Optical flow with structure information for epithelial image mosaicing

Sharib Ali (1, 2) , Khuram Faraz (1, 2) , Christian Daul (1, 2) , Walter C.P.M. Blondel (1, 2)

1 CRAN - Centre de Recherche en Automatique de Nancy
2 UL - Université de Lorraine

Mosaicing of biological tissue surfaces is challenging due to the weak image textures. This contribution presents a mosaicing algorithm based on a robust and accurate variational optical flow scheme. A Riesz pyramid based multi-scale approach aims at overcoming the “flattening-out” problem at coarser levels. Moreover, the structure information present in images of epithelial surfaces is incorporated into the data-term to improve the algorithm robustness. The algorithm accuracy is first assessed with simulated sequences and then used for mosaicing standard clinical endoscopic data.

Mots clés: Bladder image mosaicing; skin image mosaicing; optical flow; wavelets

Domaines: Traitement des images [eess.IV]; Imagerie médicale; Logiciel mathématique [cs.MS]; Robotique [cs.RO]; Optimisation et contrôle [math.OC]

Sharib Ali, Khuram Faraz, Christian Daul, Walter C.P.M. Blondel. Optical flow with structure information for epithelial image mosaicing. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Aug 2015, Milano, Italy. ⟨hal-01184618⟩