Enhanced Hemisphere Concept for Color Pixel Classification

Van Ng, Terumasa Aoki

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

1 Citation (Scopus)

Abstract

Most of current clustering methods are designed for general purpose other than a specific color pixel classification use. Color Line model representation emerged as the ultimate method for clustering pixels using RGB color components. However, this method is strongly sensitive to the adjustment of input parameters, which cannot conform to the frequent change of image structures and compositions. In this paper, we address this problem by introducing a hemisphere-grid based method for RGB pixel classification. Our method minimizes the reliance on user provided parameters as well as it can dynamically estimate the proper number of clusters. The properly clustering results prove the robustness and advantages of our method in classifying color pixels for unfamiliar input images.

Original languageEnglish
Title of host publicationProceedings - 2016 International Conference on Multimedia Systems and Signal Processing, ICMSSP 2016
EditorsChin-Chen Chang, Jeng-Shyang Pan, Young-Chang Hou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages31-35
Number of pages5
ISBN (Electronic)9781509045198
DOIs
Publication statusPublished - 2016 Jul 2
Event2016 International Conference on Multimedia Systems and Signal Processing, ICMSSP 2016 - New Taipei, Taiwan, Province of China
Duration: 2016 Sep 32016 Sep 5

Publication series

NameProceedings - 2016 International Conference on Multimedia Systems and Signal Processing, ICMSSP 2016

Other

Other2016 International Conference on Multimedia Systems and Signal Processing, ICMSSP 2016
CountryTaiwan, Province of China
CityNew Taipei
Period16/9/316/9/5

Keywords

  • RGB clustering
  • adaptive clustering
  • hemisphere-grid

ASJC Scopus subject areas

  • Media Technology
  • Signal Processing

Fingerprint Dive into the research topics of 'Enhanced Hemisphere Concept for Color Pixel Classification'. Together they form a unique fingerprint.

Cite this