by Herzog, Otthein, Miene, Andrea, Hermes, Thorsten and Alshuth, Peter
Abstract:
The large amount and the ubiquitous availability of multimedia information (e.g. video audio, image, and also text documents) require efficient, effective, and automatic annotation and retrieval methods. As videos start to play an even more important role in multimedia, content-based retrieval of videos becomes an issue, especially as ther should be an intergrated methodology for all types of multimedia documents. Our approach for the intergrated retrieval of videos, images, and text comprises three necessary steps: First, the detection and extraction of shot from a video, second, the construction of a still image from the frames in a shot. This is achieved by an extraction of key frames or a mosaicing technique. The result is a single image visualization of a shot, which in turn can be analyzed by the ImageMiner(TM) system. The ImageMiner system was developed in cooperation with IBM at the University of Bremen in the Image Processing Department of the Center for Computing Technologies. It realizes the content-based retrieval of single images through a novel combination of techniques and methods from computer vision and artificial intelligence. Its output is a textual description of an image, and thus in our case, of the static elements of a video shot. In this way, the annotations of a video can be indexed with standard text retrieval systems, along with text documents or annotations of other multimedia documents, thus ensuring an integrated interface for all kinds of multimedia documents.
Reference:
Herzog, Otthein, Miene, Andrea, Hermes, Thorsten and Alshuth, Peter, "Integrated Information Mining for Texts, Images, and Videos", In Comput. & Graphics, vol. 22, no. 6, pp. 675–685, 1998.
Bibtex Entry:
@ARTICLE{Herzog1998b,
author = {Herzog, Otthein and Miene, Andrea and Hermes, Thorsten and Alshuth,
Peter},
title = {Integrated Information Mining for Texts, Images, and Videos},
journal = {Comput. {\&} Graphics},
year = {1998},
volume = {22},
pages = {675--685},
number = {6},
abstract = {The large amount and the ubiquitous availability of multimedia information
(e.g. video audio, image, and also text documents) require efficient,
effective, and automatic annotation and retrieval methods. As videos
start to play an even more important role in multimedia, content-based
retrieval of videos becomes an issue, especially as ther should be
an intergrated methodology for all types of multimedia documents.
Our approach for the intergrated retrieval of videos, images, and
text comprises three necessary steps: First, the detection and extraction
of shot from a video, second, the construction of a still image from
the frames in a shot. This is achieved by an extraction of key frames
or a mosaicing technique. The result is a single image visualization
of a shot, which in turn can be analyzed by the ImageMiner(TM) system.
The ImageMiner system was developed in cooperation with IBM at the
University of Bremen in the Image Processing Department of the Center
for Computing Technologies. It realizes the content-based retrieval
of single images through a novel combination of techniques and methods
from computer vision and artificial intelligence. Its output is a
textual description of an image, and thus in our case, of the static
elements of a video shot. In this way, the annotations of a video
can be indexed with standard text retrieval systems, along with text
documents or annotations of other multimedia documents, thus ensuring
an integrated interface for all kinds of multimedia documents.},
owner = {pmania},
timestamp = {2012.11.06},
url = {http://www-agki.tzi.de/grp/ag-ki/download/1998/herzogetal98.pdf}
}