Morphology based sediment particle image binarization algorithm research

Ying Xiao, Bo Yuan, Dajun Zeng, Bing Wang, Fengying Xie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The diversity and complexity of sediment particle images, has become a constraint major bottleneck problem of establishing the river sediment image segmentation, using sediment particle images with similar particle images in other areas can take advantage of same-sex classes of image processing to propose a morphology-based Otsu binarization algorithm, the use of fast binary algorithm to get the initial search reference, on this basis to define a smaller range as the initial search of morphology-based Otsu binarization algorithm, then image segmentation. Experiments show that the new algorithm to maintain the speed and good noise suppression ability, at the same time this algorithm can better retain the original image characteristics, the algorithm execution speed has been greatly improved. Images have good results after binary.

Original languageEnglish (US)
Title of host publicationProceedings - 2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012
Pages375-378
Number of pages4
DOIs
StatePublished - 2012
Event2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012 - Hangzhou, Zhejiang, China
Duration: Mar 23 2012Mar 25 2012

Publication series

NameProceedings - 2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012
Volume3

Other

Other2012 International Conference on Computer Science and Electronics Engineering, ICCSEE 2012
CountryChina
CityHangzhou, Zhejiang
Period3/23/123/25/12

Keywords

  • binarization algorithm
  • morphological
  • sediment particle images

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Morphology based sediment particle image binarization algorithm research'. Together they form a unique fingerprint.

Cite this