Biologically Inspired Tensor Features
Biologically Inspired Tensor Features
复制标题
DOI：
10.1007/s12559-009-9028-5
复制
发表时间：
2009-11
影响因子：
5.4
通讯作者：
Yang Mu;D. Tao;Xuelong Li;F. Murtagh
中科院分区：
文献类型：
--
作者：
Yang Mu;D. Tao;Xuelong Li;F. Murtagh
根据过去几十年的研究成果，人脸识别并不是一项简单的任务。随着电子设备的发展，我们正在逐步揭示灵长类动物视觉皮层中物体识别的秘密。因此，现在是时候重新考虑使用生物启发特征进行人脸识别了。在本文中，我们表示人脸图像，利用C1单位，这对应于复杂的细胞在视觉皮层，和池超过S1单位，使用最大值操作，以保留只有最大的反应，每个局部地区的S1单位。新的表示被称为C1面。由于C1 Face本质上是一个三阶张量（或三维数组），因此我们提出了三路判别局部对齐（TWDLA），这是判别局部对齐的扩展，是一种基于顶级判别流形学习的子空间学习算法。TWDLA具有以下优点：（1）它直接以三阶张量作为输入，可以很好地保留输入张量的结构信息;（2）它对输入张量的每一个模态进行局部几何建模，可以保留输入张量在一个类内的空间关系;（3）它最大化了每个模态上张量和其他类张量之间的裕度，因此它在识别任务中表现良好，以及（4）不存在采样不足的问题。在YALE和FERET数据集上进行的大量实验表明：（1）提出的C1 Face表示比原始像素更好地表示人脸图像;（2）TWDLA可以适当地保留每种识别方式的局部几何形状和区分信息。
According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate’s visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition.