Improving Object Detection Performance with Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Mengjie Zhang",
  title =        "Improving Object Detection Performance with Genetic
  journal =      "International Journal on Artificial Intelligence
  year =         "2007",
  volume =       "16",
  number =       "5",
  pages =        "849--873",
  month =        oct,
  keywords =     "genetic algorithms, genetic programming, object
                 recognition, target recognition, fitness function,
                 program size, two-phase learning, neural networks",
  DOI =          "doi:10.1142/S0218213007003576",
  abstract =     "This paper describes three developments to improve
                 object detection performance using genetic programming.
                 The first investigates three feature sets, the second
                 investigates a new fitness function, and the third
                 introduces a two phase learning method using genetic
                 programming. This approach is examined on three object
                 detection problems of increasing difficulty and
                 compared with a neural network approach. The two phase
                 GP approach with the new fitness function and the local
                 concentric circular region features achieved the best
                 results. The results suggest that the concentric
                 circular pixel statistics are more effective than the
                 square features for these object detection problems.
                 The fitness function with program size is more
                 effective and more efficient than without for these
                 object detection problems and the evolved genetic
                 programs using this fitness function are much shorter
                 and easier to interpret. The two phase GP approach is
                 more effective and more efficient than the single stage
                 GP approach, and also more effective than the neural
                 network approach on these problems using the same set
                 of features.",

Genetic Programming entries for Mengjie Zhang