Graph-without-cut: an ideal graph learning for image segmentation

Gao, Lianli, Song, Jingkuan, Nie, Feiping, Zou, Fuhao, Sebe, Nicu and Shen, Heng Tao (2016). Graph-without-cut: an ideal graph learning for image segmentation. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16). AAAI Conference on Artificial Intelligence, Phoenix, AZ, United States, (1188-1194). 12-17 February 2016.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
Author Gao, Lianli
Song, Jingkuan
Nie, Feiping
Zou, Fuhao
Sebe, Nicu
Shen, Heng Tao
Title of paper Graph-without-cut: an ideal graph learning for image segmentation
Conference name AAAI Conference on Artificial Intelligence
Conference location Phoenix, AZ, United States
Conference dates 12-17 February 2016
Convener AAAI
Proceedings title Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)
Place of Publication Palo Alto, CA, United States
Publisher AAAI Press
Publication Year 2016
Sub-type Fully published paper
Open Access Status Not Open Access
Start page 1188
End page 1194
Total pages 7
Collection year 2017
Language eng
Abstract/Summary Graph-based image segmentation organizes the image elements into graphs and partitions an image based on the graph. It has been widely used and many promising results are obtained. Since the segmentation performance highly depends on the graph, most of existing methods focus on obtaining a precise similarity graph or on designing efficient cutting/merging strategies. However, these two components are often conducted in two separated steps, and thus the obtained graph similarity may not be the optimal one for segmentation and this may lead to suboptimal results. In this paper, we propose a novel framework, Graph-WithoutCut (GWC), for learning the similarity graph and image segmentations simultaneously. GWC learns the similarity graph by assigning adaptive and optimal neighbors to each vertex based on the spatial and visual information. Meanwhile, the new rank constraint is imposed to the Laplacian matrix of the similarity graph, such that the connected components in the resulted similarity graph are exactly equal to the region number. Extensive empirical results on three public data sets (i.e, BSDS300, BSDS500 and MSRC) show that our unsupervised GWC achieves state-of-the art performance compared with supervised and unsupervised image segmentation approaches.
Keyword Image segmentation
Graph learning
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Mon, 25 Jan 2016, 11:29:13 EST by Dr Heng Tao Shen on behalf of School of Information Technol and Elec Engineering