sensors-logo

Journal Browser

Journal Browser

Feature Extraction and Forensic Image Analysis

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

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 9122

Special Issue Editors

Department of Computer Science, University of Salerno, Salerno, Italy
Interests: computer science; digital forensics; experimental algorithm; image processing; source camera identification; feature extraction; big data; alignment free sequence analysis; highly scalable architectures; Hadoop MapReduce paradigm; spark distributed platform
Department of Computer Science, University of Salerno, Salerno, Italy
Interests: human–computer interaction biometrics
Department of Computer Science, University of Salerno, Salerno, Italy
Interests: digital forensics; video and image integrity; biometry; security; cryptography

Special Issue Information

Dear Colleagues,

Although the goals of biometrics and media forensics are different, the researchers in these areas share purposes and tools. This Special Issue aims to bring together papers in these areas with a common interest in modelling, designing and implementing.

In this scenario, there is a continued need for vigorous research to solve many outstanding challenging problems, since technologies are rapidly evolving to manage processes and to interact with new types of data such as 2.5 and 3D data, sensor data, high-definition video, multi-channel high-resolution audio and internet broad-band interactive content.

In this direction, this Special Issue focuses on new application fields that are emerging or becoming more viable for practical purposes, especially in supporting law enforcement and investigation. Increasingly, new scenarios arise where techniques designed for biometrics can be used for forensic purposes, or vice versa. Therefore, this Special Issue will collect original papers documenting the current state-of-the-art, the latest breakthroughs achieved by the scientists working in the area of image processing, feature extraction, ambient intelligence, biometric recognition and digital forensics, to integrate multidisciplinary research efforts to identify future promising research areas.

We invite original contributions that provide novel solutions to challenging problems.

Original research, techniques, state-of-the-art surveys, and advanced applications are invited in any of the areas listed above. Papers will be published in a Special Issue of Sensors scheduled for 2022. Acceptance will be based on quality, relevance, and originality.

Topics of interest include, but are not limited to, the following:

  • Biometrics and soft biometrics;
  • Mobile biometrics;
  • Audiovisual biometrics for multimedia forensics;
  • Biometric spoofing and liveness detection;
  • Biometric and forensic analysis of crime scene traces;
  • Forensic behavioural biometrics;
  • Security assessment for multi-biometrics systems;
  • Image feature extraction;
  • Multimedia forensics;
  • Source camera identification;
  • Image and video forgery detection;
  • Machine learning techniques in image and video forensics;
  • Deep fake detection techniques;
  • Audio forensics;
  • Security of information in social media;
  • Adversarial learning;
  • Counter-forensics;
  • Steganography and steganalysis;
  • Multimedia watermarking;
  • Multimedia fingerprinting.

Prof. Dr. Giuseppe Cattaneo
Prof. Dr. Andrea F. Abate
Dr. Andrea Bruno
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.

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 217 KiB  
Article
Mobile Forensics: Repeatable and Non-Repeatable Technical Assessments
by Raffaele Cuomo, Davide D’Agostino and Mario Ianulardo
Sensors 2022, 22(18), 7096; https://0-doi-org.brum.beds.ac.uk/10.3390/s22187096 - 19 Sep 2022
Viewed by 2281
Abstract
This paper presents several scenarios where digital evidence can be collected from mobile devices, their legal value keeping untouched. The paper describes a robust methodology for mobile forensics developed through on-field experiences directly gained by the authors over the last 10 years and [...] Read more.
This paper presents several scenarios where digital evidence can be collected from mobile devices, their legal value keeping untouched. The paper describes a robust methodology for mobile forensics developed through on-field experiences directly gained by the authors over the last 10 years and many real court cases. The results show that mobile forensics, digital analysis of smartphone Android or iOS can be obtained in two ways: on the one hand, data extraction must follow the best practice of the repeatability procedure; on the other hand, the extraction of the data must follow the best practice of the non-repeatability procedure. The laboratory study of the two methods for extracting digital data from mobile phones, for use as evidence in court trials, has shown that the same evidence can be obtained even when the procedure of unavailability of file mining activities has been adopted. Indeed, thanks to laboratory tests, the existence of multiple files frequently and continuously subjected to changes generated by the presence of several hashes found at forensic extractions conducted in very short moments of time (sometimes not exceeding 15 min) has been proven. If, on the other hand, the examination of a device is entrusted to a judicial police officer in order to conduct a forensic analysis to acquire data produced and managed by the user (such as images, audio, video, documents, SMS, MMS, chat conversations, address book content, etc.) we have sufficient grounds to believe that such examination can be organized according to the system of repeatable technical assessments. Full article
(This article belongs to the Special Issue Feature Extraction and Forensic Image Analysis)
15 pages, 2352 KiB  
Article
A PNU-Based Methodology to Improve the Reliability of Biometric Systems
by Paola Capasso, Lucia Cimmino, Andrea F. Abate, Andrea Bruno and Giuseppe Cattaneo
Sensors 2022, 22(16), 6074; https://0-doi-org.brum.beds.ac.uk/10.3390/s22166074 - 14 Aug 2022
Cited by 6 | Viewed by 1509
Abstract
Face recognition is an important application of pattern recognition and image analysis in biometric security systems. The COVID-19 outbreak has introduced several issues that can negatively affect the reliability of the facial recognition systems currently available: on the one hand, wearing a face [...] Read more.
Face recognition is an important application of pattern recognition and image analysis in biometric security systems. The COVID-19 outbreak has introduced several issues that can negatively affect the reliability of the facial recognition systems currently available: on the one hand, wearing a face mask/covering has led to growth in failure cases, while on the other, the restrictions on direct contact between people can prevent any biometric data being acquired in controlled environments. To effectively address these issues, we designed a hybrid methodology that improves the reliability of facial recognition systems. A well-known Source Camera Identification (SCI) technique, based on Pixel Non-Uniformity (PNU), was applied to analyze the integrity of the input video stream as well as to detect any tampered/fake frames. To examine the behavior of this methodology in real-life use cases, we implemented a prototype that showed two novel properties compared to the current state-of-the-art of biometric systems: (a) high accuracy even when subjects are wearing a face mask; (b) whenever the input video is produced by deep fake techniques (replacing the face of the main subject) the system can recognize that it has been altered providing more than one alert message. This methodology proved not only to be simultaneously more robust to mask induced occlusions but also even more reliable in preventing forgery attacks on the input video stream. Full article
(This article belongs to the Special Issue Feature Extraction and Forensic Image Analysis)
Show Figures

