A robust face recognition approach through symbolic modeling of Polar FFT features

作者：

Highlights：

• For the purpose of feature extraction, the proposed methodology uses a technique associated with fourier analysis in which the set of frequencies are equispaced when viewed in Polar coordinates.

• The work takes the advantage of symbolic modeling approach for better representation of extracted features.

• The performance of the proposed methodology has been evaluated by conducting various experiments on AR, ORL and LFW databases and the results are comparable to the state-of the art approaches available in the literature.

摘要

•In the proposed work a spectral domain feature extraction algorithm for novel appearance based face recognition technique is proposed, which effectively exploits the local spatial variations in a face image and deals with issues related to changes in illumination, expression and presence of occlusion during face recognition.•For the purpose of feature extraction, the proposed methodology uses a technique associated with fourier analysis in which the set of frequencies are equispaced when viewed in Polar coordinates.•The work takes the advantage of symbolic modeling approach for better representation of extracted features.•The performance of the proposed methodology has been evaluated by conducting various experiments on AR, ORL and LFW databases and the results are comparable to the state-of the art approaches available in the literature.

论文关键词：Symbolic data modeling and analysis,Polar-FFT,Face recognition,Viola–Jones

论文评审过程：Received 15 February 2017, Revised 2 June 2017, Accepted 7 June 2017, Available online 9 June 2017, Version of Record 12 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.014