3D mesh model segmentation based on skeleton extraction

ABSTRACT

In order to solve the problem of low segmentation accuracy of 3D mesh models, a non-deep learning method based on skeleton extraction is proposed. First, the skeleton of the model is extracted. Then, the skeleton feature points are extracted by analysing the relationship between the skeleton data. The feature point with the smallest distance from the centroid in the same neighbourhood is selected as the segmentation point. Finally, based on the improved region-based algorithm, the segmented skeleton region is obtained with the segmentation points as the seeds, and the corresponding original data is segmented through inverse mapping. The experimental results show that compared with the existing non-deep learning methods, the proposed method can obtain better semantic separation results and segmentation boundaries.

KEYWORDS:

• Model segmentation
• skeleton extraction
• feature points
• regional growth

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The work was supported by the National Natural Science Foundation of China [grant number 62106238].

Notes on contributors

Huiyan Han

Huiyan Han, Ph.D., as an associate professor, her research interests include artificial intelligence, signal processing, virtual simulation.

Xie Han

Xie Han, Ph.D. as a professor, her research interests include computer vision, simulation, and visualization.

Tianyi Gao

Tianyi Gao is pursuing the master degree in computer science and technology, North University of China.