2D-Shape Analysis Using Shape Invariants

Abstract:

High efficiency detection of two-dimensional objects is achieved by an appropriate choice of object invariants. The aim is to show an example of the construction of an algorithm for rapid identification also for highly complex objects. The program structure works in a similar way as animal systems in nature. Differentiating runs from whole to details. They are used to shape invariants. The program algorithm is specifically used a surfaces invariant, which represents a whole. Then was used a boundary length invariant around the object. Finally, the chord distribution code was used, which represent a detail of object recognition. The actual computational algorithms are not software-intensive and easy to debug. System uses the redundancy of uncertain information about the shape. In principle, chosen a certain balance between the confidence level of recognition and repetition of shape recognition by various methods.

• Periodical: Applied Mechanics and Materials (Volume 613)
• Pages: 452-457
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.613.452
• Online since: August 2014
• Authors: Tomáš Stejskal*
• Keywords: Object Recognition, Redundancy, Shape Invariant

References

[1] L.M. Lui, Y. Wang, T.F. Chan, PDE on manifold using global conformal parametrization, Variational, Geometric, and Level Set Methods in Computer Vision: Third International Workshop, VLSM 2005, Beijing, China, Oct. 16, 2005, pp.307-319.

DOI: 10.1007/11567646

[2] Zhu, S.C., Yuille, A.L.: A flexible object recognition and modeling system. IJCV 20 (1996) 8.

[3] Liu, T., Geiger, D.: Approximate tree matching and shape similarity. ICCV (1999) 456–462.

[4] Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. on Pattern Analysis and Machine Intelligence 24 (2002) 509–522.

DOI: 10.1109/34.993558

[5] Ericsson, A., Astrom, K.: An affine invariant deformable shape representation for general curves. Proc. IEEE Intl. Conf. on Computer Vision 2 (2003) 1142–1149.

DOI: 10.1109/iccv.2003.1238477

[6] Sebastian, T., Klein, P., Kimia, B.: Shock based indexing into large shape databases. European Conf. on Computer Vision 3 (2002) 731–746.

DOI: 10.1007/3-540-47977-5_48

[7] Dryden, I., Mardia, K.: Statistical shape analysis. John Wiley and Son (1998).

[8] Csetverikov D. et al, Basic Algorithms for Digital Image Analysis In : http: /ssip2003. info. uvt. ro/lectures/chetverikov/shape_analysis. pdf.

[9] Sonka Milan, Hlavac Vaclav, Boyle Roger, Image Processing, Analysis, and Machine Vision published by PWS (1998), ISBN 0-534-95393-X.

DOI: 10.1117/12.256634

[10] Willard S., General Topology, Publisher: Dover Publications (2004) p.384. ISBN-10: 0486434796.

[11] Fabian Stanislav, Krenický Tibor, Design, Testing and Characteristics of Mechatronic Devices. In: Zurich-Durnten: Trans Tech Publications (2014), 120 p., ISBN 978-3-03785-931-5.

[12] Krenický Tibor, Flexibilný prístup k monitorovaniu mechatronických systémov. In: Strojárstvo. Roč. 17, č. 9 (2013), s. 104-105. - ISSN 1335-2938.