Curve and surface reconstruction based on MTLS algorithm combined with k-means clustering

Curve and surface reconstruction methods play an important role in many research engineering fields. It is imperative procedure to carry out from measurement data reverse engineering, which complicated with the presence of outliers. To achieve better accuracy robustness reconstruction, improved moving total least squares (MTLS) algorithm based on k-means clustering called a KMTLS method proposed this article. Based MTLS, adjusts weight discrete points within support domain by adopting two-step fitting procedure. Firstly, ordinary (OLS) adopted obtain pre-fitting result calculate residuals as input clustering. In clustering, abnormal nodes are classified into one cluster function information introduced deal these nodes. Secondly, compact MTLS obtained procedure, weighted conducted determine final estimated value. The process detecting outliers automatic without setting threshold artificially. simulation experiment show that has great accuracy.