Extraction of Attributes, Nature and Context of Images (bibtex)
by Stefan Kuthan
Abstract:
In this thesis a framework for deriving high-level scene attributes from low-level image features is developed. Examples of attributes derived are photo-painting, indoor-outdoor, night-day and nature-city. The assignment of the attributes to images is done by a hierarchical classification of the low level features, which capture colour, texture and spatial information. A concise summary of current research and methods used in this field of research is given. Furthermore, a prototype for image classification is implemented, which aids in the evaluation of the different methods available. Training and test images are provided by the ImagEVAL project, a French computer vision evaluation project.
Reference:
Extraction of Attributes, Nature and Context of Images (Stefan Kuthan), Technical report, PRIP, TU Wien, 2005.
Bibtex Entry:
@TechReport{TR101,
  author =	 "Stefan Kuthan",
  title =	 "Extraction of Attributes, Nature and Context of
                  Images",
  institution =	 "PRIP, TU Wien",
  number =	 "PRIP-TR-101",
  year =	 "2005",
  url =		 "ftp://ftp.prip.tuwien.ac.at/pub/publications/trs/tr101.pdf",
  abstract =	 "In this thesis a framework for deriving high-level
                  scene attributes from low-level image features is
                  developed. Examples of attributes derived are
                  photo-painting, indoor-outdoor, night-day and
                  nature-city. The assignment of the attributes to
                  images is done by a hierarchical classification of
                  the low level features, which capture colour,
                  texture and spatial information. A concise summary
                  of current research and methods used in this field
                  of research is given. Furthermore, a prototype for
                  image classification is implemented, which aids in
                  the evaluation of the different methods
                  available. Training and test images are provided by
                  the ImagEVAL project, a French computer vision
                  evaluation project.",
}
Powered by bibtexbrowser