AMIFT: AFFINE-MIRROR INVARIANT FEATURE TRANSFORM

Noureddine Mohtaram (1) , Amina Radgui (1) , Guillaume Caron (2) , El Mustapha Mouaddib (2)

1 GSCM-LRIT - Laboratoire de Recherche en Informatique et Télécommunications [Rabat]
2 MIS - Modélisation, Information et Systèmes - UR UPJV 4290

In this paper, we propose a descriptor for image matching under multiple mirror reflections. Indeed, existing adaptations of SIFT for the mirror transformation are not successful when object and mirrors orientations are not constrained. Hence, we propose to combine MIFT and Affine-SIFT descriptors as the Affine Mirror Invariant Feature Transform (AMIFT). The experimental results and given evaluation show that our proposed descriptor outperforms MIFT and ASIFT on both synthetic and real images datasets.

Mots clés: SIFT; Affine transformation; local features; reflection invariant feature

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

Noureddine Mohtaram, Amina Radgui, Guillaume Caron, El Mustapha Mouaddib. AMIFT: AFFINE-MIRROR INVARIANT FEATURE TRANSFORM. IEEE International Conference on Image Processing, ICIP, Oct 2018, Athènes, Greece. ⟨hal-01907307⟩