Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.3
3.4
Journals
Sensors
Special Issues
From AI to Image Processing, Forensics, Anonymization, and Adversarial Techniques
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

From AI to Image Processing, Forensics, Anonymization, and Adversarial Techniques

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (25 April 2023) | Viewed by 7813

Special Issue Editors

Dr. Bonnie Law

E-Mail Website
Guest Editor
Department of Electronics and information engineering, The Hong Kong Polytechnic University, Hong Kong
Interests: image forensics; wavelet transform; image enhancement and retrieval; gene expression data analysis; DNA sequence analysis; source camera identification
Dr. Muhammad Irshad

E-Mail Website
Guest Editor
Department of Electronics and information engineering, The Hong Kong Polytechnic University, Hong Kong
Interests: computer vision; image forensics; source camera identification; object localization; signal processing

Special Issue Information

Dear Colleagues,

The recent increase in the number of digital images that are being uploaded and shared online has given rise to unique privacy and forensic challenges. Despite advances in computing power, pixel resolution, and frame rate, on the one hand, and the different involved different methods, such as machine learning and deep learning, on the other, this is still a difficult problem, and existing methods are still not as robust and reliable. On some occasions, data anonymization is necessary as it reduces the risk of unintended disclosure when sharing data between countries, industries, and even departments within the same company. It also reduces opportunities for identity theft to occur. Similarly, the principle of open justice can sometimes act as a bar to successful prosecutions, particularly in homicides, organised crime, and gun crime.  Many approaches have been proposed by extracting some image features. One example is based on guided image estimation, and the facial quantification statistics, which characterize the specific frequency from the perspective of image source identification. However, most of these methods only focus on extracting features from the single artifact of the camera left on the captured images. Several machine learning models are vulnerable to adversarial attacks in this regard. On the other hand, deep learning does not necessarily improve performance due to the absence of large databases and the need to tackle new and severe challenges to ensure media authenticity.

Dr. Bonnie Law
Dr. Muhammad Irshad
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • image forensics
  • video forensics
  • sensor pattern noise
  • CMOS image sensors
  • seam carving
  • image enhancement and retrieval
  • source camera identification
  • wavelet transform
  • image feature extraction
  • feature matching
  • object recognition
  • 3D vision

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 520 KiB  
Article
Detection of Double-Compressed Videos Using Descriptors of Video Encoders
by Yun Gu Lee, Gihyun Na and Junseok Byun
Sensors 2022, 22(23), 9291; https://doi.org/10.3390/s22239291 - 29 Nov 2022
Cited by 1 | Viewed by 1592
Abstract
In digital forensics, video becomes important evidence in an accident or a crime. However, video editing programs are easily available in the market, and even non-experts can delete or modify a section of an evidence video that contains adverse evidence. The tampered video [...] Read more.
In digital forensics, video becomes important evidence in an accident or a crime. However, video editing programs are easily available in the market, and even non-experts can delete or modify a section of an evidence video that contains adverse evidence. The tampered video is compressed again and stored. Therefore, detecting a double-compressed video is one of the important methods in the field of digital video tampering detection. In this paper, we present a new approach to detecting a double-compressed video using the proposed descriptors of video encoders. The implementation of real-time video encoders is so complex that manufacturers should develop hardware video encoders considering a trade-off between complexity and performance. According to our observation, hardware video encoders practically do not use all possible encoding modes defined in the video coding standard but only a subset of the encoding modes. The proposed method defines this subset of encoding modes as the descriptor of the video encoder. If a video is double-compressed, the descriptor of the double-compressed video is changed to the descriptor of the video encoder used for double-compression. Therefore, the proposed method detects the double-compressed video by checking whether the descriptor of the test video is changed or not. In our experiments, we show descriptors of various H.264 and High-Efficiency Video Coding (HEVC) video encoders and demonstrate that our proposed method successfully detects double-compressed videos in most cases. Full article
(This article belongs to the Special Issue From AI to Image Processing, Forensics, Anonymization, and Adversarial Techniques)
►▼ Show Figures

Figure 1

23 pages, 12542 KiB  
Article
Deep Learning Based One-Class Detection System for Fake Faces Generated by GAN Network
by Shengyin Li, Vibekananda Dutta, Xin He and Takafumi Matsumaru
Sensors 2022, 22(20), 7767; https://doi.org/10.3390/s22207767 - 13 Oct 2022
Cited by 12 | Viewed by 5243
Abstract
Recently, the dangers associated with face generation technology have been attracting much attention in image processing and forensic science. The current face anti-spoofing methods based on Generative Adversarial Networks (GANs) suffer from defects such as overfitting and generalization problems. This paper proposes a [...] Read more.
Recently, the dangers associated with face generation technology have been attracting much attention in image processing and forensic science. The current face anti-spoofing methods based on Generative Adversarial Networks (GANs) suffer from defects such as overfitting and generalization problems. This paper proposes a new generation method using a one-class classification model to judge the authenticity of facial images for the purpose of realizing a method to generate a model that is as compatible as possible with other datasets and new data, rather than strongly depending on the dataset used for training. The method proposed in this paper has the following features: (a) we adopted various filter enhancement methods as basic pseudo-image generation methods for data enhancement; (b) an improved Multi-Channel Convolutional Neural Network (MCCNN) was adopted as the main network, making it possible to accept multiple preprocessed data individually, obtain feature maps, and extract attention maps; (c) as a first ingenuity in training the main network, we augmented the data using weakly supervised learning methods to add attention cropping and dropping to the data; (d) as a second ingenuity in training the main network, we trained it in two steps. In the first step, we used a binary classification loss function to ensure that known fake facial features generated by known GAN networks were filtered out. In the second step, we used a one-class classification loss function to deal with the various types of GAN networks or unknown fake face generation methods. We compared our proposed method with four recent methods. Our experiments demonstrate that the proposed method improves cross-domain detection efficiency while maintaining source-domain accuracy. These studies show one possible direction for improving the correct answer rate in judging facial image authenticity, thereby making a great contribution both academically and practically. Full article
(This article belongs to the Special Issue From AI to Image Processing, Forensics, Anonymization, and Adversarial Techniques)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop