Hyperspectral Face Recognition With Spatiospectral Information Fusion and PLS Regression
Hyperspectral Face Recognition With Spatiospectral Information Fusion and PLS Regression
复制标题
DOI：
10.1109/tip.2015.2393057
复制
发表时间：
2015-03-01
影响因子：
10.6
通讯作者：
Mian, Ajmal
中科院分区：
文献类型：
--
作者：
Uzair, Muhammad;Mahmood, Arif;Mian, Ajmal
高光谱成像通过改善光谱维度的分辨率，为人脸识别提供了新的机会。然而，它也带来了新的挑战，包括低信噪比、带间不对准和高维数据。由于这些挑战，关于高光谱人脸识别的文献不仅稀少，而且局限于自组织降维技术，缺乏全面的评价。提出了一种基于空间谱协方差进行波段融合和偏最小二乘回归分类的高光谱人脸识别算法。此外，我们还首次扩展了13种现有的人脸识别技术，以进行高光谱人脸识别。我们将高光谱人脸识别描述为一个图像集分类问题，并对七种最新的图像集分类技术的性能进行了评估。在高光谱图像上应用融合技术后，我们还测试了六种最先进的灰度和RGB(彩色)人脸识别算法。在三个标准数据集上与13种扩展高光谱人脸识别技术和5种现有高光谱人脸识别技术进行了比较，结果表明，该算法的识别性能明显优于现有的5种高光谱人脸识别技术。最后，我们进行了波段选择实验，找出了可见光和近红外响应光谱中最具区分性的波段。
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.