A basin morphology approach to colour image segmentation by region merging

Authors:
Erchan Aptoula;Sébastien Lefèvre
Affiliations:
UMR, CNRS, Louis Pasteur University, LSIIT, Pôle API, Illkirch Cedex, France;UMR, CNRS, Louis Pasteur University, LSIIT, Pôle API, Illkirch Cedex, France
Venue:
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Year:
2007

Citing 8
Cited 0

Digital image processing (2nd ed.)

Digital image processing (2nd ed.)
Why mathematical morphology needs complete lattices

Signal Processing
Extensive operators in partition lattices for image sequence analysis

Signal Processing - Video segmentation for content-based processing manipulation
Image Analysis and Mathematical Morphology

Image Analysis and Mathematical Morphology
Modelling and segmentation of colour images in polar representations

Image and Vision Computing
A comparative study on multivariate mathematical morphology

Pattern Recognition
Fast segmentation of high-resolution satellite images using watershed transform combined with an efficient region merging approach

IWCIA'04 Proceedings of the 10th international conference on Combinatorial Image Analysis
Morphological operators on the unit circle

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The problem of colour image segmentation is investigated in the context of mathematical morphology. Morphological operators are extended to colour images by means of a lexicographical ordering in a polar colour space, which are then employed in the preprocessing stage. The actual segmentation is based on the use of the watershed transformation, followed by region merging, with the procedure being formalized as a basin morphology, where regions are "eroded" in order to form greater catchment basins. The result is a fully automated processing chain, with multiple levels of parametrisation and flexibility, the application of which is illustrated by means of the Berkeley segmentation dataset.