Lunga, DPrasad, SCrawford, MErsoy, O2014-02-132014-02-132013-08Lunga, D, Prasad, S, Crawford, M and Ersoy, O. 2013. Manifold learning based feature extraction for classification of hyper-spectral data. IEEE Signal Processing Magazine, vol. Vol 31(1), pp 55-661053-5888http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6678226http://hdl.handle.net/10204/7197Copyright: 2013 IEEE. This is the post print version of the work. The definitive version is published in IEEE Signal Processing Magazine, vol. Vol 31(1), pp 55-66Advances in hyperspectral sensing provide new capability for characterizing spectral signatures in a wide range of physical and biological systems, while inspiring new methods for extracting information from these data. Hyperspectral image data often lie on sparse, nonlinear manifolds whose geometric and topological structures can be exploited via manifold learning techniques. In this article, we focused on demonstrating the opportunities provided by manifold learning for classification of remotely sensed data. Challenges and opportunities remain for future research in manifold learning, including joint exploitation of advantages of global and local structures in dynamic, multi-temporal environments, multiscale manifolds, and integration with semi-supervised and active learning.enHyperspectral sensingHyperspectral imageHSIArticleLunga, D., Prasad, S., Crawford, M., & Ersoy, O. (2013). Manifold learning based feature extraction for classification of hyper-spectral data. http://hdl.handle.net/10204/7197Lunga, D, S Prasad, M Crawford, and O Ersoy "Manifold learning based feature extraction for classification of hyper-spectral data." (2013) http://hdl.handle.net/10204/7197Lunga D, Prasad S, Crawford M, Ersoy O. Manifold learning based feature extraction for classification of hyper-spectral data. 2013; http://hdl.handle.net/10204/7197.TY - Article AU - Lunga, D AU - Prasad, S AU - Crawford, M AU - Ersoy, O AB - Advances in hyperspectral sensing provide new capability for characterizing spectral signatures in a wide range of physical and biological systems, while inspiring new methods for extracting information from these data. Hyperspectral image data often lie on sparse, nonlinear manifolds whose geometric and topological structures can be exploited via manifold learning techniques. In this article, we focused on demonstrating the opportunities provided by manifold learning for classification of remotely sensed data. Challenges and opportunities remain for future research in manifold learning, including joint exploitation of advantages of global and local structures in dynamic, multi-temporal environments, multiscale manifolds, and integration with semi-supervised and active learning. DA - 2013-08 DB - ResearchSpace DP - CSIR KW - Hyperspectral sensing KW - Hyperspectral image KW - HSI LK - https://researchspace.csir.co.za PY - 2013 SM - 1053-5888 T1 - Manifold learning based feature extraction for classification of hyper-spectral data TI - Manifold learning based feature extraction for classification of hyper-spectral data UR - http://hdl.handle.net/10204/7197 ER -