Accurately estimating rigid transformations in registration using a boosting-inspired mechanism

作者：

Highlights：

• We provide a novel method for evaluating point matches established by typical methods.

• Real data based experimental results show that the method outperforms the state-of-the-art.

• Under certain conditions, the finally estimated underlying transformation is optimal.

• The transformation can be recovered with an error as small as 5% from typical point matches.

摘要

Highlights•We provide a novel method for evaluating point matches established by typical methods.•Real data based experimental results show that the method outperforms the state-of-the-art.•Under certain conditions, the finally estimated underlying transformation is optimal.•The transformation can be recovered with an error as small as 5% from typical point matches.

论文关键词：Feature extraction,Feature matching,Point match evaluation,Boosting-inspired,Rigid underlying transformation

论文评审过程：Received 7 December 2015, Revised 4 May 2016, Accepted 6 July 2016, Available online 8 July 2016, Version of Record 22 July 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.011