Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild

Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
复制标题

DOI:
10.1109/cvpr.2013.456
复制
发表时间:
2013-06
期刊:
2013 IEEE Conference on Computer Vision and Pattern Recognition
影响因子:
--
通讯作者:
Zhen Cui;Wen Li;Dong Xu;S. Shan;Xilin Chen
Zhen Cui;Wen Li;Dong Xu;S. Shan;Xilin Chen
中科院分区:
其他
文献类型:
--
作者:
Zhen Cui;Wen Li;Dong Xu;S. Shan;Xilin Chen

文献摘要

被引文献

相似文献

在许多真实世界的人脸识别场景中,由于复杂的外观变化或低质量的图像,很难准确地对齐人脸图像。为了解决这个问题,我们提出了一种新的方法来提取鲁棒的人脸区域描述符。具体来说,我们将每个图像(分别)视频)分成几个空间块(分别是,空间-时间体积),然后表示每个块(分别为体积)通过对块内采样的无位置补丁的非负稀疏码进行求和池化(分别卷)。白化主成分分析(WPCA)进一步用于减少特征维数,这导致我们的空间人脸区域描述符(SFRD)(分别)。空间-时间面部区域描述符,STFRD)用于图像(分别视频)。此外,我们开发了一种新的距离度量学习方法,称为成对约束多度量学习(PMML),以有效地整合所有块(分别)的人脸区域描述符。卷)从图像(分别视频)。我们的工作实现了国家的最先进的性能在两个现实世界的数据集LFW和YouTube的面孔(YTF)根据限制协议。
In many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex appearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face region descriptors. Specifically, we divide each image (resp. video) into several spatial blocks (resp. spatial-temporal volumes) and then represent each block (resp. volume) by sum-pooling the nonnegative sparse codes of position-free patches sampled within the block (resp. volume). Whitened Principal Component Analysis (WPCA) is further utilized to reduce the feature dimension, which leads to our Spatial Face Region Descriptor (SFRD) (resp. Spatial-Temporal Face Region Descriptor, STFRD) for images (resp. videos). Moreover, we develop a new distance metric learning method for face verification called Pairwise-constrained Multiple Metric Learning (PMML) to effectively integrate the face region descriptors of all blocks (resp. volumes) from an image (resp. a video). Our work achieves the state-of-the-art performances on two real-world datasets LFW and YouTube Faces (YTF) according to the restricted protocol.