2007 | 5 Themenheft

Browsing 2007 | 5 Themenheft by Subject "ddc:791"

Now showing 1 - 5 of 5
  • Article
    Automatic Generation of Movie Trailers using Ontologies
    The SVP Group (2007) , S. 117-139
    With the advances in digital audio and video analysis, automatic movie summarization has become an important field of research. Much of the work has been put into movie abstracting for large media databases. Looking at the topic from a different side, the movie industry has long since perfected the art of summarization in their advertising trailers to attract an audience. In this paper we introduce the approach of automatically generating entertaining Hollywood-like trailers based on a trailer grammar, enhanced by an ontology. The extraction of features from movies using state-of-the-art image and audio processing techniques builds the foundation for the selection of meaningful and usable material, which is re-assembled according to the defined rules. User testing of our automatically produced trailers shows that they are well accepted and in many ways comparable to professionally composed trailers.
  • Article
    Conclusive Notes on Computational Picture Morphology
    Schirra, Jörg (2007) , S. 140-153
    As the thematic issue of IMAGE on computational image morphology attempts in particular to mediate between computational visualistics and other disciplines investigating pictures and their uses, the following remarks broaden the perspective again and relate the computational argumentations of the preceding papers to the more general discussion of image science. The two fundamental categories of picture syntax, the geometric base structure and the marker value dimension, are described. They are applied to the questions whether pictures with ill-formed syntax may exist at all, and if so, whether computers can deal with them as well. The overview finally extends the discussion to the limits of pictorial syntax studies.
  • Article
    Image Morphology: From Perception to Rendering
    Buf, Hans Du; Rodrigues, Joao (2007) , S. 98-116
    A complete image ontology can be obtained by formalising a top-down meta-language which must address all possibilities, from global message and composition to objects and local surface properties. In computer vision, where one general goal is image understanding, one starts with a bunch of pixels. The latter is a typical example of bottom-up processing, from pixels to objects to layout and gist. Both top-down and bottom-up approaches are possible, but can these be unified? As it turns out, the answer is yes, because our visual system does it all the time. This follows from our progress in developing models of the visual system, and using the models in re-creating an input image in the form of a painting.
  • Journal Issue
  • Article
    Mereogeometry and Pictorial Morphology
    Borgo, Stefano; Ferrario, Roberta; Masolo, Claudio; Oltramari, Alessandro (2007) , S. 36-49
    The paper reviews geometrical approaches in the area of qualitative space representation by discussing formal systems of geometry based on the notion of extended regions (mereogeometries). The focus is on primitives that are cognitively motivated and that capture different notions of naive geometry. The paper then moves to consider the role of mereogeometries (and in particular of the concepts they rely upon) in the domain of picture morphology in two ways: it discusses some primitives that are motivated from the cognitive perspective, and it considers the issue of granularity and refinement.