论文标题
通过紧凑的二阶图像梯度方向识别面部识别
Face recognition via compact second order image gradient orientations
论文作者
论文摘要
基于图像梯度方向的常规子空间学习方法仅采用一阶梯度信息。但是，最近对人类视觉系统（HVS）的研究发现了神经图像是景观或表面，其几何特性可以通过二阶梯度信息捕获。二阶图像梯度方向（SOIGO）可以减轻脸部图像中噪声的不利影响。为了降低Soigo的冗余，我们通过在Soigo中应用线性复杂的主成分分析（PCA）提出紧凑的Soigo（CSOIGO）。结合基于协作表示的分类（CRC）算法，CSOIGO的分类性能进一步增强。在现实世界中的伪装，合成的遮挡和混合变化下评估CSOIGO。实验结果表明，所提出的方法在很少的训练样本中优于其竞争方法，甚至超过了一些普遍的基于神经网络的方法。 CSOIGO的源代码可从https://github.com/yinhefeng/soigo获得。
Conventional subspace learning approaches based on image gradient orientations only employ the first-order gradient information. However, recent researches on human vision system (HVS) uncover that the neural image is a landscape or a surface whose geometric properties can be captured through the second order gradient information. The second order image gradient orientations (SOIGO) can mitigate the adverse effect of noises in face images. To reduce the redundancy of SOIGO, we propose compact SOIGO (CSOIGO) by applying linear complex principal component analysis (PCA) in SOIGO. Combined with collaborative representation based classification (CRC) algorithm, the classification performance of CSOIGO is further enhanced. CSOIGO is evaluated under real-world disguise, synthesized occlusion and mixed variations. Experimental results indicate that the proposed method is superior to its competing approaches with few training samples, and even outperforms some prevailing deep neural network based approaches. The source code of CSOIGO is available at https://github.com/yinhefeng/SOIGO.
