Image and Video Indexing using Networks of Operators - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles EURASIP Journal on Image and Video Processing Year : 2007

Image and Video Indexing using Networks of Operators

Abstract

This article presents a framework for the design of concept detection systems for image and video indexing. This framework integrates in a homogeneous way all the data and processing types. The semantic gap is crossed in a number of steps, each producing a small increase in the abstraction level of the handled data. All the data inside the semantic gap and on both sides included are seen as a homogeneous type called \em numcept and all the processing modules between the various numcepts are seen as a homogeneous type called \em operator. Concepts are extracted from the raw signal using networks of operators operating on numcepts. These networks can be represented as data-flow graphs and the introduced homogenizations allow fusing elements regardless of their nature. Low-level descriptors can be fused with intermediate of final concepts.
No file

Dates and versions

hal-00953803 , version 1 (28-02-2014)

Identifiers

  • HAL Id : hal-00953803 , version 1

Cite

Stéphane Ayache, Georges Quénot. Image and Video Indexing using Networks of Operators. EURASIP Journal on Image and Video Processing, 2007. ⟨hal-00953803⟩
121 View
0 Download

Share

Gmail Facebook X LinkedIn More