Improved hierarchical optimization-based classification of hyperspectral images using shape analysis - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Improved hierarchical optimization-based classification of hyperspectral images using shape analysis

(1) , (2)
1
2

Abstract

A new spectral-spatial method for classification of hyperspectral images is proposed. The HSegClas method is based on the integration of probabilistic classification and shape analysis within the hierarchical step-wise optimization algorithm. First, probabilistic support vector machines classification is applied. Then, at each iteration two neighboring regions with the smallest Dissimilarity Criterion (DC) are merged, and classification probabilities are recomputed. The important contribution of this work consists in estimating a DC between regions as a function of statistical, classification and geometrical (area and rectangularity) features. Experimental results are presented on a 102-band ROSIS image of the Center of Pavia, Italy. The developed approach yields more accurate classification results when compared to previously proposed methods.
Fichier principal
Vignette du fichier
2012_IGARSS_tarabalka_HS.pdf (1.14 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00729038 , version 1 (07-09-2012)

Identifiers

  • HAL Id : hal-00729038 , version 1

Cite

Yuliya Tarabalka, James Tilton. Improved hierarchical optimization-based classification of hyperspectral images using shape analysis. IEEE IGARSS - International Geoscience and Remote Sensing Symposium, IEEE, Jul 2012, Munich, Germany. ⟨hal-00729038⟩

Collections

INRIA INRIA2
135 View
146 Download

Share

Gmail Facebook Twitter LinkedIn More