Multilinear Supervised Neighborhood Embedding with Local Descriptor Tensor for Face Recognition
Multilinear Supervised Neighborhood Embedding with Local Descriptor Tensor for Face Recognition
复制标题
DOI：
10.1587/transinf.e94.d.158
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
X. Han;Xu Qiao;Yenwei Chen
中科院分区：
文献类型：
--
作者：
X. Han;Xu Qiao;Yenwei Chen
近年来，基于子空间学习的人脸识别方法引起了人们的极大兴趣，包括主成分分析（PCA）、独立成分分析（伊卡）、线性判别分析（LDA）以及二维分析的一些扩展。然而，所有这些方法的缺点是，它们直接对像素级强度的整形向量或矩阵执行子空间分析，这通常在光照或姿态变化下是不稳定的。在本文中，我们提出了一个局部描述符张量，这是在图像中的局部区域（K* K像素补丁）的描述符的组合表示的人脸图像，是更有效的比流行的袋特征（BOF）模型的局部描述符组合。此外，我们建议使用多线性子空间学习算法（监督邻域嵌入-SNE）的判别特征提取的局部描述符张量的人脸图像，它可以保持局部样本结构的特征空间。在Yale和PIE数据库上进行了实验验证，实验结果表明，与传统的子空间分析方法相比，该方法的识别率有了很大的提高，尤其是在训练样本较少的情况下。
Subspace learning based face recognition methods have attracted considerable interest in recent years, including Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA), and some extensions for 2D analysis. However, a disadvantage of all these approaches is that they perform subspace analysis directly on the reshaped vector or matrix of pixel-level intensity, which is usually unstable under illumination or pose variance. In this paper, we propose to represent a face image as a local descriptor tensor, which is a combination of the descriptor of local regions (K*K-pixel patch) in the image, and is more efficient than the popular Bag-Of-Feature (BOF) model for local descriptor combination. Furthermore, we propose to use a multilinear subspace learning algorithm (Supervised Neighborhood Embedding-SNE) for discriminant feature extraction from the local descriptor tensor of face images, which can preserve local sample structure in feature space. We validate our proposed algorithm on Benchmark database Yale and PIE, and experimental results show recognition rate with our method can be greatly improved compared conventional subspace analysis methods especially for small training sample number.