Fast and Robust Image Matching using Contextual Information and Relaxation

Dro Desire Sidibe (1) , Philippe Montesinos (2) , Stefan Janaqi (2)

1 LHC - Laboratoire Hubert Curien
2 LGI2P - Laboratoire de Génie Informatique et Ingénierie de Production

This tackles the difficult problem of images matching under projective transformation. Recently, several algorithms capable of handling large changes of viewpoint as well as large changes of scale have been proposed. They are based on the comparison of local, invariant descriptors which are robust to these transformations. However, since no image descriptor is robust enough to avoid mismatches, an additional step of outliers rejection is often needed. The accuracy of which strongly depends on the number of mismatches. In this paper, we show that the matching process can be made robust to ensure a very few number of mismatches based on a relaxation labeling technique. The main contribution of this work is in providing an efficient and fast implementation of a relaxation method which can deal with large sets of features. Furthermore, we show how the contextual information can be obtained and used in this robust and fast algorithm. Experiments with real data and comparison with other matching methods, clearly show the improvements in the matching results.

Mots clés: Scale invariant features; points matching; image matching

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

Dro Desire Sidibe, Philippe Montesinos, Stefan Janaqi. Fast and Robust Image Matching using Contextual Information and Relaxation. VISAPP 07 - 2nd International Conference on Computer Vision Theory and Applications, Mar 2007, Barcelona, Spain. pp.68-75. ⟨ujm-00374332⟩