DocumentCode :
3370178
Title :
Metric tensor for multicomponent edge detection
Author :
Rousseau, Sylvain ; Helbert, David ; Carré, Philippe ; Blanc-Talon, Jacques
Author_Institution :
XLIM, Univ. of Poitiers, Futuroscope Chasseneuil, France
fYear :
2010
fDate :
26-29 Sept. 2010
Firstpage :
1953
Lastpage :
1956
Abstract :
In this paper, we present the use of differential geometry for the segmentation of multispectral images, which allows us to unify several known methods including projecting onto a particular axis or a particular plan. This is done by choosing a metric tensor on the feature space computing the pullback of the metric tensor and applying standard Di Zenzo algorithm.
Keywords :
edge detection; image segmentation; tensors; image segmentation; metric tensor; multicomponent edge detection; multispectral images; Artificial neural networks; Image color analysis; Image edge detection; Measurement; Noise; Tensile stress; Riemannian manifold; metric pullback; metric tensor;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2010.5653763
Filename :
5653763
Link To Document :
بازگشت