Review of Image Annotation for the Evaluation of Computer Vision Algorithms (bibtex)
by Allan Hanbury
Abstract:
In the field of computer vision, automated image annotation and object recognition are currently important research topics. It is hoped that these will lead to improved general image understanding which can be usefully applied in Content-based Image Retrieval. Three approaches to image annotation are reviewed: free text annotation, keyword annotation and annotation based on ontologies. An analysis of the keywords which have been used in automated image and video annotation research and evaluation campaigns is then presented. The outcome of this analysis is a list of 525 keywords divided into 15 categories. Given that this list is collected from existing image annotations, it could be used to check the applicability of ontologies describing entities which are portrayable in images.
Reference:
Review of Image Annotation for the Evaluation of Computer Vision Algorithms (Allan Hanbury), Technical report, PRIP, TU Wien, 2006.
Bibtex Entry:
@TechReport{TR102,
  author =	 "Allan Hanbury",
  title =	 "Review of Image Annotation for the Evaluation of
                  Computer Vision Algorithms",
  institution =	 "PRIP, TU Wien",
  number =	 "PRIP-TR-102",
  year =	 "2006",
  url =		 "ftp://ftp.prip.tuwien.ac.at/pub/publications/trs/tr102.pdf",
  abstract =	 " In the field of computer vision, automated image
                  annotation and object recognition are currently
                  important research topics. It is hoped that these
                  will lead to improved general image understanding
                  which can be usefully applied in Content-based Image
                  Retrieval. Three approaches to image annotation are
                  reviewed: free text annotation, keyword annotation
                  and annotation based on ontologies. An analysis of
                  the keywords which have been used in automated image
                  and video annotation research and evaluation
                  campaigns is then presented. The outcome of this
                  analysis is a list of 525 keywords divided into 15
                  categories. Given that this list is collected from
                  existing image annotations, it could be used to
                  check the applicability of ontologies describing
                  entities which are portrayable in images.",
}
Powered by bibtexbrowser