Classification for hyperspectral imaging

Research output: Contribution to conferencePoster

Abstract

Hyperspectral Imaging is a method of collecting and processing the information across pre-defined electromagnetic spectrum. These measurements make it possible to derive a continuous spectrum for each pixel of the image. After necessary adjustments these image spectra can be compared with database of reflectance spectra in order to recognise tested materials.
This project is conducted in cooperation between Fraunhofer Centre for Applied Photonics and Heriot-Watt Industrial Doctorate Centre in Photonics and Optics Technologies in partnership with University of Strathclyde. Fraunhofer Institute is known of world-class photonics solutions and this project aims in enhancement of one of their Hyperspectral Imaging systems with signal processing techniques. Set of classification procedures would be applied for the output of imaging spectrometer with the intention of spatial and spectral classification of objects captured by the spectrometer.
Spatial classification is based on Support Vector Machine (SVM) classifier. Use of texture features of the objects is considered as a base for labelling of detected items. Spectral classification is based on Partial Least Squares (PLS) method. With database of calibration reflectance spectra, method this can be used for prediction of “end members” concentration and therefore identification of the objects captured on the hyperspectral image. “

Conference

ConferenceIDC in Optics and Photonics Technologies Annual Conference
CountryUnited Kingdom
CityEdinburgh
Period17/07/1417/07/14

Fingerprint

Photonics
Spectrometers
Imaging systems
Labeling
Support vector machines
Optics
Signal processing
Classifiers
Textures
Pixels
Calibration
Imaging techniques
Hyperspectral imaging
Processing

Keywords

  • classification
  • Hyperspectral imaging
  • signal processing
  • spectral classification
  • partial least squares
  • spatial image classification

Cite this

Polak, A., Marshall, S., Ren, J., & Stothard, D. J. M. (2014). Classification for hyperspectral imaging. Poster session presented at IDC in Optics and Photonics Technologies Annual Conference, Edinburgh, United Kingdom.
Polak, Adam ; Marshall, Stephen ; Ren, Jinchang ; Stothard, David J.M. / Classification for hyperspectral imaging. Poster session presented at IDC in Optics and Photonics Technologies Annual Conference, Edinburgh, United Kingdom.1 p.
@conference{5f47beadbd9b480b8b289ddd8f28d971,
title = "Classification for hyperspectral imaging",
abstract = "Hyperspectral Imaging is a method of collecting and processing the information across pre-defined electromagnetic spectrum. These measurements make it possible to derive a continuous spectrum for each pixel of the image. After necessary adjustments these image spectra can be compared with database of reflectance spectra in order to recognise tested materials.This project is conducted in cooperation between Fraunhofer Centre for Applied Photonics and Heriot-Watt Industrial Doctorate Centre in Photonics and Optics Technologies in partnership with University of Strathclyde. Fraunhofer Institute is known of world-class photonics solutions and this project aims in enhancement of one of their Hyperspectral Imaging systems with signal processing techniques. Set of classification procedures would be applied for the output of imaging spectrometer with the intention of spatial and spectral classification of objects captured by the spectrometer. Spatial classification is based on Support Vector Machine (SVM) classifier. Use of texture features of the objects is considered as a base for labelling of detected items. Spectral classification is based on Partial Least Squares (PLS) method. With database of calibration reflectance spectra, method this can be used for prediction of “end members” concentration and therefore identification of the objects captured on the hyperspectral image. “",
keywords = "classification, Hyperspectral imaging, signal processing, spectral classification, partial least squares, spatial image classification",
author = "Adam Polak and Stephen Marshall and Jinchang Ren and Stothard, {David J.M.}",
year = "2014",
language = "English",
note = "IDC in Optics and Photonics Technologies Annual Conference ; Conference date: 17-07-2014 Through 17-07-2014",

}

Polak, A, Marshall, S, Ren, J & Stothard, DJM 2014, 'Classification for hyperspectral imaging' IDC in Optics and Photonics Technologies Annual Conference, Edinburgh, United Kingdom, 17/07/14 - 17/07/14, .

Classification for hyperspectral imaging. / Polak, Adam; Marshall, Stephen; Ren, Jinchang; Stothard, David J.M.

2014. Poster session presented at IDC in Optics and Photonics Technologies Annual Conference, Edinburgh, United Kingdom.

Research output: Contribution to conferencePoster

TY - CONF

T1 - Classification for hyperspectral imaging

AU - Polak, Adam

AU - Marshall, Stephen

AU - Ren, Jinchang

AU - Stothard, David J.M.

PY - 2014

Y1 - 2014

N2 - Hyperspectral Imaging is a method of collecting and processing the information across pre-defined electromagnetic spectrum. These measurements make it possible to derive a continuous spectrum for each pixel of the image. After necessary adjustments these image spectra can be compared with database of reflectance spectra in order to recognise tested materials.This project is conducted in cooperation between Fraunhofer Centre for Applied Photonics and Heriot-Watt Industrial Doctorate Centre in Photonics and Optics Technologies in partnership with University of Strathclyde. Fraunhofer Institute is known of world-class photonics solutions and this project aims in enhancement of one of their Hyperspectral Imaging systems with signal processing techniques. Set of classification procedures would be applied for the output of imaging spectrometer with the intention of spatial and spectral classification of objects captured by the spectrometer. Spatial classification is based on Support Vector Machine (SVM) classifier. Use of texture features of the objects is considered as a base for labelling of detected items. Spectral classification is based on Partial Least Squares (PLS) method. With database of calibration reflectance spectra, method this can be used for prediction of “end members” concentration and therefore identification of the objects captured on the hyperspectral image. “

AB - Hyperspectral Imaging is a method of collecting and processing the information across pre-defined electromagnetic spectrum. These measurements make it possible to derive a continuous spectrum for each pixel of the image. After necessary adjustments these image spectra can be compared with database of reflectance spectra in order to recognise tested materials.This project is conducted in cooperation between Fraunhofer Centre for Applied Photonics and Heriot-Watt Industrial Doctorate Centre in Photonics and Optics Technologies in partnership with University of Strathclyde. Fraunhofer Institute is known of world-class photonics solutions and this project aims in enhancement of one of their Hyperspectral Imaging systems with signal processing techniques. Set of classification procedures would be applied for the output of imaging spectrometer with the intention of spatial and spectral classification of objects captured by the spectrometer. Spatial classification is based on Support Vector Machine (SVM) classifier. Use of texture features of the objects is considered as a base for labelling of detected items. Spectral classification is based on Partial Least Squares (PLS) method. With database of calibration reflectance spectra, method this can be used for prediction of “end members” concentration and therefore identification of the objects captured on the hyperspectral image. “

KW - classification

KW - Hyperspectral imaging

KW - signal processing

KW - spectral classification

KW - partial least squares

KW - spatial image classification

M3 - Poster

ER -

Polak A, Marshall S, Ren J, Stothard DJM. Classification for hyperspectral imaging. 2014. Poster session presented at IDC in Optics and Photonics Technologies Annual Conference, Edinburgh, United Kingdom.