Genetic Graph Programming for Object Detection

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

@InProceedings{Krawiec:2006:ICAISC,
  author =       "Krzysztof Krawiec and Patryk Lijewski",
  title =        "Genetic Graph Programming for Object Detection",
  booktitle =    "Proceedings 8th International Conference on Artificial
                 Intelligence and Soft Computing {ICAISC}",
  year =         "2006",
  pages =        "804--813",
  series =       "Lecture Notes on Artificial Intelligence (LNAI)",
  volume =       "4029",
  publisher =    "Springer-Verlag",
  editor =       "Leszek Rutkowski and Ryszard Tadeusiewicz and 
                 Lotfi A. Zadeh and Jacek Zurada",
  address =      "Zakopane, Poland",
  month =        jun # " 25-29",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-540-35748-3",
  DOI =          "doi:10.1007/11785231_84",
  size =         "10 pages",
  abstract =     "We present a novel approach to learning from visual
                 information given in a form of raster images. The
                 proposed learning method uses genetic programming to
                 synthesise an image processing procedure that performs
                 the desired vision task. The evolutionary algorithm
                 maintains a population of individuals, initially
                 populated with random solutions to the problem. Each
                 individual encodes a directed acyclic graph, with graph
                 nodes corresponding to elementary image processing
                 operations (like image arithmetic, convolution
                 filtering, morphological operations, etc.), and graph
                 edges representing the data flow. Each graph contains a
                 single input node to feed in the input image and an
                 output node that yields the final processing result.
                 This genetic learning process is driven by a fitness
                 function that rewards individuals for producing output
                 that conforms the task-specific objectives. This
                 evaluation is carried out with respect to the training
                 set of images. Thanks to such formulation, the fitness
                 function is the only application-dependent component of
                 our approach, which is thus applicable to a wide range
                 of vision tasks (image enhancement, object detection,
                 object tracking, etc.). The paper presents the approach
                 in detail and describes the computational experiment
                 concerning the task of object tracking in a real-world
                 video sequence.",
}

Genetic Programming entries for Krzysztof Krawiec Patryk Lijewski

Citations