The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XL-1/W5
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W5, 411–416, 2015
https://doi.org/10.5194/isprsarchives-XL-1-W5-411-2015
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W5, 411–416, 2015
https://doi.org/10.5194/isprsarchives-XL-1-W5-411-2015

  11 Dec 2015

11 Dec 2015

UNLABELED SELECTED SAMPLES IN FEATURE EXTRACTION FOR CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH LIMITED TRAINING SAMPLES

A. Kianisarkaleh1, H. Ghassemian2, and F. Razzazi1 A. Kianisarkaleh et al.
  • 1Department of Electrical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
  • 2Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran

Keywords: Hyperspectral images, feature extraction, limited training samples, unlabeled samples selection, supervised classification

Abstract. Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.