Abstract
This paper presents a segmentation algorithm for image sequences, by multicriteria region merging. The output of a connected filter is simplified by iteratively merging the two most similar adjacent regions, while a given representation quality is preserved. We have defined several region-similitude criteria: grey-level, texture and motion resemblance. Texture and motion criteria introduce a feedback “segmentation-coding step” that improves coding efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
LEP. First results of motion prediction based on a differential estimation method. In SIM(94) 35 COST 211, Tampere, June 1994.
B. Marcotegui, J. Crespo, and F. Meyer. Morphological segmentation using texture and coding cost. IEEE Workshop on Non Linear Signal/Image Processing, Juin 1995.
F. Meyer. Algorithmes à base de files d’attente hiérarchique. Technical Report NT-46/90/MM, Ecole des Mines de Paris, Centre de Morphologie Mathématique, September 1990.
O. Monga. Segmentation d’Images par Croissance Hiérarchique de Régions. PhD thesis, Université Paris Sud. Centre d’Orsay, 1988.
M. Pardàs and P. Salembier. Time-recursive segmentation of image sequences. In EUSIPCO-94, Edinburgh, Sept 1994.
J. Serra and P. Salembier. Connected operators and pyramids. In Proceedings of SPIE, San Diego, 1993.
L. Vincent. Greyscale area openings and closings, their efficient implementation and applications. In Workshop on Mathematical Morphology, Barcelona, pages 22–27, May 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Kluwer Academic Publishers
About this chapter
Cite this chapter
Marcotegui, B. (1996). Segmentation Algorithm by Multicriteria Region Merging. In: Maragos, P., Schafer, R.W., Butt, M.A. (eds) Mathematical Morphology and its Applications to Image and Signal Processing. Computational Imaging and Vision, vol 5. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-0469-2_36
Download citation
DOI: https://doi.org/10.1007/978-1-4613-0469-2_36
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-8063-4
Online ISBN: 978-1-4613-0469-2
eBook Packages: Springer Book Archive