Affine invariant visual phrases for object instance recognition
Authors
Patraucean, Viorica
Ovsjanikov, M
Publication Date
2015Journal Title
Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Conference Name
2015 14th IAPR International Conference on Machine Vision Applications (MVA)
ISBN
9784901122153
Publisher
IEEE
Pages
14-17
Language
English
Type
Conference Object
Metadata
Show full item recordCitation
Patraucean, V., & Ovsjanikov, M. (2015). Affine invariant visual phrases for object instance recognition. Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015, 14-17. https://doi.org/10.1109/MVA.2015.7153122
Abstract
Object instance recognition approaches based on the
bag-of-words model are severely affected by the loss of
spatial consistency during retrieval. As a result, costly
RANSAC verification is needed to ensure geometric
consistency between the query and the retrieved images.
A common alternative is to inject geometric informa-
tion directly into the retrieval procedure, by endowing
the visual words with additional information. Most of
the existing approaches in this category can efficiently
handle only restricted classes of geometric transfor-
mations, including scale and translation. In this pa-
per, we propose a simple and efficient scheme that can
cover the more complex class of full affine transforma-
tions. We demonstrate the usefulness of our approach
in the case of planar object instance recognition, such
as recognition of books, logos, traffic signs, etc.
Sponsorship
This work was funded by a Google Faculty Research
Award, the Marie Curie grant CIG-334283-HRGP, a
CNRS chaire d'excellence.
Identifiers
External DOI: https://doi.org/10.1109/MVA.2015.7153122
This record's URL: https://www.repository.cam.ac.uk/handle/1810/248058
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics