Dimension Reduction Methods For Hyperspectral Image: A Survey
K. Thilagavathi1, A.Vasuki2
1K.Thilagavathi, Assistant Professor, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
2A.Vasuki, Professor, Department of Electronics and Communication Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 30 December 2018 | PP: 160-167 | Volume-8 Issue-2S, December 2018 | Retrieval Number: 100.1/ijeat.B10411282S18/18©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Hyperspectral imaging (HSI) is one of the progressive remote sensing techniques. HSI captures data in large number of continuous spectral bands with the spectral range from visible light to (near) infrared, so it is capable of detecting and identifying the minute differences of objects and their changes in temperature and moisture. But its high dimensional nature makes its analysis complex. Various methods have been developed to reduce the dimension of hyperspectral image by feature extraction. This paper highlights the advantages and drawbacks of number of classical dimension reduction algorithms in machine learning communities for HSI classification.
Keywords: Hyperspectral Imaging, Dimension Reduction, Feature Extrction, Classification.
Scope of the Article: Image Security