MODIFIED DISTANCE SIGNATURE AS AN ENHANCIVE DESCRIPTOR OF COMPLEX PLANAR SHAPES

Andrzej Florek, Tomasz Piascik

Abstract

In this paper, a simple and efficient approach to classify planar shapes is proposed. This approach is based on comparison of areas of dynamicly sampled classic signatures. Presented approach is dedicated to the recognition of convex and concave planar shapes, containing openings in the area enclosed by boundary. A way to calculate the discrete representation of classic distance-versus-angle signatures, a reduction of memory requirements and a number of calculations are presented. Analysis carried out from classification experiments applied to images of real objects (car-engine collector seals) indicates good properties of dissimilarity coefficients, based on modified signature, taken as an object descriptor.

References

  1. Demant, C., Streicher-Abel, B., Waszkiewitz, P., 1999. Industrial Image Processing. Visual Quality Control in Manufacturing, Springer Verlag, Heidelberg.
  2. Gonzales, R.C., Woods, R.E., 1992. Digital Image Processing, Addison-Wesley, Reading MA.
  3. Parker, J.R., Zhang, Z., 1998. Object recognition using signatures, Proc. IASTED Int. Conf. Signal and Image Processing, Las Vegas, pp. 1-5.
  4. Zhang, D., Lu G., 2004. Review of shape representation and description techniques, Pattern Recognition 37 (1), pp. 1-19.
Download


Paper Citation


in Harvard Style

Florek A. and Piascik T. (2007). MODIFIED DISTANCE SIGNATURE AS AN ENHANCIVE DESCRIPTOR OF COMPLEX PLANAR SHAPES . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 225-230. DOI: 10.5220/0002043702250230


in Bibtex Style

@conference{visapp07,
author={Andrzej Florek and Tomasz Piascik},
title={MODIFIED DISTANCE SIGNATURE AS AN ENHANCIVE DESCRIPTOR OF COMPLEX PLANAR SHAPES},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={225-230},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002043702250230},
isbn={978-972-8865-74-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - MODIFIED DISTANCE SIGNATURE AS AN ENHANCIVE DESCRIPTOR OF COMPLEX PLANAR SHAPES
SN - 978-972-8865-74-0
AU - Florek A.
AU - Piascik T.
PY - 2007
SP - 225
EP - 230
DO - 10.5220/0002043702250230