Automatic segmentation of interest regions in low depth of field images using ensemble clustering and graph cut optimization approaches

G. Rafiee*, S. S. Dlay, W. L. Woo

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

Automatic segmentation of images with low depth of field (DOF) plays an important role in content-based multimedia applications. The proposed approach aims to separate the important objects (i.e., interest regions) of a given image from its defocused background in two stages. In stage one, image blocks are classified into object and background blocks using a novel cluster ensemble algorithm. By indicating the certain pixels (seeds) of the object and background blocks, a hard constraint is provided for the next stage of the approach. In stage two, a minimal graph cut is constructed using object and background seeds, which is based on the max-flow method. Experimental results for a wide range of busy-texture (i.e., noisy) and smooth regions demonstrate that the proposed approach provides better segmentation performance at higher speed compared with the state-of-the-art approaches.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE International Symposium on Multimedia, ISM 2012
PublisherIEEE
Pages161-164
Number of pages4
ISBN (Print)978-1-4673-4370-1
DOIs
Publication statusPublished - 1 Feb 2013
Event14th IEEE International Symposium on Multimedia, ISM 2012 - Irvine, CA, United States
Duration: 10 Dec 201212 Dec 2012

Conference

Conference14th IEEE International Symposium on Multimedia, ISM 2012
CountryUnited States
CityIrvine, CA
Period10/12/1212/12/12

Fingerprint

Dive into the research topics of 'Automatic segmentation of interest regions in low depth of field images using ensemble clustering and graph cut optimization approaches'. Together they form a unique fingerprint.

Cite this