Non-rigid visible and infrared face registration via regularized Gaussian fields criterion
作者：
Highlights：
• We analyze the robustness of Gaussian fields criterion both in theory and experiment.
• The Gaussian fields criterion is generalized from rigid to the non-rigid case.
• We propose a new non-rigid registration method to deal with more real-world problems.
• A sparse approximation on the transformation is applied to speed up the method.
• We customize and apply the proposed method to visible/thermal IR face registration.
摘要
Highlights•We analyze the robustness of Gaussian fields criterion both in theory and experiment.•The Gaussian fields criterion is generalized from rigid to the non-rigid case.•We propose a new non-rigid registration method to deal with more real-world problems.•A sparse approximation on the transformation is applied to speed up the method.•We customize and apply the proposed method to visible/thermal IR face registration.
论文关键词：Registration,Image fusion,Infrared,Non-rigid,Face recognition,Gaussian fields
论文评审过程：Received 26 June 2014, Revised 15 August 2014, Accepted 8 September 2014, Available online 21 September 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.09.005
