An international conference connecting people
in CAD research, education and business
Copyright (C) CAD Solutions, LLC. All rights reserved.
Proceedings of CAD'16, 2016, 284-289
Fast Voxel-based Surface Propagation Method for Outlier Removal
Yu Chen, Rensselaer Polytechnic Institute Hao Chen, Shanghai University of Engineering Science Jie Shen, University of Michigan-Dearborn
Abstract. Outlier removal is an important problem in modern society. Related techniques have been widely used in a variety of fields: reverse engineering, rapid prototyping, biomedicine, architecture, entertainment industry, financial data analysis, etc. Many studies have been conducted to remove outliers effectively and efficiently. However, most of these methods perform well only in specific situations. Some methods are more suited to handling isolated outliers, and others are good in dealing with surfaces without sharp features. Shen, et al. proposed a surface propagation method combined with minimal variance and normalized histogram which performs well in both non-isolated outlier clusters and sharp edges. But, Shen’s method encounters an efficiency issue when dealing with large-scale data models. Wang and Feng further advanced Shen’s method by introducing a new method: majority voting.
Keywords. Surface Propagation, Laser Scanning, Data Outlier, Discrete Data Point