5 November 2014 Improved sequential search algorithms for classification in hyperspectral remote sensing images
Author Affiliations +
Proceedings Volume 9273, Optoelectronic Imaging and Multimedia Technology III; 927328 (2014); doi: 10.1117/12.2075281
Event: SPIE/COS Photonics Asia, 2014, Beijing, China
Abstract
Two new sequential search algorithms for feature selection in hyperspectral remote sensing images are proposed. Since many wavebands in hyperspectral images are redundant and irrelevant, the use of feature selection to improve classification results is highly needed. First, we present a new generalized steepest ascent (GSA) feature selection technique that improves upon the prior steepest ascent algorithm by selecting a better starting search point and performing a more thorough search. It is guaranteed to provide solutions that equal or exceed those of the classical sequential forward floating selection algorithm. However, when the number of available wavebands is large, the computational load required for the GSA algorithm becomes excessive. We thus propose a modification of the improved floating forward selection algorithm which is more computationally efficient. Experimental results for two hyperspectral data sets show that our proposed algorithms yield better classification results than other suboptimal search algorithms.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Songyot Nakariyakul, "Improved sequential search algorithms for classification in hyperspectral remote sensing images", Proc. SPIE 9273, Optoelectronic Imaging and Multimedia Technology III, 927328 (5 November 2014); doi: 10.1117/12.2075281; http://dx.doi.org/10.1117/12.2075281
PROCEEDINGS
9 PAGES


SHARE
KEYWORDS
Feature selection

Hyperspectral imaging

Remote sensing

Image classification

Polarization

Algorithm development

Vegetation

Back to Top