A Data-Driven Approach to Feature Space Selection for Robust Micro-Endoscopic Image Reconstruction

Pascal Bourdon (1, 2) , David Helbert (1, 2)

1 XLIM-ASALI - Synthèse et analyse d'images
2 UP - Université de Poitiers = University of Poitiers

In the article we propose a new, on-line feature space selection strategy for displacement field estimation in the context of multi-view reconstruction of biological images acquired by a multi-photon micro-endoscope. While the high variety of targets encountered in clinical endoscopy induce enough texture feature variability to prohibit the use of recent supervised learning or feature matching-based visual tracking methods, we will show how on-line learning combined with a classical method such as Digital Image Correlation (DIC) can contribute to the improvement of convex optimization-based template matching techniques.

Mots clés: Medical imaging; optical flow; microendoscopy; image mosaicing

Domaines: Traitement du signal et de l'image [eess.SP]

Pascal Bourdon, David Helbert. A Data-Driven Approach to Feature Space Selection for Robust Micro-Endoscopic Image Reconstruction. IEEE International Conference on Image Processing (ICIP), Sep 2017, Beijing, China. pp.2239-2243, ⟨10.1109/ICIP.2017.8296680⟩. ⟨hal-01519837⟩