Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images

M.H.F. Wilkinson; P. Soille; M. Pesaresi; G.K. Ouzounis

doi:10.1007/978-3-642-21569-8_29

Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images

M.H.F. Wilkinson, P. Soille, M. Pesaresi, G.K. Ouzounis

Intelligent Systems

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

9 Citations (Scopus)

82 Downloads (Pure)

Abstract

In this paper we provide an efficient parallel algorithm for reconstruction from markers, and multi-scale analysis through differential morphological profiles, which are top-hat scale spaces based on openings and closings by reconstruction. The new algorithms provide speed gain in two ways: (i) through parallelism, and (ii) through more efficient re-use of previously computed data. The best version of the algorithm provided a 17× speed-up on 24 cores, over computation of the same algorithm on a single core. Compared to the basic method of repeated reconstructions by a sequential algorithm, a speed gain of 25.1 times was obtained.

Original language	English
Title of host publication	Mathematical Morphology and Its Applications to Image and Signal Processing
Subtitle of host publication	10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings
Editors	Pierre Soille, Martino Pesaresi, Georgios Ouzounis
Publisher	Springer
Pages	331-342
Number of pages	12
ISBN (Electronic)	9783642215698
ISBN (Print)	9783642215681
DOIs	https://doi.org/10.1007/978-3-642-21569-8_29
Publication status	Published - 2011

Publication series

Name	Lecture Notes in Computer Science book series
Publisher	Springer
Volume	6671

Access to Document

10.1007/978-3-642-21569-8_29

WilkinsonSoilleOuzounisISMM2011Final author's version, 2.42 MBLicence: Unspecified

Handle.net

Persistent link

Cite this

Wilkinson, M. H. F., Soille, P., Pesaresi, M., & Ouzounis, G. K. (2011). Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images. In P. Soille, M. Pesaresi, & G. Ouzounis (Eds.), Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings (pp. 331-342). (Lecture Notes in Computer Science book series ; Vol. 6671). Springer. https://doi.org/10.1007/978-3-642-21569-8_29

Wilkinson, M.H.F. ; Soille, P. ; Pesaresi, M. et al. / Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images. Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings. editor / Pierre Soille ; Martino Pesaresi ; Georgios Ouzounis. Springer, 2011. pp. 331-342 (Lecture Notes in Computer Science book series ).

@inproceedings{1c97e1ff94644d12b63653945b55c89f,

title = "Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images",

abstract = "In this paper we provide an efficient parallel algorithm for reconstruction from markers, and multi-scale analysis through differential morphological profiles, which are top-hat scale spaces based on openings and closings by reconstruction. The new algorithms provide speed gain in two ways: (i) through parallelism, and (ii) through more efficient re-use of previously computed data. The best version of the algorithm provided a 17× speed-up on 24 cores, over computation of the same algorithm on a single core. Compared to the basic method of repeated reconstructions by a sequential algorithm, a speed gain of 25.1 times was obtained.",

author = "M.H.F. Wilkinson and P. Soille and M. Pesaresi and G.K. Ouzounis",

note = "Relation: http://www.springerlink.com/ Rights: Springer",

year = "2011",

doi = "10.1007/978-3-642-21569-8_29",

language = "English",

isbn = "9783642215681",

series = "Lecture Notes in Computer Science book series ",

publisher = "Springer",

pages = "331--342",

editor = "Soille, {Pierre } and Pesaresi, {Martino } and Ouzounis, {Georgios }",

booktitle = "Mathematical Morphology and Its Applications to Image and Signal Processing",

}

Wilkinson, MHF, Soille, P, Pesaresi, M & Ouzounis, GK 2011, Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images. in P Soille, M Pesaresi & G Ouzounis (eds), Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings. Lecture Notes in Computer Science book series , vol. 6671, Springer, pp. 331-342. https://doi.org/10.1007/978-3-642-21569-8_29

Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images. / Wilkinson, M.H.F.; Soille, P.; Pesaresi, M. et al.
Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings. ed. / Pierre Soille; Martino Pesaresi; Georgios Ouzounis. Springer, 2011. p. 331-342 (Lecture Notes in Computer Science book series ; Vol. 6671).

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

TY - GEN

T1 - Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images

AU - Wilkinson, M.H.F.

AU - Soille, P.

AU - Pesaresi, M.

AU - Ouzounis, G.K.

N1 - Relation: http://www.springerlink.com/ Rights: Springer

PY - 2011

Y1 - 2011

N2 - In this paper we provide an efficient parallel algorithm for reconstruction from markers, and multi-scale analysis through differential morphological profiles, which are top-hat scale spaces based on openings and closings by reconstruction. The new algorithms provide speed gain in two ways: (i) through parallelism, and (ii) through more efficient re-use of previously computed data. The best version of the algorithm provided a 17× speed-up on 24 cores, over computation of the same algorithm on a single core. Compared to the basic method of repeated reconstructions by a sequential algorithm, a speed gain of 25.1 times was obtained.

AB - In this paper we provide an efficient parallel algorithm for reconstruction from markers, and multi-scale analysis through differential morphological profiles, which are top-hat scale spaces based on openings and closings by reconstruction. The new algorithms provide speed gain in two ways: (i) through parallelism, and (ii) through more efficient re-use of previously computed data. The best version of the algorithm provided a 17× speed-up on 24 cores, over computation of the same algorithm on a single core. Compared to the basic method of repeated reconstructions by a sequential algorithm, a speed gain of 25.1 times was obtained.

UR - https://www.springer.com/gp/book/9783642215681

U2 - 10.1007/978-3-642-21569-8_29

DO - 10.1007/978-3-642-21569-8_29

M3 - Conference contribution

SN - 9783642215681

T3 - Lecture Notes in Computer Science book series

SP - 331

EP - 342

BT - Mathematical Morphology and Its Applications to Image and Signal Processing

A2 - Soille, Pierre

A2 - Pesaresi, Martino

A2 - Ouzounis, Georgios

PB - Springer

ER -

Wilkinson MHF, Soille P, Pesaresi M, Ouzounis GK. Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images. In Soille P, Pesaresi M, Ouzounis G, editors, Mathematical Morphology and Its Applications to Image and Signal Processing: 10th International Symposium, ISMM 2011, Verbania-Intra, Italy, July 6-8, 2011, Proceedings. Springer. 2011. p. 331-342. (Lecture Notes in Computer Science book series ). doi: 10.1007/978-3-642-21569-8_29

Concurrent Computation of Differential Morphological Profiles on Giga-Pixel Images

Abstract

Publication series

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this