A novel approach inspired by optic nerve characteristics for few-shot occluded face recognition

A novel approach inspired by optic nerve characteristics for few-shot occluded face recognition
复制标题

一种受视神经特征启发的新颖方法,用于少镜头遮挡人脸识别

DOI:
10.1016/j.neucom.2019.09.045
复制
发表时间:
2020-02
期刊:
影响因子:
6
通讯作者:
Wang Fei-Yue
Wang Fei-Yue
中科院分区:
计算机科学2区
文献类型:
--
作者:
Zheng Wenbo;Gou Chao;Wang Fei-Yue

文献摘要

参考文献

相似文献

虽然人脸识别的研究工作越来越多,但在训练样本有限的情况下,对于遮挡下的人脸识别仍然是一项具有挑战性的任务。在这项工作中,我们提出了一个新的框架,以解决问题的少数镜头遮挡人脸识别。特别是,受人类的视觉神经特性,人类识别的人脸遮挡使用上下文信息,而不是关注的面部部位,我们提出了一种有效的特征提取方法来捕获的本地和上下文信息的人脸识别。为了提高鲁棒性,我们进一步引入了一种自适应融合方法,将多个功能,包括建议的结构元素功能,连接颗粒标记功能,和加强中心对称局部二进制模式(RCSLBP)。根据我们提出的新的融合方法的所有分类结果的融合,最终识别。在AR、Extended Yale B和LFW三种流行人脸图像数据集上的实验结果表明,该方法在遮挡情况下的少镜头人脸识别中的性能优于许多现有方法。
Although there has been a growing body of work for face recognition, it is still a challenging task for faces under occlusion with limited training samples. In this work, we propose a novel framework to address the problem of few-shot occluded face recognition. In particular, inspired by the human being’s optic nerves characteristics that humans recognize the face under occlusion using contextual information rather than paying attention to the facial parts, we propose an effective feature extraction approach to capture the local and contextual information for face recognition. To enhance the robustness, we further introduce an adaptive fusion method to incorporate multiple features, including the proposed structural element feature, connected-granule labeling feature, and Reinforced Centrosymmetric Local Binary Pattern (RCSLBP). Final recognition is derived from the fusion of all classification results according to our proposed novel fusion method. Experimental results on three popular face image datasets of AR, Extended Yale B, and LFW demonstrate that our method performs better than many existing ones for few-shot face recognition in the presence of occlusion.
DOI: 10.1016/j.jvcir.2012.10.003
发表时间: 2013-01-01
影响因子: 2.6
作者:
Wang Xingyuan;Wang Zongyu
通讯作者: Wang Zongyu
DOI: 10.1109/tvt.2015.2509465
发表时间: 2016-06
影响因子: 6.8
作者:
Kunfeng Wang;Yuqiang Liu;Chao Gou;Fei-Yue Wang
通讯作者: Fei-Yue Wang
DOI: 10.1038/s41467-017-02438-8
发表时间: 2018-01-31
影响因子: 16.6
作者:
Oleskiw TD;Nowack A;Pasupathy A
通讯作者: Pasupathy A
DOI: 10.1109/tip.2017.2675206
发表时间: 2017-05-01
影响因子: 10.6
作者:
Iliadis, Michael;Wang, Haohong;Katsaggelos, Aggelos K.
通讯作者: Katsaggelos, Aggelos K.
通过无监督的跨视图度量学习进行人员重新识别
DOI: 10.1109/tcyb.2019.2909480
发表时间: 2019-04
影响因子: 11.8
作者:
Yachuang Feng;Yuan Yuan;Xiaoqiang Lu
通讯作者: Xiaoqiang Lu