Automated grain sizing using mark-based watershed algorithm

Han Sheng Chuang, Chao Hung Lin

研究成果: Paper

摘要

This paper presents a method based on mark-based watershed algorithm to automatically extract grains and determine grain sizes from images. Markers generated by the proposed approaches represent rough locations of grains and aperture. Instead of selecting pixels with local minima as marks, we select markers with a priori knowledge, enabling our approach to efficiently ease the problem of over-segmentation in traditional watershed algorithm. The grains patches are extracted correctly after merging the other fragmental patches using both the color and shape properties. Finally, the distribution of grain size is calculated by fitting an ellipse for each detected grain.

原文English
頁面2332-2335
頁數4
DOIs
出版狀態Published - 2012 十二月 1
事件2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany
持續時間: 2012 七月 222012 七月 27

Other

Other2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
國家Germany
城市Munich
期間12-07-2212-07-27

指紋

Watersheds
grain size
watershed
ellipse
segmentation
pixel
Merging
Pixels
Color
sizing
marker
distribution
method

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

引用此文

Chuang, H. S., & Lin, C. H. (2012). Automated grain sizing using mark-based watershed algorithm. 2332-2335. 論文發表於 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany. https://doi.org/10.1109/IGARSS.2012.6351027
Chuang, Han Sheng ; Lin, Chao Hung. / Automated grain sizing using mark-based watershed algorithm. 論文發表於 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany.4 p.
@conference{6a55b66e071642b9b99f5ab7821927a1,
title = "Automated grain sizing using mark-based watershed algorithm",
abstract = "This paper presents a method based on mark-based watershed algorithm to automatically extract grains and determine grain sizes from images. Markers generated by the proposed approaches represent rough locations of grains and aperture. Instead of selecting pixels with local minima as marks, we select markers with a priori knowledge, enabling our approach to efficiently ease the problem of over-segmentation in traditional watershed algorithm. The grains patches are extracted correctly after merging the other fragmental patches using both the color and shape properties. Finally, the distribution of grain size is calculated by fitting an ellipse for each detected grain.",
author = "Chuang, {Han Sheng} and Lin, {Chao Hung}",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/IGARSS.2012.6351027",
language = "English",
pages = "2332--2335",
note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

Chuang, HS & Lin, CH 2012, 'Automated grain sizing using mark-based watershed algorithm', 論文發表於 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany, 12-07-22 - 12-07-27 頁 2332-2335. https://doi.org/10.1109/IGARSS.2012.6351027

Automated grain sizing using mark-based watershed algorithm. / Chuang, Han Sheng; Lin, Chao Hung.

2012. 2332-2335 論文發表於 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany.

研究成果: Paper

TY - CONF

T1 - Automated grain sizing using mark-based watershed algorithm

AU - Chuang, Han Sheng

AU - Lin, Chao Hung

PY - 2012/12/1

Y1 - 2012/12/1

N2 - This paper presents a method based on mark-based watershed algorithm to automatically extract grains and determine grain sizes from images. Markers generated by the proposed approaches represent rough locations of grains and aperture. Instead of selecting pixels with local minima as marks, we select markers with a priori knowledge, enabling our approach to efficiently ease the problem of over-segmentation in traditional watershed algorithm. The grains patches are extracted correctly after merging the other fragmental patches using both the color and shape properties. Finally, the distribution of grain size is calculated by fitting an ellipse for each detected grain.

AB - This paper presents a method based on mark-based watershed algorithm to automatically extract grains and determine grain sizes from images. Markers generated by the proposed approaches represent rough locations of grains and aperture. Instead of selecting pixels with local minima as marks, we select markers with a priori knowledge, enabling our approach to efficiently ease the problem of over-segmentation in traditional watershed algorithm. The grains patches are extracted correctly after merging the other fragmental patches using both the color and shape properties. Finally, the distribution of grain size is calculated by fitting an ellipse for each detected grain.

UR - http://www.scopus.com/inward/record.url?scp=84873202422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873202422&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2012.6351027

DO - 10.1109/IGARSS.2012.6351027

M3 - Paper

AN - SCOPUS:84873202422

SP - 2332

EP - 2335

ER -

Chuang HS, Lin CH. Automated grain sizing using mark-based watershed algorithm. 2012. 論文發表於 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany. https://doi.org/10.1109/IGARSS.2012.6351027