Nothing Special   »   [go: up one dir, main page]
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.9
2.7
Journals
J. Imaging
Special Issues
Image Processing and Biometric Facial Analysis
share announcement

Image Processing and Biometric Facial Analysis

A special issue of Journal of Imaging (ISSN 2313-433X). This special issue belongs to the section "Biometrics, Forensics, and Security".

Deadline for manuscript submissions: closed (20 December 2022) | Viewed by 6051

Special Issue Editor

Dr. Mohamed Dahmane

E-Mail Website
Guest Editor
CRIM-Computer Research Institute of Montreal, Montreal, QC H3N 1M3, Canada
Interests: computer vision; image processing; deep learning; intelligent video surveillance; face analysis; face recognition; emotion recognition; fake image detection
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

With the advanced developments in computer vision, imaging-based sensors have become more appropriate for intelligent surveillance and people accounting. Several research works in video analysis are based on static images, while there is important temporal information to be inferred from the full image sequence. Static-based methods need adaptation to be effective in the case of continuous streams in a single- or multiple-camera setting. The literature has identified a static face database as the most influential published face dataset. Other more recent works were drawn around massively annotated static face datasets.

This Special Issue of the Journal of Imaging aims to feature the relative contribution of facial dynamics and the varied information present in the full image sequence. Some existing datasets of labeled face videos are useful for building unconstrained approaches of face recognition from videos. The objective is to design more functional solutions in the context of intelligent surveillance by exploiting the dynamic of the face that leverages higher-level information from threads of consistency through the scene.

Dr. Mohamed Dahmane
Guest Editor

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. Journal of Imaging is an international peer-reviewed open access monthly 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 1800 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

  • face recognition
  • intelligent surveillance
  • video analysis
  • face-based tracking
  • person counting
  • image processing
  • computer 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

15 pages, 1139 KiB  
Article
Masked Face Recognition Using Histogram-Based Recurrent Neural Network
by Wei-Jie Lucas Chong, Siew-Chin Chong and Thian-Song Ong
J. Imaging 2023, 9(2), 38; https://doi.org/10.3390/jimaging9020038 - 8 Feb 2023
Cited by 4 | Viewed by 2749
Abstract
Masked face recognition (MFR) is an interesting topic in which researchers have tried to find a better solution to improve and enhance performance. Recently, COVID-19 caused most of the recognition system fails to recognize facial images since the current face recognition cannot accurately [...] Read more.
Masked face recognition (MFR) is an interesting topic in which researchers have tried to find a better solution to improve and enhance performance. Recently, COVID-19 caused most of the recognition system fails to recognize facial images since the current face recognition cannot accurately capture or detect masked face images. This paper introduces the proposed method known as histogram-based recurrent neural network (HRNN) MFR to solve the undetected masked face problem. The proposed method includes the feature descriptor of histograms of oriented gradients (HOG) as the feature extraction process and recurrent neural network (RNN) as the deep learning process. We have proven that the combination of both approaches works well and achieves a high true acceptance rate (TAR) of 99 percent. In addition, the proposed method is designed to overcome the underfitting problem and reduce computational burdens with large-scale dataset training. The experiments were conducted on two benchmark datasets which are RMFD (Real-World Masked Face Dataset) and Labeled Face in the Wild Simulated Masked Face Dataset (LFW-SMFD) to vindicate the viability of the proposed HRNN method. Full article
(This article belongs to the Special Issue Image Processing and Biometric Facial Analysis)
►▼ Show Figures

Figure 1

Figure 1
<p>Overall process of the proposed method.</p> Full article ">Figure 2
<p>Training performance with proposed method in RMFD dataset.</p> Full article ">Figure 3
<p>Training performance with proposed method in LFW-SMFD dataset.</p> Full article ">
19 pages, 7914 KiB  
Article
Analysis of Real-Time Face-Verification Methods for Surveillance Applications
by Filiberto Perez-Montes, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Gibran Benitez-Garcia, Lidia Prudente-Tixteco and Osvaldo Lopez-Garcia
J. Imaging 2023, 9(2), 21; https://doi.org/10.3390/jimaging9020021 - 18 Jan 2023
Cited by 3 | Viewed by 2465
Abstract
In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient [...] Read more.
In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. Full article
(This article belongs to the Special Issue Image Processing and Biometric Facial Analysis)
►▼ Show Figures

Figure 1

Figure 1
<p>Bottleneck residual blocks in MobileFaceNet [<a href="#B41-jimaging-09-00021" class="html-bibr">41</a>].</p> Full article ">Figure 2
<p>Architectural representation of standard and composite scaling methods. (<b>a</b>) ConvNet generic, (<b>b</b>) ConvNet with width scaling, (<b>c</b>) ConvNet with Depth scaling, (<b>d</b>) ConvNet with resolution scaling, and (<b>e</b>) ConvNet with compound scaling.</p> Full article ">Figure 3
<p>Representation of a GhostNet module [<a href="#B12-jimaging-09-00021" class="html-bibr">12</a>].</p> Full article ">Figure 4
<p>Examples of the pairs chosen for the proposed evaluation subset.</p> Full article ">Figure 5
<p>Example of the five levels of resolution in the proposed evaluation subset.</p> Full article ">Figure 6
<p>Examples of the occlusions found in the faces not included.</p> Full article ">Figure 7
<p>Example of image pairs with facial pose estimation error (attributed to the [0°; 20°] interval).</p> Full article ">Figure 8
<p>Example of CPLFW image pairs incorrectly classified by EfficientNet-B0.</p> Full article ">Figure 9
<p>Example of QMUL-SurvFace image pairs incorrectly classified by EfficientNet-B0.</p> Full article ">Figure 10
<p>Example of evaluation subset pairs incorrectly classified by MobileFaceNet.</p> Full article ">Figure 11
<p>Plot results for each angle range with different resolution levels, where the following intervals are shown: (<b>a</b>) <math display="inline"><semantics> <mrow> <mo>[</mo> <msup> <mn>0</mn> <mo>∘</mo> </msup> <mo>;</mo> <msup> <mn>20</mn> <mo>∘</mo> </msup> <mo>]</mo> </mrow> </semantics></math>, (<b>b</b>) <math display="inline"><semantics> <mrow> <mo>[</mo> <msup> <mn>20</mn> <mo>∘</mo> </msup> <mo>;</mo> <msup> <mn>40</mn> <mo>∘</mo> </msup> <mo>]</mo> </mrow> </semantics></math>, (<b>c</b>) <math display="inline"><semantics> <mrow> <mo>[</mo> <msup> <mn>40</mn> <mo>∘</mo> </msup> <mo>;</mo> <msup> <mn>60</mn> <mo>∘</mo> </msup> <mo>]</mo> </mrow> </semantics></math>, (<b>d</b>) <math display="inline"><semantics> <mrow> <mo>[</mo> <msup> <mn>60</mn> <mo>∘</mo> </msup> <mo>;</mo> <msup> <mn>80</mn> <mo>∘</mo> </msup> <mo>]</mo> </mrow> </semantics></math>, and (<b>e</b>) <math display="inline"><semantics> <mrow> <mo>[</mo> <msup> <mn>80</mn> <mo>∘</mo> </msup> <mo>;</mo> <msup> <mn>180</mn> <mo>∘</mo> </msup> <mo>]</mo> </mrow> </semantics></math>. Pixel resolutions of 14 × 14, 28 × 28, 42 × 42, 84 × 84, and 112 × 112 are used in all intervals.</p> Full article ">Figure 12
<p>Examples of evaluation subset pairs per resolution interval incorrectly classified by MobileFaceNet.</p> Full article ">
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