Robust curve and surface reconstruction method based on clustering algorithm

Tianqi Gu, Hongxin Lin, Jianxiong Chen, Dawei Tang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Surface reconstruction method plays an important role in many engineering fields. It is an imperative procedure to carry out surface reconstruction from measurement data in reverse engineering, which is complicated with the presence of outliers. To achieve better accuracy and robustness of reconstruction, an improved moving total least squares (MTLS) algorithm based on k-means clustering called KMTLS method is proposed in this article. KMTLS adjusts the weights of discrete points within the support domain by adopting a two-step fitting procedure. Firstly, ordinary least squares (OLS) method is adopted to obtain the pre-fitting result and calculate the residuals as the input of k-means clustering. In kmeans clustering, abnormal nodes are classified into one cluster and a weight function based on clustering information is introduced to deal with these nodes. Secondly, based on the compact weight function in MTLS and the weight obtained in the pre-fitting procedure, weighted total least squares method is conducted to determine the final estimated value. The process of detecting outliers is automatic without setting threshold artificially. The experiment shows that KMTLS has great robustness to outliers.
Original languageEnglish
Title of host publicationProceedings of The 7th Asia Pacific Conference on Optics Manufacture(APCOM2021)
EditorsJiubin Tan, Xiangang Luo, Ming Huang, Lingbao Kong, Dawei Zhang
Number of pages6
ISBN (Electronic)9781510652095
ISBN (Print)9781510652088
Publication statusPublished - 15 Feb 2022
EventThe 7th Asia Pacific Conference on Optics Manufacture - Shanghai, China
Duration: 13 Aug 202116 Aug 2021

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceThe 7th Asia Pacific Conference on Optics Manufacture
Abbreviated titleAPCOM 2021


Dive into the research topics of 'Robust curve and surface reconstruction method based on clustering algorithm'. Together they form a unique fingerprint.

Cite this