Distortion model-based spectral augmentation for generalized recaptured document detection

Document recapturing is a presentation attack that covers the forensic traces in the digital domain. Document presentation attack detection (DPAD) is an important step in the document authentication pipeline. Existing DPAD methods suffer from low generalization performance under the cross-domain sce...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Changsheng, Li, Bokang, Cai, Rizhao, Zeng, Jishen, Huang, Jiwu
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/173279
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-173279
record_format dspace
spelling sg-ntu-dr.10356-1732792024-01-23T01:17:43Z Distortion model-based spectral augmentation for generalized recaptured document detection Chen, Changsheng Li, Bokang Cai, Rizhao Zeng, Jishen Huang, Jiwu School of Electrical and Electronic Engineering ROSE Laboratory Engineering::Electrical and electronic engineering Recapture Detection Distortion Model Document recapturing is a presentation attack that covers the forensic traces in the digital domain. Document presentation attack detection (DPAD) is an important step in the document authentication pipeline. Existing DPAD methods suffer from low generalization performance under the cross-domain scenario with different types of documents. Data augmentation is a de facto technique to reduce the risk of overfitting the training data and improve the generalizability of a trained model. In this work, we improve the generalization performance of DPAD approaches by addressing two important limitations of the existing frequency domain augmentation (FDA) methods. First, contrary to the existing FDA methods that treat different spectral bands equally, we establish a band-of-interest localization (BOIL) method that locates the spectral band-of-interest (BOI) related to the recapturing operation by domain knowledge from the theoretical distortion models. Second, we propose a frequency-domain halftoning augmentation (FHAG) strategy that enhances the halftoning features in the BOI with considerations of different halftoning distortions. To evaluate the generalization performance of our FHAG with BOIL method on different types of document images, we have constructed a diverse recaptured document image dataset with 162 types of documents (RDID162), consisting of 5346 samples. The proposed method has been evaluated on the generic deep learning models and a state-of-the-art DPAD approach under both cross-device and cross-domain protocols for the DPAD task. Compared to the existing FDA methods, our method has improved the models with ResNet50 backbone by reducing more than 25% or 5 percentage points in EERs. The source code and data in this work is available at https://github.com/chenlewis/FHAG-with-BOIL. This work was supported in part by NSFC under Grant 62072313, Grant 62371301, Grant 62272314, and Grant U19B2022; and in part by the CCF-Alibaba Innovative Research Fund for Young Scholars. 2024-01-23T01:17:43Z 2024-01-23T01:17:43Z 2024 Journal Article Chen, C., Li, B., Cai, R., Zeng, J. & Huang, J. (2024). Distortion model-based spectral augmentation for generalized recaptured document detection. IEEE Transactions On Information Forensics and Security, 19, 1283-1298. https://dx.doi.org/10.1109/TIFS.2023.3333548 1556-6013 https://hdl.handle.net/10356/173279 10.1109/TIFS.2023.3333548 2-s2.0-85179080144 19 1283 1298 en IEEE Transactions on Information Forensics and Security © 2023 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Recapture Detection
Distortion Model
spellingShingle Engineering::Electrical and electronic engineering
Recapture Detection
Distortion Model
Chen, Changsheng
Li, Bokang
Cai, Rizhao
Zeng, Jishen
Huang, Jiwu
Distortion model-based spectral augmentation for generalized recaptured document detection
description Document recapturing is a presentation attack that covers the forensic traces in the digital domain. Document presentation attack detection (DPAD) is an important step in the document authentication pipeline. Existing DPAD methods suffer from low generalization performance under the cross-domain scenario with different types of documents. Data augmentation is a de facto technique to reduce the risk of overfitting the training data and improve the generalizability of a trained model. In this work, we improve the generalization performance of DPAD approaches by addressing two important limitations of the existing frequency domain augmentation (FDA) methods. First, contrary to the existing FDA methods that treat different spectral bands equally, we establish a band-of-interest localization (BOIL) method that locates the spectral band-of-interest (BOI) related to the recapturing operation by domain knowledge from the theoretical distortion models. Second, we propose a frequency-domain halftoning augmentation (FHAG) strategy that enhances the halftoning features in the BOI with considerations of different halftoning distortions. To evaluate the generalization performance of our FHAG with BOIL method on different types of document images, we have constructed a diverse recaptured document image dataset with 162 types of documents (RDID162), consisting of 5346 samples. The proposed method has been evaluated on the generic deep learning models and a state-of-the-art DPAD approach under both cross-device and cross-domain protocols for the DPAD task. Compared to the existing FDA methods, our method has improved the models with ResNet50 backbone by reducing more than 25% or 5 percentage points in EERs. The source code and data in this work is available at https://github.com/chenlewis/FHAG-with-BOIL.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Chen, Changsheng
Li, Bokang
Cai, Rizhao
Zeng, Jishen
Huang, Jiwu
format Article
author Chen, Changsheng
Li, Bokang
Cai, Rizhao
Zeng, Jishen
Huang, Jiwu
author_sort Chen, Changsheng
title Distortion model-based spectral augmentation for generalized recaptured document detection
title_short Distortion model-based spectral augmentation for generalized recaptured document detection
title_full Distortion model-based spectral augmentation for generalized recaptured document detection
title_fullStr Distortion model-based spectral augmentation for generalized recaptured document detection
title_full_unstemmed Distortion model-based spectral augmentation for generalized recaptured document detection
title_sort distortion model-based spectral augmentation for generalized recaptured document detection
publishDate 2024
url https://hdl.handle.net/10356/173279
_version_ 1789482977871265792