Segmentation of elongated objects using attribute profiles and area stability: application to melanocyte segmentation.

Andrés Serna (1) , Beatriz Marcotegui (1) , Etienne Decencière (1) , Thérese Baldeweck (2) , Ana-Maria Pena (2) , Sébastien Brizion (2)

1 CMM - Centre de Morphologie Mathématique
2 L’Oréal Recherche & Innovation

In this paper, a method to segment elongated objects is proposed. It is based on attribute profiles and area stability. Images are represented as component trees using a threshold decomposition. Then, some attributes are computed on each node of the tree. Finally, the attribute profile is analyzed to identify important events useful for segmentation tasks. In this work, a new attribute, combining geodesic elongation and area stability is defined. This methodol-ogy is successfully applied to the segmentation of cells in multiphoton fluores-cence microscopy images of engineered skin. Quantitative results are provided, demonstrating the performance and robustness of the new attribute. A compar-ison with MSER is also given.

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

Andrés Serna, Beatriz Marcotegui, Etienne Decencière, Thérese Baldeweck, Ana-Maria Pena, et al.. Segmentation of elongated objects using attribute profiles and area stability: application to melanocyte segmentation.. Pattern Recognition Letters, 2014, 10.1016/j.patrec.2014.03.014. ⟨hal-01101643⟩