Translator Disclaimer
Paper
18 June 2003 K-means reclustering: algorithmic options with quantifiable performance comparisons
Author Affiliations +
Proceedings Volume 5001, Optical Engineering at the Lawrence Livermore National Laboratory; (2003) https://doi.org/10.1117/12.500371
Event: High-Power Lasers and Applications, 2003, San Jose, CA, United States
Abstract
This paper presents various architectural options for implementing a K-Means Re-Clustering algorithm suitable for unsupervised segmentation of hyperspectral images. Performance metrics are developed based upon quantitative comparisons of convergence rates and segmentation quality. A methodology for making these comparisons is developed and used to establish K values that produce the best segmentations with minimal processing requirements. Convergence rates depend on the initial choice of cluster centers. Consequently, this same methodology may be used to evaluate the effectiveness of different initialization techniques.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alan W. Meyer, David W. Paglieroni, and Cyrus Astaneh "K-means reclustering: algorithmic options with quantifiable performance comparisons", Proc. SPIE 5001, Optical Engineering at the Lawrence Livermore National Laboratory, (18 June 2003); https://doi.org/10.1117/12.500371
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT


Back to Top