Region Graphs for Organizing Image Collections

Alexander Ladikos 1 Edmond Boyer 2 Nassir Navab 1 Slobodan Ilic 1
2 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper we consider large image collections and their organization into meaningful data structures upon which applications can be build (e.g. navigation or reconstruction). In contrast to structures that only reflect local relationships between pairs of images we propose to account for the information an image brings to a collection with respect to all other images. Our approach builds on abstracting from image domains and focusing on image regions, thereby reducing the influence of outliers and background clutter. We introduce a graph structure based on these regions which encodes the overlap between them. The contribution of an image to a collection is then related to the amount of overlap of its regions with the other images in the collection. We demonstrate our graph based structure with several applications: image set reduction, canonical view selection and image-based navigation. The data sets used in our experiments range from small examples to large image collections with thousands of images.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download


https://hal.inria.fr/inria-00568914
Contributor : Edmond Boyer <>
Submitted on : Wednesday, February 23, 2011 - 8:04:12 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:46 AM
Long-term archiving on : Tuesday, May 24, 2011 - 4:32:21 AM

Files

Ladikos.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Alexander Ladikos, Edmond Boyer, Nassir Navab, Slobodan Ilic. Region Graphs for Organizing Image Collections. ECCV 2010 Workshop on Reconstruction and Modeling of Large-Scale 3D Virtual Environments, Sep 2010, Heraklion, Greece. pp.239-252, ⟨10.1007/978-3-642-35740-4_19⟩. ⟨inria-00568914⟩

Share

Metrics

Record views

625

Files downloads

377