Face recognition in hyperspectral images

By Zhihong Pan, Glenn Healey, Manish Prasad, Bruce J. Tromberg. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003

440 citations recorded by the source corpus.

Hyperspectral cameras provide useful discriminants for human face recognition that cannot be obtained by other imaging methods. We examine the utility of using near-infrared hyperspectral images for the recognition of faces over a database of 200 subjects. The hyperspectral images were collected using a CCD camera equipped with a liquid crystal tunable filter. Spectral measurements over the near-infrared allow the sensing of subsurface tissue structure, which is significantly different from person to person but relatively stable over time. The local spectral properties of human tissue are nearly invariant to face orientation and expression, which allows hyperspectral discriminants to be used for recognition over a large range of poses and expressions. We describe a face recognition algorithm that exploits spectral measurements for multiple facial tissue types. We demonstrate experimentally that this algorithm can be used to recognize faces over time in the presence of changes in facial pose and expression.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/8a429d46533d82d8999da15a8a7daec4049957fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

2D and 3D face recognition: A survey (2007, methodology): “Indeed, in (Pan et al., 2003) such a technique based on the hyperspectral images has been applied on a database of 200 subjects, which has been acquired under different pose, expression and illumination conditions.”
A Physical Model of Human Skin and its Application for Search and Rescue (2012, background): “For example, the spectral signature of skin on the face provides a pose-invariant feature for use in these algorithms [62].”
Multispectral Imaging Using Multiplexed Illumination (2007, methodology): “Multispectral imaging has been used for color analysis, color constancy, object recognition, and the analysis of works of art (for examples, see [1, 17, 6].”
Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “Hyperspectral imaging has been recently applied in many computer vision tasks, including the tracking [19], face recognition[20] and segmentation[28].”
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction (2021, background): “, remote sensing [5, 31, 42, 60], object tracking [19, 37, 38], medical image processing [3,30,34], etc.”
Hyperspectral Super-Resolution by Coupled Spectral Unmixing (2015, neutral): “This capability has proved useful for visual tasks such as tracking [23] and segmentation [22], in applications including face recognition [19], document analysis [18], food inspection [26] and earth observation [6].”
HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images (2018, background): “In recent years, the hyperspectral image begins to be applied to various computer vision tasks, such as image segmentation, face recognition, and object tracking [31, 28, 33].”
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (2022, background): “Because of this advantage, HSIs have wide applications such as medical image processing [8, 51, 57], remote sensing [10,54,82], object tracking [35,61], and so * Equal Contribution, † Corresponding Author The horizontal axis is FLOPS (computational complexity), the vertical axis is PSNR (…”
Hyperspectral Imaging Applications in Agriculture and Agro-Food Product Quality and Safety Control: A Review (2013, methodology): “The technique has been used in the medical sector to determine various diseases, such as peripheral vascular diseases (23), and in ophthalmology and oncology (24), immunohistochemistry (25), latent fingerprinting and age assessment of bruises in forensic medicine (26), and face recognition in biomed”
Illumination Invariant Face Recognition Using Near-Infrared Images (2007, background): “The use of near infrared (NIR) imaging brings a new dimension for face detection and recognition [41], [42], [43].”
A survey of skin-color modeling and detection methods (2007, background): “Many of the problems encountered in visual spectrum can be overcome by using non-visual spectrum such as infrared (IR) [5] [6] and spectral imaging [7] [8] [9].”