Hyperspectral feature recognition based on kernel PCA and relational perspective map
Chinese Optics Letters, Vol. 8, Issue 8, pp. 811-814 (2010)
Acrobat PDF (447 KB)
Abstract
A novel joint kernel principal component analysis (PCA) and relational perspective map (RPM) method called KPmapper is proposed for hyperspectral dimensionality reduction and spectral feature recognition. Kernel PCA is used to analyze hyperspectral data so that the major information corresponding to features can be better extracted. RPM is used to visualize hyperspectral data through two-dimensional (2D) maps, and it is an efficient approach to discover regularities and extract information by partitioning the data into pieces and mapping them onto a 2D space. The experimental results prove that the KPmapper algorithm can effectively obtain the intrinsic features in nonlinear high dimensional data. It is useful and impressing for dimensionality reduction and spectral feature recognition.
© 2010 Chinese Optics Letters
OCIS Codes
(100.5010) Image processing : Pattern recognition
(300.6170) Spectroscopy : Spectra
(280.4788) Remote sensing and sensors : Optical sensing and sensors
Citation
Hongjun Su and Yehua Sheng, "Hyperspectral feature recognition based on kernel PCA and relational perspective map," Chin. Opt. Lett. 8, 811-814 (2010)
http://www.opticsinfobase.org/col/abstract.cfm?URI=col-8-8-811
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
Related Journal Articles 
- Automatic extraction of ground control regions and orthorectification of remote sensing imagery (OE)
- Fusion of infrared and visual images through region extraction by using multi scale center-surround top-hat transform (OE)
- Optimal design of a spectral readout type planar waveguide-mode sensor with a monolithic structure (OE)
- Noise-suppressed image enhancement using multiscale top-hat selection transform through region extraction (AO)
- Adaptive affinity propagation with spectral angle mapper for semi-supervised hyperspectral band selection (AO)
Related Conference Papers
- Probing Nano-Structures Using Rayleigh Scattering with Supercontinuum Radiation
- Ultrafast relaxation inside proteins: Calculation and measurement of electron-vibration coupling in enzymes
- Singular optics with polychromatic light: spectral anomalies in diffraction
- Photoluminescence excitation spectra in T-shaped quantum wires
- Protein-Membrane Interaction Probed by Single Plasmonic Nanoparticles
OSA is a member of 