Hyperspectral Image Analysis Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4340

  author =       "Brian J. Ross and Anthony G. Gualtieri and 
                 Frank Fueten and Paul Budkewitsch",
  title =        "Hyperspectral Image Analysis Using Genetic
  institution =  "Department of Computer Science, Brock University",
  year =         "2002",
  type =         "Technical Report",
  number =       "CS-02-12",
  month =        may,
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.cosc.brocku.ca/Department/Research/TR/cs0212.pdf",
  URL =          "http://citeseer.ist.psu.edu/523309.html",
  abstract =     "Genetic programming is used to evolve mineral
                 identification functions for hyperspectral images. The
                 input image set comprises 168 images from different
                 wavelengths ranging from 428 nm (visible blue) to 2507
                 nm (invisible shortwave in the infrared), taken over
                 Cuprite, Nevada, with the AVIRIS hyperspectral sensor.
                 A composite mineral image indicating the overall
                 reflectance percentage of three minerals (alunite,
                 kaolnite, buddingtonite) is used as a reference or
                 {"}solution{"} image. The training set is manually
                 selected from this composite image. The task of the GP
                 system is to evolve mineral identifiers, where each
                 identifier is trained to identify one of the three
                 mineral specimens. A number of different GP experiments
                 were undertaken, which parameterised features such as
                 thresholded mineral reflectance intensity and target GP
                 language. The results are promising, especially for
                 minerals with higher re ectance thresholds (more
                 intense concentrations). One complication in using this
                 technology is the time and expertise required to
                 interpret the data. Hyperspectral imaging systems such
                 as the NASA/JPL AVIRIS 1 sensor can capture over 200
                 bandwidths for a single geographic location (Green et
                 al. 1998). This is denoted by a hyperspectral cube,
                 which takes the form of many hundreds of mega-bytes of
                 information. Interpreting this massive amount of data
                 is difficult, especially considering that the spectra
                 obtained represent mixed spectral signatures of a
                 variety of materials. Moreover, noise and other
                 unwanted effects must be considered. Deciphering this
                 enormous volume of cryptic data is therefore next to
                 impossible for humans to do manually.",
  size =         "9 pages. See also \cite{ross2:2002:gecco}",

Genetic Programming entries for Brian J Ross Anthony G Gualtieri Frank Fueten Paul Budkewitsch