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.
翻译:以图像梯度方向为基础的常规子空间学习方法仅采用第一级梯度定位法;然而,最近对人类视觉系统的研究发现,神经图像是一种景观或表面,可以通过第二级梯度信息捕捉到几何特性;第二级图像梯度定位法(SOIGO)可以减轻表面图像噪音的不利影响;为减少SOIGO的冗余,我们建议通过在SOIGO中应用线性复杂主要成分分析(PCA)来减少SOIGO(CSOIGO)的压缩。结合基于协作代表的分类算法,COSIGO的分类性能得到进一步加强。CSOIGO在真实世界伪装、合成隔离和混合变异的情况下进行了评估。实验结果表明,拟议方法优于与少数培训样本的竞争性方法,甚至优于某些普遍的深神经网络方法。COSIGO的源代码可在https://github.com/yinhefeng/SOIGO中查阅。