Figure 1

18 pages, 12831 KiB  
Article
Assessment for Different Neural Networks with FeatureSelection in Classification Issue
by Joy Iong-Zong Chen and Chung-Sheng Pi
Sensors 2022, 22(8), 3099; https://0-doi-org.brum.beds.ac.uk/10.3390/s22083099 - 18 Apr 2022
Viewed by 1772
Abstract
In general, the investigation of NN (neural network) computing systems requires the management of a significant number of simultaneous distinct algorithms, such as parallel computing, fault tolerance, classification, and data optimization. Supervised learning for NN originally comes from certain parameters, such as self-revised [...] Read more.
In general, the investigation of NN (neural network) computing systems requires the management of a significant number of simultaneous distinct algorithms, such as parallel computing, fault tolerance, classification, and data optimization. Supervised learning for NN originally comes from certain parameters, such as self-revised learning, input learning datasets, and multiple second learning processes. Specifically, the operation continues to adjust the NN connection synapses’ weight to achieve a self-learning computer system. The current article is aimed at developing the CC (correlation coefficient) assignment scheme adaptively joint with the FS (feature selection) categories to pursue the solutions utilized in solving the restrictions of NN computing. The NN computing system is expected to solve high-dimensional data, data overfitting, and strict FS problems. Hence, the Fruits-360 dataset is applied in the current article, that is, the variety of fruits, the sameness of color, and the differences in appearance features are utilized to examine the NN system accuracy, performance, and loss rate. Accordingly, there are 120 different kinds with a total of 20,860 fruit image datasets collected from AlexNet, GoogLeNet, and ResNet101, which were implemented in the CC assignment scheme proposed in this article. The results are employed to verify that the accuracy rate can be improved by reducing strict FS. Finally, the results of accuracy rate from the training held for the three NN frameworks are discussed. It was discovered that the GoogLeNet model presented the most significant FS performance. The demonstrated outcomes validate that the proposed CC assignment schemes are absolutely worthwhile in designing and choosing an NN training model for feature discrimination. From the simulation results, it has been observed that the FS-based CC assignment improves the accurate rate of recognition compared to the existing state-of-the-art approaches. Full article
(This article belongs to the Special Issue Feature Extraction and Forensic Image Analysis)
Show Figures

Figure 1

18 pages, 5128 KiB  
Article
Iris Image Compression Using Deep Convolutional Neural Networks
by Ehsaneddin Jalilian, Heinz Hofbauer and Andreas Uhl
Sensors 2022, 22(7), 2698; https://0-doi-org.brum.beds.ac.uk/10.3390/s22072698 - 31 Mar 2022
Cited by 11 | Viewed by 2262
Abstract
Compression is a way of encoding digital data so that it takes up less storage and requires less network bandwidth to be transmitted, which is currently an imperative need for iris recognition systems due to the large amounts of data involved, while deep [...] Read more.
Compression is a way of encoding digital data so that it takes up less storage and requires less network bandwidth to be transmitted, which is currently an imperative need for iris recognition systems due to the large amounts of data involved, while deep neural networks trained as image auto-encoders have recently emerged a promising direction for advancing the state-of-the-art in image compression, yet the generalizability of these schemes to preserve the unique biometric traits has been questioned when utilized in the corresponding recognition systems. For the first time, we thoroughly investigate the compression effectiveness of DSSLIC, a deep-learning-based image compression model specifically well suited for iris data compression, along with an additional deep-learning based lossy image compression technique. In particular, we relate Full-Reference image quality as measured in terms of Multi-scale Structural Similarity Index (MS-SSIM) and Local Feature Based Visual Security (LFBVS), as well as No-Reference images quality as measured in terms of the Blind Reference-less Image Spatial Quality Evaluator (BRISQUE), to the recognition scores as obtained by a set of concrete recognition systems. We further compare the DSSLIC model performance against several state-of-the-art (non-learning-based) lossy image compression techniques including: the ISO standard JPEG2000, JPEG, H.265 derivate BPG, HEVC, VCC, and AV1 to figure out the most suited compression algorithm which can be used for this purpose. The experimental results show superior compression and promising recognition performance of the model over all other techniques on different iris databases. Full article
(This article belongs to the Special Issue Feature Extraction and Forensic Image Analysis)
Show Figures

Figure 1

Back to TopTop