Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning
Camera identification has recently attracted considerable attention in the image forensic field of research. Several algorithms have been established based on the hand-crafted features and deep learning, through analysis of the traces achieved by the digital image acquisition process. Although these...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8633894/ |
id |
doaj-bee8b04cf37d4d359a89e2171774ff6c |
---|---|
record_format |
Article |
spelling |
doaj-bee8b04cf37d4d359a89e2171774ff6c2021-03-29T22:38:53ZengIEEEIEEE Access2169-35362019-01-017258782589010.1109/ACCESS.2019.28973608633894Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task LearningXinghao Ding0Yunshu Chen1Zhen Tang2Yue Huang3https://orcid.org/0000-0002-3913-9400School of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaCamera identification has recently attracted considerable attention in the image forensic field of research. Several algorithms have been established based on the hand-crafted features and deep learning, through analysis of the traces achieved by the digital image acquisition process. Although these approaches have led to a breakthrough in the image forensics, some important problems still remain unsolved. For instance, extracting the hand-crafted features with human efforts is a difficult and time-consuming process, while data-driven deep learning methods tend to learn features that represent image contents rather than cameras' characteristics. To fully take advantages of both hand-crafted and data-driven technologies, we propose a domain knowledge-driven method, which consists of one pre-processing module, one feature extractor, and one hierarchical multi-task learning procedure. The pre-processing module can introduce the domain knowledge to the subsequent deep learning network. Moreover, for device-level identification, hierarchical multi-task learning can provide more supervise information from the brand and model. The proposed framework is evaluated on three different tasks, i.e., the brand, model, and device-level identification using original and manipulated images. Our classification results demonstrate that the proposed method is effective and robust. To evaluate the robustness of the proposed method, we create a new database for the cell-phone identification and evaluate the proposed method. It is found that the accuracy of the cell-phone device identification can reach 84.3%, which is much higher than that of the camera identification. Moreover, the t-distributed stochastic neighbor embedding visualization results confirm that the features of different cell-phone devices are visually more separable than cameras.https://ieeexplore.ieee.org/document/8633894/Camera identificationimage forensic fileddomain knowledge-drivenmulti-task learningcell-phone identification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xinghao Ding Yunshu Chen Zhen Tang Yue Huang |
spellingShingle |
Xinghao Ding Yunshu Chen Zhen Tang Yue Huang Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning IEEE Access Camera identification image forensic filed domain knowledge-driven multi-task learning cell-phone identification |
author_facet |
Xinghao Ding Yunshu Chen Zhen Tang Yue Huang |
author_sort |
Xinghao Ding |
title |
Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning |
title_short |
Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning |
title_full |
Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning |
title_fullStr |
Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning |
title_full_unstemmed |
Camera Identification Based on Domain Knowledge-Driven Deep Multi-Task Learning |
title_sort |
camera identification based on domain knowledge-driven deep multi-task learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Camera identification has recently attracted considerable attention in the image forensic field of research. Several algorithms have been established based on the hand-crafted features and deep learning, through analysis of the traces achieved by the digital image acquisition process. Although these approaches have led to a breakthrough in the image forensics, some important problems still remain unsolved. For instance, extracting the hand-crafted features with human efforts is a difficult and time-consuming process, while data-driven deep learning methods tend to learn features that represent image contents rather than cameras' characteristics. To fully take advantages of both hand-crafted and data-driven technologies, we propose a domain knowledge-driven method, which consists of one pre-processing module, one feature extractor, and one hierarchical multi-task learning procedure. The pre-processing module can introduce the domain knowledge to the subsequent deep learning network. Moreover, for device-level identification, hierarchical multi-task learning can provide more supervise information from the brand and model. The proposed framework is evaluated on three different tasks, i.e., the brand, model, and device-level identification using original and manipulated images. Our classification results demonstrate that the proposed method is effective and robust. To evaluate the robustness of the proposed method, we create a new database for the cell-phone identification and evaluate the proposed method. It is found that the accuracy of the cell-phone device identification can reach 84.3%, which is much higher than that of the camera identification. Moreover, the t-distributed stochastic neighbor embedding visualization results confirm that the features of different cell-phone devices are visually more separable than cameras. |
topic |
Camera identification image forensic filed domain knowledge-driven multi-task learning cell-phone identification |
url |
https://ieeexplore.ieee.org/document/8633894/ |
work_keys_str_mv |
AT xinghaoding cameraidentificationbasedondomainknowledgedrivendeepmultitasklearning AT yunshuchen cameraidentificationbasedondomainknowledgedrivendeepmultitasklearning AT zhentang cameraidentificationbasedondomainknowledgedrivendeepmultitasklearning AT yuehuang cameraidentificationbasedondomainknowledgedrivendeepmultitasklearning |
_version_ |
1724191199262146560 |