Deakin University
Browse

Higher order conditional random field for multi-label interactive image segmentation

Version 2 2024-06-04, 05:55
Version 1 2017-09-06, 22:57
conference contribution
posted on 2024-06-04, 05:55 authored by TV Nguyen, N Pham, T Tran, B Le
In this paper, we propose the efficient approach to tackle the multi-label interactive image segmentation issue by applying the higher order Conditional Random Fields model which associates superpixel as higher order energy. People did take advantage of CRF model for unsupervised segmentation for years, but it requires training set for providing neccessary information. Therefore, unsupervised strategy is fairly restrictive for the variety of image contexts and categorizations. For this reason, the user interaction seems inevitable to help us address the multilabel segmentation's riddle in accordance with exploiting CRF perspectives. The promising experiments are conducted in MSRC and Berkeley dataset comparing with the original Conditional Random Fields framework.

History

Pagination

282-285

Location

Ho Chi Minh City, Vietnam

Start date

2012-02-27

End date

2012-03-01

ISBN-13

9781467303088

Language

eng

Publication classification

E Conference publication, E1.1 Full written paper - refereed

Copyright notice

2012, IEEE

Title of proceedings

RIVF 2012 : Proceedings of the IEEE International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future

Event

Computing & Communication Technologies, Research, Innovation, and Vision for the Future. IEEE International Conference (2012 : Ho Chi Minh City, Vietnam)

Publisher

IEEE

Place of publication

Piscataway, N.J.