Title :
Hyperspectral Face Recognition With Spatiospectral Information Fusion and PLS Regression
Author :
Uzair, Muhammad ; Mahmood, Arif ; Mian, Ajmal
Author_Institution :
Sch. of Comput. Sci. & Software Eng., Univ. of Western Australia, Crawley, WA, Australia
Abstract :
Hyperspectral imaging offers new opportunities for face recognition via improved discrimination along the spectral dimension. However, it poses new challenges, including low signal-to-noise ratio, interband misalignment, and high data dimensionality. Due to these challenges, the literature on hyperspectral face recognition is not only sparse but is limited to ad hoc dimensionality reduction techniques and lacks comprehensive evaluation. We propose a hyperspectral face recognition algorithm using a spatiospectral covariance for band fusion and partial least square regression for classification. Moreover, we extend 13 existing face recognition techniques, for the first time, to perform hyperspectral face recognition. We formulate hyperspectral face recognition as an image-set classification problem and evaluate the performance of seven state-of-the-art image-set classification techniques. We also test six state-of-the-art grayscale and RGB (color) face recognition algorithms after applying fusion techniques on hyperspectral images. Comparison with the 13 extended and five existing hyperspectral face recognition techniques on three standard data sets show that the proposed algorithm outperforms all by a significant margin. Finally, we perform band selection experiments to find the most discriminative bands in the visible and near infrared response spectrum.
Keywords :
data reduction; face recognition; image classification; image colour analysis; image fusion; least mean squares methods; regression analysis; PLS regression; RGB face recognition algorithms; ad hoc dimensionality reduction techniques; band fusion; band selection experiments; comprehensive evaluation; data dimensionality; discriminative bands; grayscale face recognition algorithms; hyperspectral face recognition algorithm; hyperspectral imaging; image-set classification problem; interband misalignment; near infrared response spectrum; partial least square regression; signal-to-noise ratio; spatiospectral covariance; spatiospectral information fusion; Databases; Face; Face recognition; Gray-scale; Hyperspectral imaging; Vectors; Hyperspectral imaging; face recognition; image set classification;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2015.2393057