Paper Info
Title
Hyperspectral image segmentation using Binary Partition Trees.
Abstract
The work presented here proposes a new Binary Partition Tree pruning strategy aimed at the segmentation of hyperspectral images. The BPT is a region-based representation of images that involves a reduced number of elementary primitives and therefore allows to design a robust and efficient segmentation algorithm. Here, the regions contained in the BPT branches are studied by recursive spectral graph partitioning. The goal is to remove subtrees composed of nodes which are considered to be similar. To this end, affinity matrices on the tree branches are computed using a new distance-based measure depending on canonical correlations relating principal coordinates. Experimental results have demonstrated the good performances of BPT construction and pruning.
Year
DOI
Venue
2011
10.1109/ICIP.2011.6115666
ICIP
Keywords
Field
DocType
geophysical image processing,image representation,image segmentation,trees (mathematics),BPT,affinity matrices,binary partition tree pruning strategy,hyperspectral image segmentation,recursive spectral graph partitioning,region-based representation,Binary Partition Tree,Hyperspectral imaging,canonical correlations,graph partitioning,segmentation
Pattern recognition,Segmentation,Computer science,Matrix (mathematics),Image segmentation,Hyperspectral imaging,Artificial intelligence,Graph partition,Partition (number theory),Pruning,Binary number
Conference
ISSN
Citations 
PageRank 
1522-4880
2
0.44
References 
Authors
5
3
Name
Order
Citations
PageRank
Silvia Valero117113.81
Philippe Salembier260387.65
Jocelyn Chanussot34145272.11