Abstract
Pixel Purity Index (PPI) is one of effective endmember extraction algorithms, which is a processing technique designed to determine which pixels are the most spectrally unique or pure. This paper proposes an automatic endmember extraction using pixel purity index for hyperspectral imagery. In computing the PPI, projection vectors are generated by applying the Givens rotation firstly. Then, pixels are projected onto the projection vectors. Next, the pixels located at the extreme positions are recorded. At last, the PPI score can be obtained. In endmember extraction, the number of endmembers is determined by using the Noise Subspace Projection (NSP) method. Hyperspectral image dimension is reduced by improving the Noise Covariance Matrix (NCM) estimation for Minimum Noise Fraction (MNF) transformation. The endmembers can be extracted with the improved pixel purity index. Compared with traditional APPI algorithm, the experimental results show that the proposed algorithm can obtain more endmembers as well as improve the accuracy of endmembers.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ngadi, M.O., Liu, L.: Hyperspectral Image Processing Technology: Hyperspectral Imaging for Food Quality Analysis and Control. Elsevier (2010)
Xu, M., Du, B., Zhang, L.: Spatial-spectral information based abundance-constrained endmember extraction methods. IEEE Trans. Geosci. Remote Sens. 7, 2004–2015 (2014)
Kowkabi, F., Ghassemian, H., Keshavarz, A.: Using spatial and spectral information for improving endmember extraction algorithms in hyperspectral remotely sensed images. In: ICCKE Conference, Mashhad, pp. 548–553 (2014)
Nascimento, J.M.P., Bioucas-Dias, J.M.: Vertex component analysis: a fast algorithm tounmix hyperspectral data. IEEE Trans. Geosci. Remote Sens. 43, 898–910 (2005)
Wang, L., Shen, C., Hartley, R.: On the optimality of sequential forward feature selection using class separability measure. In: DICTA Conference, Adelaide, pp. 203–208 (2011)
Chang, C., Xiong, W., Wen, C.: A theory of high-order statistics-based virtual dimensionality for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 52, 188–208 (2014)
Sun, Q., An, J., Song, M., Lin, B., Zhang, Y.: The improved N-FINDR endmember extraction algorithm and its application in the oil analysis. In: ICACI Conference, Hangzhou, pp. 601–604 (2012)
Heylen, R., Scheunders, P.: Multidimensional pixel purity index for convex hull estimation and endmember extraction. IEEE Trans. Geosci. Remote Sens. 51, 4059–4069 (2013)
Chang, C., Wu, C.: Iterative pixel purity index. In: WHISPERS Conference, Lausanne, pp. 1–4 (2012)
Hasanlou, M., Samadzadegan, F.: Comparative study of intrinsic dimensionality estimation and dimension reduction techniques on hyperspectral images using K-NN classifier. IEEE Trans. Geosci. Remote Sens. 9, 1046–1050 (2012)
Acito, N., Corsini, G., Diani, M.: A novel technique for hyperspectral signal subspace estimation in target detection applications. In: IGARSS Conference, Boston, pp. 95–98 (2008)
Zhang, D., Yu, L.: Support vector machine based classification for hyperspectral remote sensing images after minimum noise fraction rotation transformation. In: ICICIS Conference, pp. 132–135 (2010)
Li, Z., Chang, C.: Adaptive noise variance identification for data fusion using subspace-based technique. In: ICACC Conference, Beijing, pp. 764–770 (2010)
Zhang, J., Cao, Y., Zhuo, L., Wang, C., Zhou, Q.: Improved band similarity-based hyperspectral imagery band selection for target detection. J. Appl. Remote Sens. 9, 095091.1–095091.12 (2015)
Gao, L., Zhang, B., Zhang, X., Zhang, W., Tong, Q.: A new operational method for estimating noise in hyperspectral images. IEEE Trans. Geosci. Remote Sens. 5, 83–87 (2008)
Cheng, B.: Hyperspectral data unmixing algorithm comparative analysis based on linear spectral mixture model. In: IHMSC Conference, Hangzhou, pp. 11–14 (2013)
Acknowledgment
The work in this paper is supported by the National Natural Science Foundation of China (No. 61370189, No. 61372149, No. 61429201, and No. 61471013), the Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions (No. CIT&TCD 201304036, No. CIT&TCD20150311, No. CIT&TCD 201404043), the Science and Technology Development Program of Beijing Education Committee (No. KM201410005002), the part to Dr. Qi Tian by ARO grant W911NF-12-10057 and Faculty Research Awards by NEC Laboratories of America, the Specialized Research Fund for the Doctoral Program of Higher Education (No. 20121103110017), the Natural Science Foundation of Beijing (No. 4142009), Funding Project for Academic Human Resources Development in Institutions of Higher Learning Under the Jurisdiction of Beijing Municipality.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhou, Q., Zhang, J., Tian, Q., Zhuo, L., Geng, W. (2016). Automatic Endmember Extraction Using Pixel Purity Index for Hyperspectral Imagery. In: Tian, Q., Sebe, N., Qi, GJ., Huet, B., Hong, R., Liu, X. (eds) MultiMedia Modeling. MMM 2016. Lecture Notes in Computer Science(), vol 9517. Springer, Cham. https://doi.org/10.1007/978-3-319-27674-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-27674-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27673-1
Online ISBN: 978-3-319-27674-8
eBook Packages: Computer ScienceComputer Science (R0)