Applying incremental learning to parallel image segmentation

Cyril Charron, Yulia Hicks, Peter Hall

Research output: Chapter in Book/Report/Conference proceedingChapter

  • 2 Citations

Abstract

Segmenting large or multiple images is time and memory consuming. These issues have been addressed in the past by implementing parallel versions of popular algorithms such as Graph Cuts and Mean Shift. Here, we propose to use an incremental Gaussian Mixture Model (GMM) learning algorithm for parallel image segmentation. We show that our approach allows us to reduce the memory requirements dramatically whilst obtaining high quality of segmentation. We also compare memory, time and quality of the performance of our approach and several other state of the art segmentation algorithms in a rigorous set of experiments, which produce favorable results.
LanguageEnglish
Title of host publication2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009
PublisherIEEE
Pages2064-2071
Number of pages8
ISBN (Print)9781424444427
DOIs
StatusPublished - 2009
Event2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, September 27, 2009 - October 4, 2009 - Kyoto, Japan
Duration: 1 Jan 2009 → …

Conference

Conference2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, September 27, 2009 - October 4, 2009
CountryJapan
CityKyoto
Period1/01/09 → …

Fingerprint

Image segmentation
Data storage equipment
Learning algorithms
Experiments

Cite this

Charron, C., Hicks, Y., & Hall, P. (2009). Applying incremental learning to parallel image segmentation. In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009 (pp. 2064-2071). [5457535] IEEE. DOI: 10.1109/ICCVW.2009.5457535

Applying incremental learning to parallel image segmentation. / Charron, Cyril; Hicks, Yulia; Hall, Peter.

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. IEEE, 2009. p. 2064-2071 5457535.

Research output: Chapter in Book/Report/Conference proceedingChapter

Charron, C, Hicks, Y & Hall, P 2009, Applying incremental learning to parallel image segmentation. in 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009., 5457535, IEEE, pp. 2064-2071, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, September 27, 2009 - October 4, 2009, Kyoto, Japan, 1/01/09. DOI: 10.1109/ICCVW.2009.5457535
Charron C, Hicks Y, Hall P. Applying incremental learning to parallel image segmentation. In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. IEEE. 2009. p. 2064-2071. 5457535. Available from, DOI: 10.1109/ICCVW.2009.5457535
Charron, Cyril ; Hicks, Yulia ; Hall, Peter. / Applying incremental learning to parallel image segmentation. 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. IEEE, 2009. pp. 2064-2071
@inbook{99cc04458efc442dafc311da9e170454,
title = "Applying incremental learning to parallel image segmentation",
abstract = "Segmenting large or multiple images is time and memory consuming. These issues have been addressed in the past by implementing parallel versions of popular algorithms such as Graph Cuts and Mean Shift. Here, we propose to use an incremental Gaussian Mixture Model (GMM) learning algorithm for parallel image segmentation. We show that our approach allows us to reduce the memory requirements dramatically whilst obtaining high quality of segmentation. We also compare memory, time and quality of the performance of our approach and several other state of the art segmentation algorithms in a rigorous set of experiments, which produce favorable results.",
author = "Cyril Charron and Yulia Hicks and Peter Hall",
year = "2009",
doi = "10.1109/ICCVW.2009.5457535",
language = "English",
isbn = "9781424444427",
pages = "2064--2071",
booktitle = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009",
publisher = "IEEE",
address = "USA United States",

}

TY - CHAP

T1 - Applying incremental learning to parallel image segmentation

AU - Charron,Cyril

AU - Hicks,Yulia

AU - Hall,Peter

PY - 2009

Y1 - 2009

N2 - Segmenting large or multiple images is time and memory consuming. These issues have been addressed in the past by implementing parallel versions of popular algorithms such as Graph Cuts and Mean Shift. Here, we propose to use an incremental Gaussian Mixture Model (GMM) learning algorithm for parallel image segmentation. We show that our approach allows us to reduce the memory requirements dramatically whilst obtaining high quality of segmentation. We also compare memory, time and quality of the performance of our approach and several other state of the art segmentation algorithms in a rigorous set of experiments, which produce favorable results.

AB - Segmenting large or multiple images is time and memory consuming. These issues have been addressed in the past by implementing parallel versions of popular algorithms such as Graph Cuts and Mean Shift. Here, we propose to use an incremental Gaussian Mixture Model (GMM) learning algorithm for parallel image segmentation. We show that our approach allows us to reduce the memory requirements dramatically whilst obtaining high quality of segmentation. We also compare memory, time and quality of the performance of our approach and several other state of the art segmentation algorithms in a rigorous set of experiments, which produce favorable results.

UR - http://dx.doi.org/10.1109/ICCVW.2009.5457535

U2 - 10.1109/ICCVW.2009.5457535

DO - 10.1109/ICCVW.2009.5457535

M3 - Chapter

SN - 9781424444427

SP - 2064

EP - 2071

BT - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

PB - IEEE

ER -