Region extraction with multiple active contour models

Toru Abe, Yuki Matsuzawa

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

1 Citation (Scopus)

Abstract

For interactive image manipulation, a new region extraction method using active contour models (ACM) is proposed. In this method, to improve extraction accuracy, multiple ACMs controlled by the statistical characteristics of image data are applied to the region of a single object. These ACMs compete with each other and each ACM extracts a subregion of uniform image properties. As a result of this competition, the entire region of the object is extracted as a set of several subregions. In addition, to lighten the load of the initial ACM settings, a procedure for making multiple initial ACMs from a few initial curves is also proposed. In this procedure, a few initial curves are set in an image, each initial curve is divided into several segments at the optimal loci, and multiple initial ACMs are made by dilating these segments.

Original languageEnglish
Title of host publicationProceedings - 2nd International Workshop on Digital and Computational Video, DCV 2001
PublisherIEEE Computer Society
Pages56-63
Number of pages8
ISBN (Print)9780769511108
DOIs
Publication statusPublished - 2001
Externally publishedYes
Event2nd International Workshop on Digital and Computational Video, DCV 2001 - Tampa, FL, United States
Duration: 2001 Feb 82001 Feb 9

Publication series

NameProceedings - 2nd International Workshop on Digital and Computational Video, DCV 2001

Other

Other2nd International Workshop on Digital and Computational Video, DCV 2001
CountryUnited States
CityTampa, FL
Period01/2/801/2/9

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this