An Mesh Segment Algorithm Based On Graph Cuts

Conference: ECITech 2022 - The 2022 International Conference on Electrical, Control and Information Technology
03/25/2022 - 03/27/2022 at Kunming, China

Proceedings: ECITech 2022

Pages: 7Language: englishTyp: PDF

Authors:
Xu, Chenyang (Intelligent Manufacturing Department Wu Yi University Jiangmen, China)
Ye, Xudong (Henan Institute of Advanced Technology Zhengzhou University Zhengzhou, China)
Peng, Wujie (Intelligent Manufacturing Department WuYi University Jiangmen, China)

Abstract:
In many computer vision applications, segmentation of 3D models is crucial. Many alternative segmentation algorithms have been proposed over the past several decades as a result of intensive study. Despite the fact that several automated segmentation algorithms have been presented, finding the relevant component of a mesh with precision is difficult. This study shows how to extract relevant elements from a triangle mesh using an interactive technique and an efficient algorithm. Min-cut, 2D image segmentation methods, is extended to the domain of 3D mesh in this work. It has an onscreen user interface that allows the user to quickly determine the important element. Our strategy is divided into two parts: 1) we simplify a big mesh using a quadric-based surface; 2) we employ min-cut in the simplified mesh. The prior cuts in the original mesh are then refined using graph cuts. The method was shown to be valid for mesh cutout in experiments.