Efficient 3D mesh salient region detection using local homogeneity measure

Sayed, Abdul Rahman El; Chakik, Abdallah El; Alabboud, Hassan; Yassine, Adnan

doi:10.1049/iet-ipr.2017.0598

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To define the neighboring set 𝐷 𝑛 (𝑣 𝑖 ) of a given vertex, we use the concept of Delaunay triangulation [10]. For a given 3D surface point represented by a graph vertex 𝑣 𝑖 , we construct circumscribed spheres that do not contain any other surface points inside them.…”

Section: A Surface Modeling and Normal Estimationmentioning

confidence: 99%

“…In this paper, we propose a robust curve-skeleton extraction method for 3D objects. We construct a Delaunay graph [10] from the initial data to ensure an efficient neighboring modeling relation. Then, we use a heuristic algorithm to compute discrete contours and construct spiral patches for vertices, representing the shortest self-loop from the vertex over the contour.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Curve-Skeleton Extraction from 3D Objects Using Spiral Patch

SAYED,

Chakik,

Samad

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The process of extracting a curve-skeleton from a 3D object is critical for various computer vision applications, including 3D object matching and recognition, 3D object segmentation, 3D animation, and 3D surface reconstruction. In this paper, we present a novel and efficient method for extracting the skeleton from general 3D objects based on a weight graph representation. Our method defines a unique spiral patch for each graph vertex, representing the shortest loop over the surface contour starting from the vertex. We construct a curve skeleton graph (CSG) using these spiral patches, which accurately represents the skeleton. We demonstrate the robustness of our method through various experiments, including noise reduction and different transformations. Furthermore, we showcase two practical applications based on our method: shape partitioning and gesture recognition. Our approach outperforms existing methods, demonstrating superior accuracy and efficiency. Overall, our proposed method presents a robust and efficient solution for extracting a curve-skeleton from general 3D objects, with promising applications in various computer vision fields.

show abstract

Section: A Surface Modeling and Normal Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%