计算机科学 ›› 2018, Vol. 45 ›› Issue (4): 285-290.doi: 10.11896/j.issn.1002-137X.2018.04.048
李小薪,李晶晶,贺霖,刘志勇
LI Xiao-xin, LI Jing-jing, HE Lin and LIU Zhi-yong
摘要： 基于核范数的矩阵回归方法(Nuclear norm based Matrix Regression,NMR)对人脸图像中因遮挡和光照变化等噪声引发的误差具有很强的鲁棒性。分析了NMR的鲁棒性的基本原理:首先,误差的核范数度量的是误差在其主方向上的能量,而主方向上的能量通常都去除了常规噪声的干扰；其次,误差的核范数度量嵌入了噪声的空间结构信息,而噪声的空间结构对于表示并排除噪声的影响至关重要。然而,仅仅考虑噪声的空间结构并不能有效消除噪声的影响。将具有噪声抑制能力的高维梯度方向(High-dimensional Gradient Orientation,HGO)特征嵌入NMR,提出了 一种基于高维梯度方向特征的NMR方法(High-dimensional Gradient Orientations-based NMR,HGO-NMR)极大地提升了NMR的识别性能。其重要意义在于指出噪声空间结构信息和噪声抑制机制对于面向现实的鲁棒人脸识别系统同等重要,单方面强调其中任何一种机制都将导致不稳定的识别性能。
| [1] WRIGHT J,YANG A Y,GANESH A,et al.Robust Face Re-cognition Via Sparse Representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227. [2] YANG J,LUO L,QIAN J,et al.Nuclear Norm Based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(1):156-171. [3] YANG M,ZHANG L,SHIU S C,et al.Gabor Feature Based Robust Representation and Classification for Face Recognition with Gabor Occlusion Dictionary [J].Pattern Recognition,2013,46(7):1865-1878. [4] ZHANG L,YANG M,FENG X.Sparse Representation or Collaborative Representation:Which Helps Face Recognition?[C]∥Proceedings of IEEE International Conference on Computer Vision.2011:471-478. [5] LUO L,YANG J,QIAN J,et al.Nuclear-L1 Norm Joint Regression for Face Reconstruction and Recognition with Mixed Noise [J].Pattern Recognition,2015,48(12):3811-3824. [6] QIAN J,LUO L,YANG J,et al.Robust Nuclear Norm Regulari-zed Regression for Face Recognition with Occlusion [J].Pattern Recognition,2015,48(10):3145-3159. [7] WRIGHT J,GANESH A,RAO S,et al.Robust Principal Component Analysis:Exact Recovery of Corrupted Low-Rank Matrices Via Convex Optimization[C]∥Proceedings of Advances in Neural Information Processing Systems.Curran Associates,Inc.,2009:2080-2088. [8] CANDES E J,LI X,MA Y,et al.Robust Principal Component Analysis? [J].Journal of the ACM,2011,58(31):1-73. [9] KIM W,SUH S,HWANG W,et al.Svd Face:Illumination-Invariant Face Representation [J].IEEE Signal Processing Letters,2014,21(11):1336-1340. [10] LI X,DAI D,ZHANG X,et al.Structured Sparse Error Coding for Face Recognition with Occlusion [J].IEEE Transactions on Image Processing,2013,22(5):1889-1900. [11] WEI X,LI C,HU Y.Robust Face Recognition Under Varying Illumination and Occlusion Considering Structured Sparsity[C]∥International Conference on Digital Image Computing Techniques and Applications.2012:1-7. [12] JIA K,CHAN T H,MA Y.Robust and Practical Face Recognition Via Structured Sparsity[C]∥European Conference on Computer Vision.2012:331-344. [13] TZIMIROPOULOS G,ZAFEIRIOU S,PANTIC M.SubspaceLearning From Image Gradient Orientations [J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2012,34(12):2454-2466. [14] ZHANG T,TANG Y Y,FANG B,et al.Face Recognition under Varying Illumination Using Gradientfaces [J].IEEE Transactions on Image Processing,2009,18(11):2599-2606. |
| No related articles found! |
|
||
首页