Genetic programming for improving image descriptors generated using the scale-invariant feature transform

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

@InProceedings{conf/ivcnz/HindmarshAZ12,
  author =       "Samuel Hindmarsh and Peter Andreae and Mengjie Zhang",
  title =        "Genetic programming for improving image descriptors
                 generated using the scale-invariant feature transform",
  booktitle =    "Image and Vision Computing New Zealand, IVCNZ, 2012",
  year =         "2012",
  editor =       "Brendan McCane and Steven Mills and Jeremiah D. Deng",
  pages =        "85--90",
  address =      "Dunedin, New Zealand",
  month =        nov # " 26-28",
  publisher =    "ACM",
  keywords =     "genetic algorithms, genetic programming, SIFT, object
                 recognition",
  isbn13 =       "978-1-4503-1473-2",
  URL =          "http://dl.acm.org/citation.cfm?id=2425836",
  DOI =          "doi:10.1145/2425836.2425855",
  acmid =        "2425855",
  bibdate =      "2013-01-15",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/ivcnz/ivcnz2012.html#HindmarshAZ12",
  size =         "6 pages",
  abstract =     "Object recognition is an important task in the
                 computer vision field as it has many applications,
                 including optical character recognition and facial
                 recognition. However, many existing methods have
                 demonstrated relatively poor performance in all but the
                 most simple cases. Scale-invariant feature transform
                 (SIFT) features attempt to alleviate issues surrounding
                 complex examples involving variances in scale, rotation
                 and illumination, but suffer, potentially, from the way
                 the algorithm describes the key points it detects in
                 images. Genetic programming (GP) is used for the first
                 time in an attempt to find the optimal way of
                 describing the image keypoints extracted by the SIFT
                 algorithm. Training and testing results show that the
                 fittest program from a GP search can improve on the
                 standard SIFT descriptors after only a few generations
                 of a small population. While early results may not yet
                 show major improvements over standard SIFT features,
                 they do open the door for further research and
                 experimentation.",
  notes =        "IVCNZ",
}

Genetic Programming entries for Samuel Hindmarsh Peter Andreae Mengjie Zhang

Citations