Automatic detection of repeated objects in images

Mariano Rodríguez (1) , Jean-Michel Morel (1) , Julie Delon (2)

1 CB - CB - Centre Borelli - UMR 9010
2 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5

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.

Mots clés: image comparison; SIFT; autosimilarities; symmetry detection; RANSAC; NFA

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

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. ⟨10.1109/icip42928.2021.9506799⟩. ⟨hal-03126917⟩