UNIGE document Chapitre d'actes
previous document  unige:47720  next document
add to browser collection

Temporal precedence in asynchronous visual indexing

Published in D. Chetverikov and W. G. Kropatsch. Proceedings of the 5th International Conference on Computer Analysis of Images and Patterns (CAIP'93). Budapest (Hungary): Springer-Verlag. 1993, p. 468-475
Collection Lecture Notes in Computer Science; 719
Abstract 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.
Keywords Signal, Image and Speech ProcessingPattern RecognitionSoftware Engineering/Programming and Operating SystemsComputer-Aided Engineering (CAD, CAE) and DesignImage Processing and Computer Vision
Full text
Research groups Computer Vision and Multimedia Laboratory
Multimodal Interaction Group
(ISO format)
BOST, Jean Marc, MILANESE, Ruggero, PUN, Thierry. Temporal precedence in asynchronous visual indexing. In: D. Chetverikov and W. G. Kropatsch (Ed.). 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; 719) doi: 10.1007/3-540-57233-3_61 https://archive-ouverte.unige.ch/unige:47720

359 hits



Deposited on : 2015-03-06

Export document
Format :
Citation style :