A Domain-independent Window approach to Multiclass Object Detection using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{Zhang:2003:JASP,
  author =       "Mengjie Zhang and Victor B. Ciesielski and 
                 Peter Andreae",
  title =        "A Domain-independent Window approach to Multiclass
                 Object Detection using Genetic Programming",
  journal =      "{EURASIP} Journal on Applied Signal Processing",
  year =         "2003",
  volume =       "2003",
  number =       "8",
  pages =        "841--859",
  month =        jul,
  note =         "Special Issue on Genetic and Evolutionary Computation
                 for Signal Processing and Image Analysis",
  email =        "mengjie@mcs.vuw.ac.nz",
  keywords =     "genetic algorithms, genetic programming, machine
                 learning, neural networks, object recognition, target
                 detection, computer vision",
  ISSN =         "1110-8657",
  URL =          "http://www.mcs.vuw.ac.nz/~pondy/eurasip2003.pdf",
  URL =          "http://downloads.hindawi.com/journals/asp/2003/206791.pdf",
  DOI =          "doi:10.1155/S1110865703303063",
  abstract =     "a domain-independent approach to the use of genetic
                 programming for object detection problems in which the
                 locations of small objects of multiple classes in large
                 images must be found. The evolved program is scanned
                 over the large images to locate the objects of
                 interest. The paper develops three terminal sets based
                 on domain-independent pixel statistics and considers
                 two different function sets. The fitness function is
                 based on the detection rate and the false alarm rate.
                 We have tested the method on three object detection
                 problems of increasing difficulty. This work not only
                 extends genetic programming to multiclass-object
                 detection problems, but also shows how to use a single
                 evolved genetic program for both object classification
                 and localisation. The object classification map
                 developed in this approach can be used as a general
                 classification strategy in genetic programming for
                 multiple-class classification problems.",
  notes =        "Special Issue on genetic and evolutionary computation
                 for signal processing and image analysis
                 http://asp.hindawi.com/volume-2003/issue-8.html
                 European Association for Speech, Signal and Image
                 Processing (EURASIP) asp@asp.hindawi.com

                 31 Aug 2003 problems reading PDF",
}

Genetic Programming entries for Mengjie Zhang Victor Ciesielski Peter Andreae

Citations