A Caltech Library Service

Bayesian reasoning on qualitative descriptions from images and speech

Socher, Gudrun and Sagerer, Gerhard and Perona, Pietro (2000) Bayesian reasoning on qualitative descriptions from images and speech. Image and Vision Computing, 18 (2). pp. 155-172. ISSN 0262-8856.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Article
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
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.
Funding AgencyGrant Number
German Research Foundation (DFG)SFB 360
German Academic Exchange Service (DAAD)HSP II/AUFE
Subject Keywords:Image understanding; Bayesian networks; Spatial relations; Qualitative description
Issue or Number:2
Record Number:CaltechAUTHORS:20140730-101720846
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47626
Deposited By: Caroline Murphy
Deposited On:18 Aug 2014 23:42
Last Modified:03 Oct 2019 06:55

Repository Staff Only: item control page