Skip to Main content Skip to Navigation
Conference papers

Scale-Invariant Proximity Graph for Fast Probabilistic Object Recognition

Jérôme Revaud 1 Guillaume Lavoué 2 Yasuo Ariki Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : A pseudo-hierarchical graph matching procedure dedicated to object recognition is presented in this paper. From a single model image, a graph is built by extracting invariant local features and linking them according to a so-called proximity rule. The resulting graph presents several interesting properties including invariance to scale, robustness to various distortions and empirical linearity of the number of edges with respect to the number of nodes. The matching process is made hierarchical in order to increase both speed and detection performances. It relies on progressively incorporating the smaller model features as the hierarchy level increases. As a result, even a matching between graphs containing thousands of nodes is very fast (a few milliseconds). Experiments demonstrates that the method outperforms state-of-the-art specific object detectors in terms of precision-recall measures and detection time.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01381493
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Friday, October 14, 2016 - 2:46:55 PM
Last modification on : Thursday, November 21, 2019 - 2:35:43 AM

Links full text

Identifiers

Citation

Jérôme Revaud, Guillaume Lavoué, Yasuo Ariki, Atilla Baskurt. Scale-Invariant Proximity Graph for Fast Probabilistic Object Recognition. Conference on Image and Video Retrieval (CIVR), Jul 2010, Xi'an, China. pp.414-421, ⟨10.1145/1816041.1816102⟩. ⟨hal-01381493⟩

Share

Metrics

Record views

191