Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published January 2000 | Accepted Version
Journal Article Open

Bayesian reasoning on qualitative descriptions from images and speech

Abstract

Image understanding denotes not only the ability to extract specific, non-numerical information from images, but it implies also reasoning about the extracted information. We propose a qualitative representation for image understanding results, which is suitable for reasoning with Bayesian networks. Our qualitative representation is enhanced with probabilistic information to represent uncertainties and errors in the understanding of noisy sensory data. The probabilistic information is supplied to a Bayesian network in order to find the most plausible interpretation. We apply this approach for the integration of image and speech understanding in a scenario where we want to find objects in a visually observed scene which are verbally described by a human. Results demonstrate the performance of our approach.

Additional Information

Copyright © 2000 Elsevier. Received 18 September 1997, Revised 18 December 1998, Accepted 13 July 1999, Available online 12 January 2000. This work has been supported by the German Research Foundation (DFG) in the project SFB 360 and the German Academic Exchange Service (DAAD) under the grant program HSP II/AUFE. Collaborations with Constanze Vorwerg, Thomas Fuhr, and Franz Kummert have been very fruitful for this work.

Attached Files

Accepted Version - socher_sagerer_perona98.pdf

Files

socher_sagerer_perona98.pdf
Files (1.2 MB)
Name Size Download all
md5:c14d8da00607f061f1455511514cb9dc
1.2 MB Preview Download

Additional details

Created:
August 21, 2023
Modified:
October 26, 2023