30 October 2009 Semi-supervised segmentation of multispectral remote sensing image based on spectral clustering
Author Affiliations +
Proceedings Volume 7494, MIPPR 2009: Multispectral Image Acquisition and Processing; 74941F (2009) https://doi.org/10.1117/12.832880
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
In this paper, a new multi-spectral remote sensing image segmentation method based on multi-parameter semi-supervised spectral clustering (STS3C) is proposed. Two types of instance-level constraints: must-link and cannot-link are incorporated into spectral cluster to construct semi-supervised spectral clustering in which the self-tuning parameter is applied to avoid the selection of the scaling parameter. Further, when STS3C is applied to multi-spectral remote sensing image segmentation, the uniform sampling technique combined with nearest neighbor rule is used to reduce the computation complexity. Segmentation results show that STS3C outperforms the semi-supervised spectral clustering with fixed parameter and the well-known clustering methods including k-means and FCM in multi-spectral remote sensing image segmentation.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiangrong Zhang, Xiangrong Zhang, Ting Wang, Ting Wang, Licheng Jiao, Licheng Jiao, } "Semi-supervised segmentation of multispectral remote sensing image based on spectral clustering", Proc. SPIE 7494, MIPPR 2009: Multispectral Image Acquisition and Processing, 74941F (30 October 2009); doi: 10.1117/12.832880; https://doi.org/10.1117/12.832880
PROCEEDINGS
6 PAGES


SHARE
Back to Top