Use of Flawed and Ideal Image Pairs to Drive Filter Creation by Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3949

@InProceedings{conf/dphoto/SridharDE16,
  title =        "Use of Flawed and Ideal Image Pairs to Drive Filter
                 Creation by Genetic Programming",
  author =       "Subash Marri Sridhar and Henry G. Dietz and 
                 Paul Selegue Eberhart",
  editor =       "Jackson Roland and Radka Tezaur and Dietmar Wueller",
  publisher =    "Ingenta",
  year =         "2016",
  volume =       "2016",
  number =       "18",
  keywords =     "genetic algorithms, genetic programming",
  ISSN =         "2470-1173",
  URL =          "http://www.ingentaconnect.com/content/ist/ei/2016/00002016/00000018/art00023",
  DOI =          "doi:10.2352/ISSN.2470-1173.2016.18.DPMI-016",
  bibdate =      "2016-07-05",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/dphoto/dphoto2016.html#SridharDE16",
  booktitle =    "Digital Photography and Mobile Imaging {XII}, San
                 Francisco, California, {USA}, February 14-18, 2016",
  URL =          "http://ist.publisher.ingentaconnect.com/content/ist/ei/2016/00002016/00000018",
  abstract =     "Traditional image enhancement techniques improve
                 images by applying a series of filters, each of which
                 repairs a specific type of flaw, but most modern
                 digital cameras produce images with a variety of subtle
                 interacting defects. Sequential repair is slow, and the
                 interactions limit the effectiveness. This paper
                 describes a fundamentally different approach in which a
                 single filter is created to repair the potentially
                 myriad interacting defects associated with a particular
                 camera configuration and set of exposure parameters.
                 Genetic programming (GP) is used to automatically
                 evolve a filter algorithm that will convert flawed
                 images into images minimally differing at the pixel
                 level from the corresponding provided ideal images. For
                 example, the flawed images might be shot at a high ISO
                 and the ideal ones might be the exact same static
                 scenes, aligned at the pixel level, but shot at a low
                 ISO using appropriately longer exposure times. Just as
                 easily, the flawed images might be technically well
                 corrected, while the ideal ones were manually-edited to
                 adjust and smooth skin tones, sharpen hair, enhance
                 shadow regions, et. The custom-coded parallel GP, its
                 performance, and performance of the generated filters
                 is discussed with an example.",
  notes =        "Published in Electronic Imaging science and
                 technology",
}

Genetic Programming entries for Subash Marri Sridhar Henry G Dietz Paul Selegue Eberhart

Citations