Geometric decomposition of 3D surface meshes using Morse theory and region growing

被引:11
作者
Wang, Jun [1 ]
Yu, Zeyun [1 ]
机构
[1] Univ Wisconsin, Dept Comp Sci, Milwaukee, WI 53211 USA
关键词
Surface decomposition; Mesh segmentation; Curvature labeling; Morse theory; Critical point; Region growing; SEGMENTATION; CURVATURE;
D O I
10.1007/s00170-011-3259-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper presents a new algorithm for decomposition (segmentation) of surfaces using curvature labeling, Morse theory, and region growing technologies. The geometric properties are estimated on triangular meshes and all mesh elements (vertices and triangles) are labeled with different surface types. The surface decomposition method proposed consists of two steps: initial segmentation and refinement. The initial segmentation is performed by grouping the topologically adjacent mesh elements with the same surface type using the region growing technique. A Morse function is then defined based on the smoothed curvatures using bilateral filtering to extract the critical points of a triangular surface mesh. The final segmentation is obtained by a combination of the steepest ascent/descent strategy and region growing technique. The experimental results on many 3D models, particularly molecular surfaces, have demonstrated the effectiveness and robustness of the proposed segmentation method.
引用
收藏
页码:1091 / 1103
页数:13
相关论文
共 50 条
[31]   Dense graph convolutional neural networks on 3D meshes for 3D object segmentation and classification [J].
Tang, Wenming ;
Qiu, Guoping .
IMAGE AND VISION COMPUTING, 2021, 114
[32]   Neural implicit surface reconstruction of freehand 3D ultrasound volume with geometric constraints [J].
Chen, Hongbo ;
Kumaralingam, Logiraj ;
Zhang, Shuhang ;
Song, Sheng ;
Zhang, Fayi ;
Zhang, Haibin ;
Pham, Thanh-Tu ;
Punithakumar, Kumaradevan ;
Lou, Edmond H. M. ;
Zhang, Yuyao ;
Le, Lawrence H. ;
Zheng, Rui .
MEDICAL IMAGE ANALYSIS, 2024, 98
[33]   Geometric segmentation of 3D scanned surfaces [J].
Di Angelo, Luca ;
Di Stefano, Paolo .
COMPUTER-AIDED DESIGN, 2015, 62 :44-56
[34]   MeT: A graph transformer for semantic segmentation of 3D meshes [J].
Vecchio, Giuseppe ;
Prezzavento, Luca ;
Pino, Carmelo ;
Rundo, Francesco ;
Palazzo, Simone ;
Spampinato, Concetto .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 235
[35]   Robust detection of perceptually salient features on 3D meshes [J].
Mao Zhihong ;
Cao Guo ;
Zhao Mingxi .
VISUAL COMPUTER, 2009, 25 (03) :289-295
[36]   An A* Algorithm for Extracting Feature Curves from 3D Meshes [J].
Min, Kyungha .
CONVERGENCE AND HYBRID INFORMATION TECHNOLOGY, 2012, 310 :393-400
[37]   A hybrid method based on level set and 3D region growing for segmentation of the thoracic aorta [J].
Antonio Martinez-Mera, Juan ;
Tahoces, Pablo G. ;
Carreira, Jose M. ;
Juan Suarez-Cuenca, Jorge ;
Souto, Miguel .
COMPUTER AIDED SURGERY, 2013, 18 (5-6) :109-117
[38]   Automatic 3D Segmentation of Lung Airway Tree: A Novel Adaptive Region Growing Approach [J].
Lai, Kai ;
Zhao, Peng ;
Huang, Yufeng ;
Liu, Junwei ;
Wang, Chang ;
Feng, Huanqing ;
Li, Chuanfu .
2009 3RD INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICAL ENGINEERING, VOLS 1-11, 2009, :2195-+
[39]   3D segmentation of medical image using the geometric active contour model [J].
Jang, DP ;
Cho, YH ;
Kim, SI .
MEDICAL IMAGING 1999: IMAGE PROCESSING, PTS 1 AND 2, 1999, 3661 :957-967
[40]   Robust normal estimation and region growing segmentation of infrastructure 3D point cloud models [J].
Khaloo, Ali ;
Lattanzi, David .
ADVANCED ENGINEERING INFORMATICS, 2017, 34 :1-16