Morphology Based Spatial Relationships between Local Primitives in Line Drawings
Local primitives and their spatial relationships are useful in the analysis, recognition and retrieval of document and patent binary images. In this paper, a morphology based approach is proposed to establish the connections between the local primitives found at the optimally detected junction points and end points. The grayscale geodesic dilation is employed as the basic technique by taking a marker image with gray values at the local primitives and the skeleton of the original image as the mask image. The geodesic paths along the skeleton between the local primitives are traversed and their points of contact are protected by updating the mask image after each geodesic dilation iteration. By scanning the final marker image for the contact points of the traversed geodesic paths, connections between the local primitives are established. The proposed approach is robust and scale invariant.
Keywordslocal primitives spatial relationships grayscale geodesic dilation
Unable to display preview. Download preview PDF.
- 3.Bhatti, N.A., Hanbury, A.: Co-occurrence bag of words for object recognition. In: Proceedings of the 15th Computer Vision Winter Workshop, pp. 21–28 (2010)Google Scholar
- 4.Bhatti, N.A., Hanbury, A.: Detection and classification of local primitives in line drawings. In: Proceedings of the 35th Austrian Association for Pattern Recognition (2011)Google Scholar
- 5.Bhatti, N.A., Hanbury, A.: Granulometry based detection of junction and end points in patent drawings. In: Proceedings of the 7th International Symposium on Image and Signal Processing and Analysis, ISPA (2011)Google Scholar
- 6.Desolneux, A., Moisan, L., Morel, J.-M.: Seeing, Thinking and Knowing. In: Carsetti, A. (ed.) Kluwer Academic Publishers, Dordrecht (2004)Google Scholar
- 7.Fonseca, M.J., Ferreira, A., Jorge, J.A.: Content-based retrieval of technical drawings. Special Issue of International Journal of Computer Applications in Technology, IJCAT (2004)Google Scholar
- 9.Förstner, W.: Uncertain neighborhood relations of point sets and fuzzy delaunay triangulation. In: Mustererkennung 1999, 21. DAGM-Symposium, pp. 213–222 (1999)Google Scholar
- 11.Huet, B., Guarascio, G., Kern, N.J., Mérialdo, B.: Relational skeletons for retrieval in patent drawings. In: ICIP, pp. 737–740 (2001)Google Scholar
- 12.Leung, W.H., Chen, T.: User-independent retrieval of free-form hand-drawn sketches. In: Proc. of the IEEE ICASSP 2002, pp. 2029–2032. IEEE Press (2002)Google Scholar
- 15.Parker, C., Chen, T.: Hierarchical matching for retrieval of hand-drawn sketches. In: ICME, pp. 29–32. IEEE Computer Society, Washington, DC, USA (2003)Google Scholar
- 18.Forstner, W., Heuel, S.: A dual, scalable and hierarchical representation for. perceptual organization of binary images. In: Workshop on Perceptual Organization in Computer Vision. IEEE Computer Society (1998)Google Scholar