Altered Fingerprints Detection Based on Deep Feature Fusion
Summary :
The altered fingerprints help criminals escape from police and cause great harm to the society. In this letter, an altered fingerprint detection method is proposed. The method is constructed by two deep convolutional neural networks to train the time-domain and frequency-domain features. A spectral attention module is added to connect two networks. After the extraction network, a feature fusion module is then used to exploit relationship of two network features. We make ablation experiments and add the module proposed in some popular architectures. Results show the proposed method can improve the performance of altered fingerprint detection compared with the recent neural networks.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.9 pp.1647-1651
- Publication Date
- 2022/09/01
- Publicized
- 2022/06/13
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDL8028
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Chao XU
Shanghai University
Yunfeng YAN
Zhejiang University
Lehangyu YANG
University of Macau
Sheng LI
Fudan Univeristy
Guorui FENG
Shanghai University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chao XU, Yunfeng YAN, Lehangyu YANG, Sheng LI, Guorui FENG, "Altered Fingerprints Detection Based on Deep Feature Fusion" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 9, pp. 1647-1651, September 2022, doi: 10.1587/transinf.2022EDL8028.
Abstract: The altered fingerprints help criminals escape from police and cause great harm to the society. In this letter, an altered fingerprint detection method is proposed. The method is constructed by two deep convolutional neural networks to train the time-domain and frequency-domain features. A spectral attention module is added to connect two networks. After the extraction network, a feature fusion module is then used to exploit relationship of two network features. We make ablation experiments and add the module proposed in some popular architectures. Results show the proposed method can improve the performance of altered fingerprint detection compared with the recent neural networks.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8028/_p
Copy
@ARTICLE{e105-d_9_1647,
author={Chao XU, Yunfeng YAN, Lehangyu YANG, Sheng LI, Guorui FENG, },
journal={IEICE TRANSACTIONS on Information},
title={Altered Fingerprints Detection Based on Deep Feature Fusion},
year={2022},
volume={E105-D},
number={9},
pages={1647-1651},
abstract={The altered fingerprints help criminals escape from police and cause great harm to the society. In this letter, an altered fingerprint detection method is proposed. The method is constructed by two deep convolutional neural networks to train the time-domain and frequency-domain features. A spectral attention module is added to connect two networks. After the extraction network, a feature fusion module is then used to exploit relationship of two network features. We make ablation experiments and add the module proposed in some popular architectures. Results show the proposed method can improve the performance of altered fingerprint detection compared with the recent neural networks.},
keywords={},
doi={10.1587/transinf.2022EDL8028},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Altered Fingerprints Detection Based on Deep Feature Fusion
T2 - IEICE TRANSACTIONS on Information
SP - 1647
EP - 1651
AU - Chao XU
AU - Yunfeng YAN
AU - Lehangyu YANG
AU - Sheng LI
AU - Guorui FENG
PY - 2022
DO - 10.1587/transinf.2022EDL8028
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2022
AB - The altered fingerprints help criminals escape from police and cause great harm to the society. In this letter, an altered fingerprint detection method is proposed. The method is constructed by two deep convolutional neural networks to train the time-domain and frequency-domain features. A spectral attention module is added to connect two networks. After the extraction network, a feature fusion module is then used to exploit relationship of two network features. We make ablation experiments and add the module proposed in some popular architectures. Results show the proposed method can improve the performance of altered fingerprint detection compared with the recent neural networks.
ER -
English
