Hyperspectral Face Recognition with Patch-Based Low Rank Tensor Decomposition and PFFT Algorithm

Mengmeng Wu,Liren Zhang,Dongmei Wei,Yuefeng Zhao

doi:10.3390/sym10120714

Abstract

Hyperspectral imaging technology with sufficiently discriminative spectral and spatial information brings new opportunities for robust facial image recognition. However, hyperspectral imaging poses several challenges including a low signal-to-noise ratio (SNR), intra-person misalignment of wavelength bands, and a high data dimensionality. Many studies have proven that both global and local facial features play an important role in face recognition. This research proposed a novel local features extraction algorithm for hyperspectral facial images using local patch based low-rank tensor decomposition that also preserves the neighborhood relationship and spectral dimension information. Additionally, global contour features were extracted using the polar discrete fast Fourier transform (PFFT) algorithm, which addresses many challenges relevant to human face recognition such as illumination, expression, asymmetrical (orientation), and aging changes. Furthermore, an ensemble classifier was developed by combining the obtained local and global features. The proposed method was evaluated by using the Poly-U Database and was compared with other existing hyperspectral face recognition algorithms. The illustrative numerical results demonstrate that the proposed algorithm is competitive with the best CRC_RLS and PLS methods.

Highlights

Intra-person differences in terms of emotions, view point, illumination variations, and occlusion effects are still a challenging problem for face recognition tasks
It is necessary to research and develop an effective method for exploring the unexposed information rather than the structure and texture in a facial spatial domain. From this point of view, hyperspectral imaging (HSI) technology is considered as a technical solution since it provides the information beyond the human visible spectrum
The structure of a hyperspectral image is in a 3D data cube format that comprises of two spatial dimensions and one spectral dimension

Summary

Introduction

Intra-person differences in terms of emotions, view point, illumination variations, and occlusion effects are still a challenging problem for face recognition tasks. It is necessary to research and develop an effective method for exploring the unexposed information rather than the structure and texture in a facial spatial domain. From this point of view, hyperspectral imaging (HSI) technology is considered as a technical solution since it provides the information beyond the human visible spectrum. The structure of a hyperspectral image is in a 3D data cube format that comprises of two spatial dimensions and one spectral dimension. A hyperspectral image consists of tens to hundreds of bands, which increases the intra-face discrimination. The cause of the difference in spectral reflectance between the same points of inter-person (as an example of Figure 1) or intra-person

Methods

Results

Conclusion