A Two Phase Genetic Programming Approach to Object Detection

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Mengjie Zhang and Peter Andreae and Urvesh Bhowan",
  title =        "A Two Phase Genetic Programming Approach to Object
  institution =  "Computer Science, Victoria University of Wellington",
  year =         "2004",
  number =       "CS-TR-04-6",
  address =      "New Zealand",
  keywords =     "genetic algorithms, genetic programming, pixel
                 statistics, false alarm area, program size, two-phase
                 approach, multiclass object detection",
  URL =          "http://www.mcs.vuw.ac.nz/comp/Publications/archive/CS-TR-04/CS-TR-04-6.pdf",
  URL =          "http://www.mcs.vuw.ac.nz/comp/Publications/CS-TR-04-6.abs.html",
  size =         "14 pages",
  abstract =     "This paper describes two innovations that improve the
                 efficiency and effectiveness of a genetic programming
                 approach to object detection problems. The approach
                 uses genetic programming to construct object detection
                 programs that are applied, in a moving window fashion,
                 to the large images to locate the objects of interest.
                 The first innovation is to break the GP search into two
                 phases with the first phase applied to a selected
                 subset of the training data, and a simplified fitness
                 function. The second phase is initialised with the
                 programs from the first phase, and uses the full set of
                 training data with a complete fitness function to
                 construct the final detection programs. The second
                 innovation is to add a program size component to the
                 fitness function. This approach was applied to three
                 object detection problems of increasing difficulty. The
                 results indicate that the innovations increased both
                 the effectiveness and the efficiency of the genetic
                 programming search, and also that the genetic
                 programming approach was more effective than a neural
                 network approach.",

Genetic Programming entries for Mengjie Zhang Peter Andreae Urvesh Bhowan