Graph Structuring of Skeleton Object for Its High-Level Exploitation

Rabaa Youssef (1, 2) , Anis Kacem (3) , Sylvie Sevestre-Ghalila (1) , Christine Chappard (4)

1 CEA-LinkLab
2 COSIM-Laboratoire Communication, Signaux et Images
3 Institut TELECOM/TELECOM Lille1
4 B2OA (UMR_7052) - Bioingénierie et Bioimagerie Ostéo-articulaires ; Biomécanique et Biomatériaux Ostéo-Articulaires

Skeletonization is a morphological operation that summarizes an object by its median lines while preserving the initial image topology. It provides features used in biometric for the matching process, as well as medical imaging for quantification of the bone microarchitec-ture. We develop a solution for the extraction of structural and morpho-metric features useful in biometric, character recognition and medical imaging. It aims at storing object descriptors in a re-usable and hierarchical format. We propose graph data structures to identify skeleton nodes and branches, link them and store their corresponding features. This graph structure allows us to generate CSV files for high level analysis and to propose a pruning method that removes spurious branches regarding their length and mean gray level. We illustrate manipulations of the skeleton graph structure on medical image dedicated to bone mi-croarchitecture characterization.

Domaines: Imagerie médicale; Traitement des images [eess.IV]

Rabaa Youssef, Anis Kacem, Sylvie Sevestre-Ghalila, Christine Chappard. Graph Structuring of Skeleton Object for Its High-Level Exploitation. 12th International Conference on Image Analysis and Recognition (ICIAR 2015), Jul 2015, Niagara Falls, ON, Canada. pp.419 - 426, ⟨10.1007/978-3-319-20801-5_46⟩. ⟨hal-01436778⟩