Fuzzy correspondences guided Gaussian mixture model for point set registration

作者：

Highlights：

• The proposed fuzzy correspondences guided Gaussian mixture model for registration.

• Soft-assignment strategy is used to construct fuzzy correspondences.

• The proposed method is robust to data degradations and non-rigid transformation.

摘要

•The proposed fuzzy correspondences guided Gaussian mixture model for registration.•Soft-assignment strategy is used to construct fuzzy correspondences.•The proposed method is robust to data degradations and non-rigid transformation.

论文关键词：Point matching,Point set registration,Fuzzy correspondences,Mixture model,Kernel method

论文评审过程：Received 29 March 2017, Revised 9 September 2017, Accepted 11 September 2017, Available online 12 September 2017, Version of Record 4 October 2017.

论文官网地址：https://doi.org/10.1016/j.knosys.2017.09.016