Combining watersheds and conditional random fields for image classification

Yanchai Yang, Guitao Cao

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

4 Scopus citations

Abstract

Simultaneous image segmentation and labeling are fundamental problems in computer vision. In this paper we propose a sequential method based on conditional random fields (CRF) combined with the marker-controlled watershed transform method after classification and image enhancement of artificial structures in natural images. Firstly, we use the CRF model to determine the location of interested regions. Then on the basis of the result from the CRF, we are only concentrating on labeled region by using a dual morphological reconstruction method. Lastly, the marker-controlled watershed transform method was applied to the enhanced images. Experiments show that our method has improved the accuracy of edge detection.

Original languageEnglish
Title of host publicationProceedings - 2013 10th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2013
PublisherIEEE Computer Society
Pages805-810
Number of pages6
ISBN (Print)9781467352536
DOIs
StatePublished - 2013
Event2013 10th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2013 - Shenyang, China
Duration: 23 Jul 201325 Jul 2013

Publication series

NameProceedings - 2013 10th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2013

Conference

Conference2013 10th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2013
Country/TerritoryChina
CityShenyang
Period23/07/1325/07/13

Keywords

  • conditional random fields (CRF)
  • image enhancement
  • image labeling
  • image segmentation
  • watershed transform

Fingerprint

Dive into the research topics of 'Combining watersheds and conditional random fields for image classification'. Together they form a unique fingerprint.

Cite this