Learning Stacked Image Descriptor for Face Recognition

Learning Stacked Image Descriptor for Face Recognition
复制标题

学习用于人脸识别的堆叠图像描述符

DOI:
10.1109/tcsvt.2015.2473415
复制
发表时间:
2016-09
期刊:
IEEE Transaction on Circuits and Systems for Video Technology
影响因子:
--
通讯作者:
Stan Z. Li
Stan Z. Li
中科院分区:
其他
文献类型:
--
作者:
Zhen Lei;Dong Yi;Stan Z. Li

文献摘要

参考文献

被引文献

相似文献

基于学习的人脸描述符不断提高人脸识别性能。与手工特征相比,基于学习的特征被认为能够为特定任务利用具有更好区分能力的信息。受最近深度学习成功的启发,本文通过引入堆叠图像描述符(SID),将原始浅层人脸描述符扩展到深度判别人脸特征。利用深层结构,可以提取更复杂的人脸信息,提高特征表示的鉴别性和紧凑性。SID以向前优化的方式学习,与深度学习相比,这是计算效率高的。在各种人脸数据库上进行了大量的实验,结果表明,与其他最先进的描述符相比,SID能够实现高的人脸识别性能,具有紧凑的人脸表示。
Learning-based face descriptors have constantly improved the face recognition performance. Compared with the hand-crafted features, learning-based features are considered to be able to exploit information with better discriminative ability for specific tasks. Motivated by the recent success of deep learning, in this paper, we extend the original shallow face descriptors to deep discriminant face features by introducing a stacked image descriptor (SID). With deep structure, more complex facial information can be extracted and the discriminant and compactness of feature representation can be improved. The SID is learned in a forward optimization way, which is computational efficient compared with deep learning. Extensive experiments on various face databases are conducted to show that SID is able to achieve high face recognition performance with compact face representation, compared with other state-of-the-art descriptors.
DOI: 10.1109/fg.2011.5771444
发表时间: 2011-03
期刊: Face and Gesture 2011
影响因子: --
作者:
Daniel Maturana;D. Mery;Á. Soto
通讯作者: Daniel Maturana;D. Mery;Á. Soto
用于可靠人脸识别的多方位多层次双交叉模式
DOI: 10.1109/tpami.2015.2462338
发表时间: 2016-03-01
影响因子: 23.6
作者:
Ding, Changxing;Choi, Jonghyun;Davis, Larry S.
通讯作者: Davis, Larry S.
DOI: 10.1109/cvpr.2003.1211457
发表时间: 2003-06
期刊: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
影响因子: --
作者:
M. Alex O. Vasilescu;Demetri Terzopoulos
通讯作者: M. Alex O. Vasilescu;Demetri Terzopoulos
DOI: 10.1109/tip.2015.2475625
发表时间: 2015-12-01
影响因子: 10.6
作者:
Chan, Tsung-Han;Jia, Kui;Ma, Yi
通讯作者: Ma, Yi
DOI: 10.1007/bfb0015522
发表时间: 1996-04
期刊: --
影响因子: --
作者:
P. Belhumeur;J. Hespanha;D. Kriegman
通讯作者: P. Belhumeur;J. Hespanha;D. Kriegman