Revisiting component tree based segmentation using meaningful photometric informations

Authors:
Michał Kazimierz Kowalczyk;Bertrand Kerautret;Benoît Naegel;Jonathan Weber
Affiliations:
LORIA, UMR 7503, Université de Lorraine, France;LORIA, UMR 7503, Université de Lorraine, France;LSIIT, UMR 7005, Université de Strasbourg, France;LORIA, UMR 7503, Université de Lorraine, France
Venue:
ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
Year:
2012

Citing 5
Cited 0

Component-Trees and Multi-value Images: A Comparative Study

ISMM '09 Proceedings of the 9th International Symposium on Mathematical Morphology and Its Application to Signal and Image Processing
An extension of component-trees to partial orders

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Interactive segmentation based on component-trees

Pattern Recognition
Spatio-temporal quasi-flat zones for morphological video segmentation

ISMM'11 Proceedings of the 10th international conference on Mathematical morphology and its applications to image and signal processing
Meaningful Scales Detection along Digital Contours for Unsupervised Local Noise Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes to revisit a recent interactive segmentation algorithm based on an original image representation called the component-tree [1]. This method relies on an optimisation process allowing to choose a segmentation result fitting at best some image markers defined by the user. We propose different solutions to improve the efficiency of the method, in particular by including meaningful photometric informations and by assessing automatically the user parameter α.