Attribute Profiles from Partitioning Trees

被引：12

作者：

Bosilj, Petra ^{[1
,4
]}

Damodaran, Bharath Bhushan ^{[1
]}

Aptoula, Erchan ^{[2
]}

Dalla Mura, Mauro ^{[3
]}

Lefevre, Ebastien ^{[1
]}

机构：

[1] Univ Bretagne Sud, IRISA, Vannes, France

[2] Gebze Tech Univ, Inst Informat Technol, Gebze, Turkey

[3] Grenoble INP, Dept Image & Signal, GIPSA Lab, St Martin Dheres, France

[4] Univ Lincoln, Lincoln, England

来源：

MATHEMATICAL MORPHOLOGY AND ITS APPLICATIONS TO SIGNAL AND IMAGE PROCESSING (ISMM 2017) | 2017年 / 10225卷

关键词：

Attribute profiles; Partitioning trees; alpha-tree; (omega)-tree; Hyperspectral images; SPECTRAL-SPATIAL CLASSIFICATION; IMAGE CLASSIFICATION; SEGMENTATION; FILTERS; SHAPES;

D O I：

10.1007/978-3-319-57240-6_31

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Morphological attribute profiles are among the most prominent spatial-spectral pixel description tools. They can be calculated efficiently from tree based representations of an image. Although widely and successfully used with various inclusion trees (i.e., component trees and tree of shape), in this paper, we investigate their implementation through partitioning trees, and specifically alpha- and (omega)-trees. Our preliminary findings show that they are capable of comparable results to the state-of-the-art, while possessing additional properties rendering them suitable for the analysis of multivariate images.

引用

收藏

页码：381 / 392

页数：12

相关论文

共 26 条

[1] Deep Learning With Attribute Profiles for Hyperspectral Image Classification [J].

Aptoula, Erchan ;

Ozdemir, Murat Can ;

Yanikoglu, Berrin .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (12) :1970-1974

[2] Vector Attribute Profiles for Hyperspectral Image Classification [J].

Aptoula, Erchan ;

Dalla Mura, Mauro ;

Lefevre, Sebastien .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (06) :3208-3220

[3] Hyperspectral Image Classification With Multidimensional Attribute Profiles [J].

Aptoula, Erchan .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (10) :2031-2035

[4] The tree of shapes of an image [J].

Ballester, C ;

Caselles, V ;

Monasse, P .

ESAIM-CONTROL OPTIMISATION AND CALCULUS OF VARIATIONS, 2003, 9 (01) :1-18

[5] Classification and feature extraction for remote sensing images from urban areas based on morphological transformations [J].

Benediktsson, JA ;

Pesaresi, M ;

Arnason, K .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (09) :1940-1949

[6] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[7] MToS: A Tree of Shapes for Multivariate Images [J].

Carlinet, Edwin ;

Geraud, Thierry .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (12) :5330-5342

[8] Remote Sensing Image Classification Using Attribute Filters Defined Over the Tree of Shapes [J].

Cavallaro, Gabriele ;

Dalla Mura, Mauro ;

Benediktsson, Jon Atli ;

Plaza, Antonio .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (07) :3899-3911

[9] Classification of Hyperspectral Images by Using Extended Morphological Attribute Profiles and Independent Component Analysis [J].

Dalla Mura, Mauro ;

Villa, Alberto ;

Benediktsson, Jon Atli ;

Chanussot, Jocelyn ;

Bruzzone, Lorenzo .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (03) :542-546

[10] Extended profiles with morphological attribute filters for the analysis of hyperspectral data [J].

Dalla Mura, Mauro ;

Benediktsson, Jon Atli ;

Waske, Bjoern ;

Bruzzone, Lorenzo .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2010, 31 (22) :5975-5991