Person Re-Identification Net of Spindle Net Fusing Facial Feature

Person Re-Identification Net of Spindle Net Fusing Facial Feature

In the field of person re-identification, the extraction of pedestrian features is mainly focused on the extraction of features from the whole pedestrian or limb torso, and the facial features are less used. The facial features is integrated into the network to enhance pedestrian recognition accurac...

Full description

Bibliographic Details
Format: Article
Language:zho
Published: The Northwestern Polytechnical University 2019-10-01
Series:Xibei Gongye Daxue Xuebao
Subjects:
person re-identification
facial
convolutional neural network
Online Access:https://www.jnwpu.org/articles/jnwpu/full_html/2019/05/jnwpu2019375p1070/jnwpu2019375p1070.html
id doaj-b7228b436195404e84acc9ef4caad72e
record_format Article
spelling doaj-b7228b436195404e84acc9ef4caad72e2021-05-03T01:24:19ZzhoThe Northwestern Polytechnical UniversityXibei Gongye Daxue Xuebao1000-27582609-71252019-10-013751070107610.1051/jnwpu/20193751070jnwpu2019375p1070Person Re-Identification Net of Spindle Net Fusing Facial Feature01School of Computer Science and Technology, Changchun University of Science and TechnologySchool of Computer Science and Technology, Changchun University of Science and TechnologyIn the field of person re-identification, the extraction of pedestrian features is mainly focused on the extraction of features from the whole pedestrian or limb torso, and the facial features are less used. The facial features is integrated into the network to enhance pedestrian recognition accuracy rate. By introducing the MTCNN facial extraction network in the framework of person re-identification network Spindle Net, and improves the accuracy of person re-identification by improving the weight of facial features in the overall pedestrian characteristics. The experimental results show that the accuracy of Rank-1 on the CUHK01, CUHK03, VIPeR, PRID, i-LIDS, and 3DPeS data sets is 7% higher than that of Spindle Net.https://www.jnwpu.org/articles/jnwpu/full_html/2019/05/jnwpu2019375p1070/jnwpu2019375p1070.htmlperson re-identificationfacialconvolutional neural network
collection DOAJ
language zho
format Article
sources DOAJ
title Person Re-Identification Net of Spindle Net Fusing Facial Feature
spellingShingle Person Re-Identification Net of Spindle Net Fusing Facial Feature
Xibei Gongye Daxue Xuebao
person re-identification
facial
convolutional neural network
title_short Person Re-Identification Net of Spindle Net Fusing Facial Feature
title_full Person Re-Identification Net of Spindle Net Fusing Facial Feature
title_fullStr Person Re-Identification Net of Spindle Net Fusing Facial Feature
title_full_unstemmed Person Re-Identification Net of Spindle Net Fusing Facial Feature
title_sort person re-identification net of spindle net fusing facial feature
publisher The Northwestern Polytechnical University
series Xibei Gongye Daxue Xuebao
issn 1000-2758
2609-7125
publishDate 2019-10-01
description In the field of person re-identification, the extraction of pedestrian features is mainly focused on the extraction of features from the whole pedestrian or limb torso, and the facial features are less used. The facial features is integrated into the network to enhance pedestrian recognition accuracy rate. By introducing the MTCNN facial extraction network in the framework of person re-identification network Spindle Net, and improves the accuracy of person re-identification by improving the weight of facial features in the overall pedestrian characteristics. The experimental results show that the accuracy of Rank-1 on the CUHK01, CUHK03, VIPeR, PRID, i-LIDS, and 3DPeS data sets is 7% higher than that of Spindle Net.
topic person re-identification
facial
convolutional neural network
url https://www.jnwpu.org/articles/jnwpu/full_html/2019/05/jnwpu2019375p1070/jnwpu2019375p1070.html
_version_ 1721485986237513728

Similar Items