Proceedings chapter
Open access

Temporal precedence in asynchronous visual indexing

Published inProceedings of the 5th International Conference on Computer Analysis of Images and Patterns (CAIP'93), Editors D. Chetverikov and W. G. Kropatsch, p. 468-475
Presented at Budapest (Hungary)
  • Lecture Notes in Computer Science; 719
Publication date1993

A recent trend in model-based object recognition is to build efficient systems for primary hypotheses generation. These systems, also called visual indexing, rely on the assumption that object identification can be performed by recovering local invariants. However, reliable and significant local features are difficult to retrieve when the image background is not uniform.Our solution to this problem takes advantage of a new concept called temporal precedence. The originality of the approach consists in transforming the initial static input image into a dynamic flow of data. Primitives extracted from the image are temporally ranked so as to favor most relevant features for recognition. Most importantly, ranks of features of different kinds may be compared.The architecture of our indexing system is composed of a set of knowledge sources which update in parallel a blackboard structure. The asynchronism produced by the flow of input primitives is used in the activation strategy of knowledge sources.

  • Signal, Image and Speech Processing
  • Pattern Recognition
  • Software Engineering/Programming and Operating Systems
  • Computer-Aided Engineering (CAD, CAE) and Design
  • Image Processing and Computer Vision
Citation (ISO format)
BOST, Jean Marc, MILANESE, Ruggero, PUN, Thierry. Temporal precedence in asynchronous visual indexing. In: Proceedings of the 5th International Conference on Computer Analysis of Images and Patterns (CAIP′93). Budapest (Hungary). [s.l.] : Springer-Verlag, 1993. p. 468–475. (Lecture Notes in Computer Science) doi: 10.1007/3-540-57233-3_61
Main files (1)
Proceedings chapter (Accepted version)

Technical informations

Creation03/06/2015 5:12:09 PM
First validation03/06/2015 5:12:09 PM
Update time03/14/2023 10:58:51 PM
Status update03/14/2023 10:58:51 PM
Last indexation08/29/2023 3:10:09 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack