Guiding a Bottom-Up Visual Attention Mechanism to Locate Specific Image Regions Using a Distributed Genetic Optimization

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Pereira:2006:CIARP,
  author =       "Eanes T. Pereira and Herman M. Gomes",
  title =        "Guiding a Bottom-Up Visual Attention Mechanism to
                 Locate Specific Image Regions Using a Distributed
                 Genetic Optimization",
  booktitle =    "11th Iberoamerican Congress in Pattern Recognition,
                 CIARP 2006",
  year =         "2006",
  editor =       "Jose Francisco Martinez-Trinidad and 
                 Jesus Ariel {Carrasco Ochoa} and Josef Kittler",
  volume =       "4225",
  series =       "LNCS",
  pages =        "257--266",
  address =      "Cancun, Mexico",
  month =        nov # " 14-17",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-540-46557-7",
  annote =       "The Pennsylvania State University CiteSeerX Archives",
  bibsource =    "OAI-PMH server at citeseerx.ist.psu.edu",
  language =     "en",
  oai =          "oai:CiteSeerX.psu:10.1.1.584.8447",
  rights =       "Metadata may be used without restrictions as long as
                 the oai identifier remains attached to it.",
  URL =          "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.584.8447",
  broken =       "http://www.dsc.ufcg.edu.br/~wdcopin/VWDCOPIN/artigos/eanes/eanes.pdf",
  DOI =          "doi:10.1007/11892755_26",
  size =         "10 pages",
  abstract =     "The purpose of this paper is to present an approach to
                 locate specific regions in images. The novelty of the
                 approach is the combination of a weighted bottom-up
                 visual attention mechanism with a genetic algorithm
                 optimisation running on a computational grid. The
                 visual attention mechanism is based on the model
                 proposed by Itti and Koch [1]. A saliency map indicates
                 the most interesting points in an image using a number
                 of intermediate low level features, which are detected
                 at different scales and orientations. Using the
                 saliency map weights as parameters, the optimisation
                 problem is to minimise the number of most salient
                 points needed to locate a set of reference image
                 regions, previously (and manually) labelled as being
                 interesting. Both an objective and subjective
                 evaluation have demonstrated that the proposed approach
                 is more effective when compared to a fixed weight
                 attention mechanism.",
}

Genetic Programming entries for Eanes T Pereira Herman M Gomes

Citations