Khotanzad and E. Zink. Color paper map segmentation using eigenvector line-fitting. In proc. of the IEEE Southwest Symposium on Image Analysis and Interpretation, pages 190–194, 1996.
A. Mecocci and M. Lilla. AI-based technique for tracking chains of discontinuous symbols and its application to the analysis of topographic maps. In Image and signal processing for remote sensing, volume 2315, pages 680–691, 1994.
A. Rozenfield, R. A. Hummel and S. W. Zucker. Scene labeling by relaxation operations. IEEE Trans. on System, Man, Mach. and Cyber., 6(6):421–433, June 1976.
F. Dupont, M. P. Deseilligny, and M. Gondran. Automatic interpretation of scanned maps: Reconstruction of contour lines. In Proc. of the,2nd IAPR Workshop on Graphics Recognition (GREC'97), pages 193–200, 1997.
H. Yamada, K. Yamamoto and K. Hosokawa. Directional Mathematical Morphology and reformalized Hough transformation for the analysis of topographic maps. IEEE PAMI, 15(4):380–387, April 1993.
H. Yamada, K. Yamamoto and T. Saito. Recognition of elevation value in topographic maps by Multi-Angled Parallelism. Int. journal of Pattern Recogn. and Artificial Intelligence, 8(5):149–173, 1994.
H. Yan. Color map image segmentation using optimized nearest neighbor classifiers. In Proc. of the 2nd Int. Conf. on Document Analysis and Recognition (ICDAR'93), pages 111–114, 1993.
H. Yan and J. Wu. Character and line extraction from color map using a multi-layer neural network. Pattern Recognition Letters, 15:97–103, January 1994.
J. Y1ä-Jääski and H. Ahonen. Knowledge based analysis of line drawing. In The 6th Scandinavian Conference on Image Analysis, pages 774–777, June 1989.
K. J. Goodson and P. H. Lewis. A knowledge based line recognition system. Pattern Recognition Letters, 11:295–304, April 1990.
K. Yamamoto, H. Yamada and S. Muraki. Symbol recognition and surface reconstruction from topographic map by parallel method. In Proc. of the 2nd Int. Conf. on Document Analysis and Recognition (ICDAR'93), pages 914–917, 1993.
L. Eikvil, K. Aas and H. Koren. Tools for interactive map conversion and vectorization. In Proc. of the 3th Int. Conf. on Document Analysis and Recognition (ICDAR'95), pages 927–930, 1995.
M. P. Deseilligny. Lecture automatique de cartes. PhD thesis, Université PARIS V, 1994.
M. P. Deseilligny, F. Dupont and H. Le Men. Automatic Interpretation of Contour Lines out of Scanned Maps: An A Priori Topological Knowledge Based Approach. In Proc. of the 4th Int. Conf. on Document Analysis and Recognition (ICDAR'97), page 91, 1997.
M. P. Deseilligny, H. Le Men and G. Stamon. Character strings recognition on maps, a rotation-invariant recognition method. Pattern Recognition Letters, 16:1297–1310, 1995.
M. Roux, S. Kunduri, A. Clainchard and H. Maître. Analyse colorimétrique de cartes numérisées. Technical report, Ecole Nationale Supérieur des Télécommunications (Paris), 1996.
R. Mariani, F. Lecourt, M. P. Deseilligny, J. Labiche, Y. Lecourtier. Interpétation de cartes géographiques. Algorithmes de reconstruction des réseux hydrographiques et routiers. In RFIA'96, Rennes, France, pages 34–42, january 1996.
R. Mariani, M. P. Deseilligny, J. Labiche, Y. Lecourtier. Geographic Map understanding. Attributes computation for hydrographic network. In proc. of the IEEE Southwest Symposium on Image Analysis and Interpretation, pages 252–257, april 1996.
S. Muraki, N. Yokoya and K. Yamamoto. 3D Surface reconstruction from contour line image by a regularization method. SPIE — Close range photogrametry meets machine vision, 1395:226–233, 1990.
S. Shimada, K. Maruyama, A. Matsumoto and K. Hiraki. Agent-based parallel recognition method of contour lines. In Proc. of the 3th Int. Conf. on Document Analysis and Recognition (ICDAR'95), pages 154–157, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dupont, F., Deseilligny, M.P., Gondran, M. (1998). Automatic interpretation of scanned maps: Reconstruction of Contour Lines. In: Tombre, K., Chhabra, A.K. (eds) Graphics Recognition Algorithms and Systems. GREC 1997. Lecture Notes in Computer Science, vol 1389. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64381-8_49
Download citation
DOI: https://doi.org/10.1007/3-540-64381-8_49
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64381-4
Online ISBN: 978-3-540-69766-4
eBook Packages: Springer Book Archive