Human identification based on temporal lifting using 5/3 wavelet filters and radon transform

作者：

Highlights：

• A spatio-temporal gait recognition system is proposed.

• A gait template approach (5/3GI) based on lifting 5/3 wavelet filters is introduced.

• Radon transform is performed on the generated temporal templates.

• PCA is utilized on Radon templates to reduce the dimensionality of feature vectors.

• The system achieves better performance compared with the recently published approaches.

摘要

•A spatio-temporal gait recognition system is proposed.•A gait template approach (5/3GI) based on lifting 5/3 wavelet filters is introduced.•Radon transform is performed on the generated temporal templates.•PCA is utilized on Radon templates to reduce the dimensionality of feature vectors.•The system achieves better performance compared with the recently published approaches.

论文关键词：Gait recognition,Principal component analysis (PCA),Radon transform,Lifting,Wavelet transform

论文评审过程：Received 5 February 2015, Revised 10 April 2017, Accepted 13 April 2017, Available online 14 April 2017, Version of Record 28 April 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.015