Graph Structuring of Skeleton Object for Its High-Level Exploitation

Abstract

Abstract. 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 microarchitecture. We develop a solution for the extraction of structural and morphometric 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 microarchitecture characterization.

GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping

“…To address this, we incorporate an additional step that refines and thins the seam detection predictions. We use a relatively straightforward adaptation of the idea of skeletonization of graphs and images [Abu-Ain et al 2013;Youssef et al 2015]. This first requires the estimated edge probabilities to be converted to a probability value per vertex, which is simply the maximum probability of any edge incident on the vertex.…”

“…Moreover, the supervised nature of these algorithms enables the proposed method to reproduce similar styles on test objects, a feature that artists are always looking for. In addition, the translation of the distortion minimization task to the graph learning context allows us to propose a post-processing algorithm based on the Steiner tree problem [Sheffer and Hart 2002] and skeletonization [Abu-Ain et al 2013;Youssef et al 2015]. The post-processing step helps to produce seams that align with semantic boundaries and reduces the number of shells.…”

A novel sketch-based 3D model retrieval approach based on skeleton

“…However, their approach is only motivated by the visually similar skeleton graphs, without considering the topological graph structure. Youssef R et al [17] found that the graph representation algorithm is widely investigated regarding matching issues, due to the correspondence between skeleton branches with graph edges and nodes is natural and intuitive. However, the solutions in the literature are based on shock graphs [18] or attributed relational graphs [19] which are only used in certain application domains and usually with higher time complexity.…”

Artificial intelligent matching for scratches of semiconductor wafers based on a K-NN algorithm

“…In this paper, we match scratches without distinction based on skeletonization and KNN algorithm. In general, scratch maps are usually irregular pixels that do not have meaningful mathematical and geometrical interpretation, which could be extracted skeleton by [19,20]. And similar scratch segments are matched using the KNN algorithm.…”