Sparsely Encoded Local Descriptor for face recognition
Sparsely Encoded Local Descriptor for face recognition
复制标题
DOI：
10.1109/fg.2011.5771389
复制
发表时间：
2011-03
期刊：
影响因子：
--
通讯作者：
Zhen Cui;S. Shan;Xilin Chen;Lei Zhang
中科院分区：
文献类型：
--
作者：
Zhen Cui;S. Shan;Xilin Chen;Lei Zhang
提出了一种新的稀疏编码局部描述符(SELD)用于人脸识别。与以往基于K-均值或随机投影树的方法相比，在字典学习和后续图像编码中引入了稀疏性约束，这意味着更稳定和更具区分性的人脸表示。稀疏编码还导致稀疏系数向量之和的图像描述符，这与现有的基于码字出现频率(/直方图)的描述符有很大不同。在FERET和Challenging LFW数据库上的大量实验表明了该方法的有效性。特别是在LFW数据集上，获得了可与最已知结果相媲美的识别精度。
In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictionary learning and sequent image encoding, which implies more stable and discriminative face representation. Sparse coding also leads to an image descriptor of summation of sparse coefficient vectors, which is quite different from existing code-words appearance frequency(/histogram)-based descriptors. Extensive experiments on both FERET and challenging LFW database show the effectiveness of the proposed SELD method. Especially on the LFW dataset, recognition accuracy comparable to the best known results is achieved.