Two-Tier genetic programming: towards raw pixel-based image classification

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

@Article{AlSahaf2012,
  author =       "Harith Al-Sahaf and Andy Song and 
                 Kourosh Neshatian and Mengjie Zhang",
  title =        "Two-Tier genetic programming: towards raw pixel-based
                 image classification",
  journal =      "Expert Systems with Applications",
  volume =       "39",
  number =       "16",
  pages =        "12291--12301",
  year =         "2012",
  ISSN =         "0957-4174",
  DOI =          "doi:10.1016/j.eswa.2012.02.123",
  URL =          "http://www.sciencedirect.com/science/article/pii/S0957417412003867",
  keywords =     "genetic algorithms, genetic programming, Evolutionary
                 computation, Feature extraction, Feature selection,
                 Image classification",
  abstract =     "Classifying images is of great importance in machine
                 vision and image analysis applications such as object
                 recognition and face detection. Conventional methods
                 build classifiers based on certain types of image
                 features instead of raw pixels because the
                 dimensionality of raw inputs is often too large.
                 Determining an optimal set of features for a particular
                 task is usually the focus of conventional image
                 classification methods. In this study we propose a
                 Genetic Programming (GP) method by which raw images can
                 be directly fed as the classification inputs. It is
                 named as Two-Tier GP as every classifier evolved by it
                 has two tiers, the other for computing features based
                 on raw pixel input, one for making decisions. Relevant
                 features are expected to be self-constructed by GP
                 along the evolutionary process. This method is compared
                 with feature based image classification by GP and
                 another GP method which also aims to automatically
                 extract image features. Four different classification
                 tasks are used in the comparison, and the results show
                 that the highest accuracies are achieved by Two-Tier
                 GP. Further analysis on the evolved solutions reveals
                 that there are genuine features formulated by the
                 evolved solutions which can classify target images
                 accurately.",
}

Genetic Programming entries for Harith Al-Sahaf Andy Song Kourosh Neshatian Mengjie Zhang

Citations