Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China.
IEEE Trans Image Process. 2010 Jun;19(6):1635-50. doi: 10.1109/TIP.2010.2042645. Epub 2010 Feb 17.
Making recognition more reliable under uncontrolled lighting conditions is one of the most important challenges for practical face recognition systems. We tackle this by combining the strengths of robust illumination normalization, local texture-based face representations, distance transform based matching, kernel-based feature extraction and multiple feature fusion. Specifically, we make three main contributions: 1) we present a simple and efficient preprocessing chain that eliminates most of the effects of changing illumination while still preserving the essential appearance details that are needed for recognition; 2) we introduce local ternary patterns (LTP), a generalization of the local binary pattern (LBP) local texture descriptor that is more discriminant and less sensitive to noise in uniform regions, and we show that replacing comparisons based on local spatial histograms with a distance transform based similarity metric further improves the performance of LBP/LTP based face recognition; and 3) we further improve robustness by adding Kernel principal component analysis (PCA) feature extraction and incorporating rich local appearance cues from two complementary sources--Gabor wavelets and LBP--showing that the combination is considerably more accurate than either feature set alone. The resulting method provides state-of-the-art performance on three data sets that are widely used for testing recognition under difficult illumination conditions: Extended Yale-B, CAS-PEAL-R1, and Face Recognition Grand Challenge version 2 experiment 4 (FRGC-204). For example, on the challenging FRGC-204 data set it halves the error rate relative to previously published methods, achieving a face verification rate of 88.1% at 0.1% false accept rate. Further experiments show that our preprocessing method outperforms several existing preprocessors for a range of feature sets, data sets and lighting conditions.
在不受控光照条件下提高识别的可靠性是实用人脸识别系统的最重要挑战之一。我们通过结合鲁棒光照归一化、基于局部纹理的人脸表示、基于距离变换的匹配、基于核的特征提取和多种特征融合的优势来解决这个问题。具体来说，我们做出了三个主要贡献：1）我们提出了一个简单而有效的预处理链，该链消除了大部分变化光照的影响，同时仍然保留了识别所需的基本外观细节；2）我们引入了局部三元模式（LTP），这是局部二值模式（LBP）的推广，它在均匀区域中具有更强的判别力和对噪声的敏感性更小，并且我们表明，用基于距离变换的相似性度量代替基于局部空间直方图的比较进一步提高了基于 LBP/LTP 的人脸识别的性能；3）我们通过添加核主成分分析（PCA）特征提取并从两个互补来源——Gabor 小波和 LBP——中加入丰富的局部外观线索，进一步提高了鲁棒性，表明组合比任何单个特征集都更准确。所得到的方法在三个广泛用于测试困难光照条件下识别的数据集上提供了最新的性能：扩展耶鲁-B、CAS-PEAL-R1 和人脸识别大挑战版本 2 实验 4（FRGC-204）。例如，在具有挑战性的 FRGC-204 数据集上，它将错误率相对于先前发布的方法减半，在 0.1%的错误接受率下实现了 88.1%的人脸验证率。进一步的实验表明，我们的预处理方法在多种特征集、数据集和光照条件下优于几种现有的预处理器。
