Skip to Main content Skip to Navigation
Conference papers

Automatic detection of repeated objects in images

Abstract : The definition of an "object" through the presentation of several of its instances is certainly one of the most efficient ways for humans and machines to learn. An object can be "learned" from a single image, just because it is repeating. In this paper, we explore a three step algorithm to detect repeated objects in images. Starting from a graph of auto-correspondences inside an image, we first extract subgraphs composed of repetitions of unbreakable pieces of objects, that we call atoms. Then, these graphs of atoms are grouped into initial propositions of object instances. Finally, geometry inconsistencies are filtered out to end up with the final repeated object. The meaningfulness of object repetitions is measured by their Number of False Alarms (NFA), which provides a natural order among repeated objects in images; a very low NFA being a strong proof of existence of the discovered object. Source codes are available at https: //rdguez-mariano.github.io/pages/autosim.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03126917
Contributor : Mariano Rodríguez Connect in order to contact the contributor
Submitted on : Monday, February 1, 2021 - 10:46:25 AM
Last modification on : Tuesday, January 4, 2022 - 6:01:56 AM
Long-term archiving on: : Sunday, May 2, 2021 - 6:53:58 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03126917, version 1

Citation

Mariano Rodríguez, Jean-Michel Morel, Julie Delon. Automatic detection of repeated objects in images. IEEE International Conference on Image Processing, Sep 2021, Anchorage, Alaska, United States. ⟨hal-03126917⟩

Share

Metrics

Les métriques sont temporairement indisponibles