An adaptive unsupervised hyperspectral classification method based on Gaussian distribution

Jiang Yue; Jing-wei Wu; Yi Zhang; Lian-fa Bai

doi:10.1117/12.2073195

Translator Disclaimer

24 November 2014 An adaptive unsupervised hyperspectral classification method based on Gaussian distribution

Jiang Yue, Jing-wei Wu, Yi Zhang, Lian-fa Bai

Author Affiliations +

Proceedings Volume 9301, International Symposium on Optoelectronic Technology and Application 2014: Image Processing and Pattern Recognition; 93013F (2014) https://doi.org/10.1117/12.2073195
Event: International Symposium on Optoelectronic Technology and Application 2014, 2014, Beijing, China

Abstract

In order to achieve adaptive unsupervised clustering in the high precision, a method using Gaussian distribution to fit the similarity of the inter-class and the noise distribution is proposed in this paper, and then the automatic segmentation threshold is determined by the fitting result. First, according with the similarity measure of the spectral curve, this method assumes that the target and the background both in Gaussian distribution, the distribution characteristics is obtained through fitting the similarity measure of minimum related windows and center pixels with Gaussian function, and then the adaptive threshold is achieved. Second, make use of the pixel minimum related windows to merge adjacent similar pixels into a picture-block, then the dimensionality reduction is completed and the non-supervised classification is realized. AVIRIS data and a set of hyperspectral data we caught are used to evaluate the performance of the proposed method. Experimental results show that the proposed algorithm not only realizes the adaptive but also outperforms K-MEANS and ISODATA on the classification accuracy, edge recognition and robustness.

Citation Download Citation

Jiang Yue, Jing-wei Wu, Yi Zhang, and Lian-fa Bai "An adaptive unsupervised hyperspectral classification method based on Gaussian distribution", Proc. SPIE 9301, International Symposium on Optoelectronic Technology and Application 2014: Image Processing and Pattern Recognition, 93013F (24 November 2014); https://doi.org/10.1117/12.2073195

ACCESS THE FULL ARTICLE