10 February 2009 Hyper-spectral image segmentation using spectral clustering with covariance descriptors
Author Affiliations +
Abstract
Image segmentation is an important and difficult computer vision problem. Hyper-spectral images pose even more difficulty due to their high-dimensionality. Spectral clustering (SC) is a recently popular clustering/segmentation algorithm. In general, SC lifts the data to a high dimensional space, also known as the kernel trick, then derive eigenvectors in this new space, and finally using these new dimensions partition the data into clusters. We demonstrate that SC works efficiently when combined with covariance descriptors that can be used to assess pixelwise similarities rather than in the high-dimensional Euclidean space. We present the formulations and some preliminary results of the proposed hybrid image segmentation method for hyper-spectral images.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Olcay Kursun, Olcay Kursun, Fethullah Karabiber, Fethullah Karabiber, Cemalettin Koc, Cemalettin Koc, Abdullah Bal, Abdullah Bal, } "Hyper-spectral image segmentation using spectral clustering with covariance descriptors", Proc. SPIE 7245, Image Processing: Algorithms and Systems VII, 724512 (10 February 2009); doi: 10.1117/12.811132; https://doi.org/10.1117/12.811132
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

A semi automatic 2D to stereoscopic 3D image and video...
Proceedings of SPIE (March 11 2013)
Computer vision based room interior design
Proceedings of SPIE (December 07 2015)
Segmenting text images with massively parallel machines
Proceedings of SPIE (January 31 1992)
Fast Automated Object Detection Using Signature Parsing
Proceedings of SPIE (February 28 1990)

Back to Top