Distributed Component Forests:  ImagesHierarchical Image Representations Suitable for Tera-Scale

M.H.F. Wilkinson; Simon Gazagnes

Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

96 Downloads (Pure)

Abstract

The standard representations know as component trees, used in morphological connected attribute filtering and multi-scale analysis, are unsuitable for cases in which either the image itself, or the tree do not fit in the memory of a single compute node. Recently, a new structure has been developed which consists of a collection of modified component trees, one for each image tile. It has to date only been applied to fairly simple image filtering based on area. In this paper we explore other applications of these distributed component forests, in particular to multi-scale analysis such as pattern spectra, and morphological attribute profiles and multi-scale leveling segmentations

Original language	English
Title of host publication	Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence
Editors	Ching Y. Suen
Place of Publication	Montreal, Canada
Publisher	CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada
Pages	96-101
ISBN (Electronic)	978-1-895193-04-6
Publication status	Published - 2018
Event	International Conference on Pattern Recognition and Artificial Intelligence ICPRAI 2018 - Montreal, Quebec, Canada Duration: 14-May-2018 → 17-May-2018

Conference

Conference	International Conference on Pattern Recognition and Artificial Intelligence ICPRAI 2018
Country/Territory	Canada
City	Montreal, Quebec
Period	14/05/2018 → 17/05/2018

Access to Document

ICPRAI 2018 ProceedingsFinal publisher's version, 164 MBLicence: Unspecified

Handle.net

Persistent link

Cite this

Wilkinson, M. H. F., & Gazagnes, S. (2018). Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale. In C. Y. Suen (Ed.), Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence (pp. 96-101). CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada .

Wilkinson, M.H.F. ; Gazagnes, Simon. / Distributed Component Forests : ImagesHierarchical Image Representations Suitable for Tera-Scale. Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence . editor / Ching Y. Suen. Montreal, Canada : CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada , 2018. pp. 96-101

@inproceedings{1cd0fea8401849a3bb8d045d2103f0f2,

title = "Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale",

abstract = "The standard representations know as component trees, used in morphological connected attribute filtering and multi-scale analysis, are unsuitable for cases in which either the image itself, or the tree do not fit in the memory of a single compute node. Recently, a new structure has been developed which consists of a collection of modified component trees, one for each image tile. It has to date only been applied to fairly simple image filtering based on area. In this paper we explore other applications of these distributed component forests, in particular to multi-scale analysis such as pattern spectra, and morphological attribute profiles and multi-scale leveling segmentations",

author = "M.H.F. Wilkinson and Simon Gazagnes",

year = "2018",

language = "English",

pages = "96--101",

editor = "Suen, {Ching Y.}",

booktitle = "Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence",

publisher = "CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada ",

note = "International Conference on Pattern Recognition and Artificial Intelligence ICPRAI 2018 ; Conference date: 14-05-2018 Through 17-05-2018",

}

Wilkinson, MHF & Gazagnes, S 2018, Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale. in CY Suen (ed.), Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence . CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada , Montreal, Canada, pp. 96-101, International Conference on Pattern Recognition and Artificial Intelligence ICPRAI 2018, Montreal, Quebec, Canada, 14/05/2018.

Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale. / Wilkinson, M.H.F.; Gazagnes, Simon.
Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence . ed. / Ching Y. Suen. Montreal, Canada: CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada , 2018. p. 96-101.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Distributed Component Forests

T2 - International Conference on Pattern Recognition and Artificial Intelligence ICPRAI 2018

AU - Wilkinson, M.H.F.

AU - Gazagnes, Simon

PY - 2018

Y1 - 2018

N2 - The standard representations know as component trees, used in morphological connected attribute filtering and multi-scale analysis, are unsuitable for cases in which either the image itself, or the tree do not fit in the memory of a single compute node. Recently, a new structure has been developed which consists of a collection of modified component trees, one for each image tile. It has to date only been applied to fairly simple image filtering based on area. In this paper we explore other applications of these distributed component forests, in particular to multi-scale analysis such as pattern spectra, and morphological attribute profiles and multi-scale leveling segmentations

AB - The standard representations know as component trees, used in morphological connected attribute filtering and multi-scale analysis, are unsuitable for cases in which either the image itself, or the tree do not fit in the memory of a single compute node. Recently, a new structure has been developed which consists of a collection of modified component trees, one for each image tile. It has to date only been applied to fairly simple image filtering based on area. In this paper we explore other applications of these distributed component forests, in particular to multi-scale analysis such as pattern spectra, and morphological attribute profiles and multi-scale leveling segmentations

M3 - Conference contribution

SP - 96

EP - 101

BT - Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence

A2 - Suen, Ching Y.

PB - CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada

CY - Montreal, Canada

Y2 - 14 May 2018 through 17 May 2018

ER -

Wilkinson MHF, Gazagnes S. Distributed Component Forests: ImagesHierarchical Image Representations Suitable for Tera-Scale. In Suen CY, editor, Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence . Montreal, Canada: CENPARMI, Centre for Pattern Recognition and Machine Intellig ence Concordia University, Montreal, Canada . 2018. p. 96-101