Home > Research > Publications & Outputs > Hand-Based Person Identification using Global a...

Electronic data

  • 2101.05260v1

    Final published version, 812 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Keywords

View graph of relations

Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning. / Baisa, Nathanael L.; Jiang, Zheheng; Vyas, Ritesh et al.
In: arXiv, 13.01.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{92a15ab2e9ce4e4983a1df4aa3e0f16d,
title = "Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning",
abstract = " In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose hand-based person identification by learning both global and local deep feature representation. Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features. For learning the local (part-level) features, we perform uniform partitioning on the conv-layer in both horizontal and vertical directions. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. We make extensive evaluations on two large multi-ethnic and publicly available hand datasets, demonstrating that our proposed method significantly outperforms competing approaches. ",
keywords = "cs.CV",
author = "Baisa, {Nathanael L.} and Zheheng Jiang and Ritesh Vyas and Bryan Williams and Hossein Rahmani and Plamen Angelov and Sue Black",
year = "2021",
month = jan,
day = "13",
language = "English",
journal = "arXiv",
issn = "2331-8422",

}

RIS

TY - JOUR

T1 - Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning

AU - Baisa, Nathanael L.

AU - Jiang, Zheheng

AU - Vyas, Ritesh

AU - Williams, Bryan

AU - Rahmani, Hossein

AU - Angelov, Plamen

AU - Black, Sue

PY - 2021/1/13

Y1 - 2021/1/13

N2 - In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose hand-based person identification by learning both global and local deep feature representation. Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features. For learning the local (part-level) features, we perform uniform partitioning on the conv-layer in both horizontal and vertical directions. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. We make extensive evaluations on two large multi-ethnic and publicly available hand datasets, demonstrating that our proposed method significantly outperforms competing approaches.

AB - In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose hand-based person identification by learning both global and local deep feature representation. Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features. For learning the local (part-level) features, we perform uniform partitioning on the conv-layer in both horizontal and vertical directions. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. We make extensive evaluations on two large multi-ethnic and publicly available hand datasets, demonstrating that our proposed method significantly outperforms competing approaches.

KW - cs.CV

M3 - Journal article

JO - arXiv

JF - arXiv

SN - 2331-8422

ER -