Face recognition using localized features based on non-negative sparse coding
Face recognition using localized features based on non-negative sparse coding
复制标题
DOI：
10.1007/s00138-006-0052-0
复制
发表时间：
2007-04
影响因子：
3.3
通讯作者：
B. Shastri;M. Levine
中科院分区：
文献类型：
--
作者：
B. Shastri;M. Levine
视觉系统中的神经网络可能对学习到的局部特征进行稀疏编码，这些特征在质量上与初级视觉皮层V1中简单细胞的接受野非常相似。在传统的稀疏编码中，数据被描述为包含加法和减法分量的基本特征的组合。然而，使用减法可以“相互抵消”的事实与将部分组合成整体的直观概念相反。因此，最近人们强烈主张完全非负面表征。本文将非负稀疏编码（NNSC）应用于人脸识别的人脸特征学习，并与其他基于部分的非负矩阵分解（NMF）和局部非负矩阵分解（LNMF）技术进行了比较。NNSC方法已分别在alex - robert （AR）、人脸识别技术（FERET）、耶鲁B和剑桥ORL数据库上进行了测试。在此过程中，我们比较和评估了不同表情、不同光照、太阳镜遮挡、围巾遮挡和不同姿势下的NNSC人脸识别技术。试验采用不同的距离度量，如thel1度量、l2度量和归一化相互关系（NCC）。所有这些实验都涉及到大范围的基本维度。总的来说，NNSC是三种基于部分的方法中的最佳方法，但必须注意的是，不同实验的最佳距离度量并不一致。
Neural networks in the visual system may be performing sparse coding of learnt local features that are qualitatively very similar to the receptive fields of simple cells in the primary visual cortex, V1. In conventional sparse coding, the data are described as a combination of elementary features involving both additive and subtractive components. However, the fact that features can ‘cancel each other out’ using subtraction is contrary to the intuitive notion of combining parts to form a whole. Thus, it has recently been argued forcefully for completely non-negative representations. This paper presents Non-Negative Sparse Coding (NNSC) applied to the learning of facial features for face recognition and a comparison is made with the other part-based techniques, Non-negative Matrix Factorization (NMF) and Local-Non-negative Matrix Factorization (LNMF). The NNSC approach has been tested on the Aleix–Robert (AR), the Face Recognition Technology (FERET), the Yale B, and the Cambridge ORL databases, respectively. In doing so, we have compared and evaluated the proposed NNSC face recognition technique under varying expressions, varying illumination, occlusion with sunglasses, occlusion with scarf, and varying pose. Tests were performed with different distance metrics such as theL1-metric,L2-metric, and Normalized Cross-Correlation (NCC). All these experiments involved a large range of basis dimensions. In general, NNSC was found to be the best approach of the three part-based methods, although it must be observed that the best distance measure was not consistent for the different experiments.