Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/22357
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiu, W-
dc.contributor.authorWei, X-
dc.contributor.authorLei, T-
dc.contributor.authorWang, X-
dc.contributor.authorMeng, H-
dc.contributor.authorNandi, A-
dc.date.accessioned2021-03-04T05:59:01Z-
dc.date.available2021-03-04T05:59:01Z-
dc.date.issued2021-03-08-
dc.identifierORCID iDs: Tao Lei https://orcid.org/0000-0002-2104-9298; Hongying Meng https://orcid.org/0000-0002-8836-1382; Asoke K. Nandi https://orcid.org/0000-0001-6248-2875.-
dc.identifier.citationLiu, W. et al. (2022) 'Data Fusion based Two-stage Cascade Framework for Multi-Modality Face Anti-Spoofing', IEEE Transactions on Cognitive and Developmental Systems, 14 (2), pp. 672 - 683. doi: 10.1109/TCDS.2021.3064679.-
dc.identifier.issn2379-8920-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/22357-
dc.description.abstractCopyright © 2021 The Author(s). Existing face anti-spoofing models using deep learning for multimodality data suffer from low generalization in the case of using variety of presentation attacks, such as 2-D printing and high-precision 3-D face masks. One of the main reasons is that the nonlinearity of multispectral information used to preserve the intrinsic attributes between a real and a fake face is not well extracted. To address this issue, we propose a multimodility data-based two-stage cascade framework for face anti-spoofing. The proposed framework has two advantages. First, we design a two-stage cascade architecture that can selectively fuse low-level and high-level features from different modalities to improve feature representation. Second, we use multimodality data to construct a distance-free spectral on RGB and infrared to augment the nonlinearity of data. The presented data fusion strategy is different from popular fusion approaches, since it can strengthen discrimination ability of network models on physical attribute features than identity structure features under certain constraints. In addition, a multiscale patch-based weighted fine-tuning strategy is designed to learn each specific local face region. The experimental results show that the proposed framework achieves better performance than other state-of-the-art methods on both benchmark data sets and self-established data sets, especially on multimaterial masks spoofing.-
dc.description.sponsorship10.13039/501100001809-National Natural Science Foundation of China (IEC\NSFC\170396, Royal Society, U.K.) (Grant Number: 61871259, 61811530325, 61871260, 61672333 and 61873155) 10.13039/501100007128-Natural Science Foundation of Shaanxi Province (Grant Number: 2018JM6065) 10.13039/501100017592-Key Science and Technology Program of Shaanxi Province (Grant Number: 2020NY-172)en_US
dc.format.extent672 - 683-
dc.format.mediumPrint-Electronic-
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsCopyright © 2021 The Author(s). Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/-
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/-
dc.titleData Fusion based Two-stage Cascade Framework for Multi-Modality Face Anti-Spoofingen_US
dc.typeArticleen_US
dc.identifier.doihttps://doi.org/10.1109/TCDS.2021.3064679-
dc.relation.isPartOfIEEE Transactions on Cognitive and Developmental Systems-
pubs.issue2-
pubs.publication-statusPublished-
pubs.volume14-
dc.identifier.eissn2379-8939-
dc.rights.holderThe Author(s)-
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2021 The Author(s). Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/2 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons