Special Issue "Advanced Biometrics with Deep Learning"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (31 December 2019).

Special Issue Editors

Prof. Dr. Andrew Teoh Beng Jin
Website
Guest Editor
School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, South Korea
Interests: biometrics; biometric security; machine learning
Prof. Dr. Lu Leng
Website
Guest Editor
School of Software, Nanchang Hangkong University, P. R. China
Interests: Biometrics, Biometric Security, Machine Learning

Special Issue Information

Dear Colleagues,

Biometrics such as fingerprint, iris, face, hand print, hand vein, speech and gait recognition etc. as a means of identity management has become commonplace nowadays for various applications. Biometric systems follow a typical pipeline that is composed of separate preprocessing, feature extraction and classification. Deep learning as a data-driven representation learning approach has been shown to be a promising alternative to conventional data-agnostic and handcrafted pre-processing and feature extraction for biometric systems. Furthermore, deep learning offers an end-to-end learning paradigm to unify preprocessing, feature extraction and recognition based solely on biometric data. The objective of this Special Issue is to invite high-quality, state-of-the-art research papers that deal with challenging issues in advanced deep learning-based biometric systems. We solicit the original papers of unpublished and completed research that are not currently under review by any other conference/magazine/journal. Topics of interest include, but are not limited to:

  • Biometric signal, image and video preprocessing based on deep learning
  • Biometric feature extraction based on deep learning
  • Biometric classification and recognition based on deep learning
  • End-to-end deep learning for biometric systems
  • Multimodal biometrics based on deep learning
  • Spoof detection based on deep learning
  • Biometric encryption and template protection based on deep learning.

Prof. Dr. Andrew Teoh Beng Jin
Prof. Dr. Lu Leng
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 papers will be 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. Applied Sciences 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 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.

Published Papers (12 papers)

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

Research

Open AccessArticle
Fast and Accurate Algorithm for ECG Authentication Using Residual Depthwise Separable Convolutional Neural Networks
Appl. Sci. 2020, 10(9), 3304; https://doi.org/10.3390/app10093304 - 09 May 2020
Abstract
The electrocardiogram (ECG) is relatively easy to acquire and has been used for reliable biometric authentication. Despite growing interest in ECG authentication, there are still two main problems that need to be tackled, i.e., the accuracy and processing speed. Therefore, this paper proposed [...] Read more.
The electrocardiogram (ECG) is relatively easy to acquire and has been used for reliable biometric authentication. Despite growing interest in ECG authentication, there are still two main problems that need to be tackled, i.e., the accuracy and processing speed. Therefore, this paper proposed a fast and accurate ECG authentication utilizing only two stages, i.e., ECG beat detection and classification. By minimizing time-consuming ECG signal pre-processing and feature extraction, our proposed two-stage algorithm can authenticate the ECG signal around 660 μs. Hamilton’s method was used for ECG beat detection, while the Residual Depthwise Separable Convolutional Neural Network (RDSCNN) algorithm was used for classification. It was found that between six and eight ECG beats were required for authentication of different databases. Results showed that our proposed algorithm achieved 100% accuracy when evaluated with 48 patients in the MIT-BIH database and 90 people in the ECG ID database. These results showed that our proposed algorithm outperformed other state-of-the-art methods. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
A Novel P300 Classification Algorithm Based on a Principal Component Analysis-Convolutional Neural Network
Appl. Sci. 2020, 10(4), 1546; https://doi.org/10.3390/app10041546 - 24 Feb 2020
Cited by 1
Abstract
Aiming at enhancing the classification accuracy of P300 Electroencephalogram signals in a non-invasive brain–computer interface system, a novel P300 electroencephalogram signals classification algorithm is proposed which is based on improved convolutional neural network. In the data preprocessing part, the proposed P300 classification algorithm [...] Read more.
Aiming at enhancing the classification accuracy of P300 Electroencephalogram signals in a non-invasive brain–computer interface system, a novel P300 electroencephalogram signals classification algorithm is proposed which is based on improved convolutional neural network. In the data preprocessing part, the proposed P300 classification algorithm used the Principal Component Analysis algorithm to not only remove the noise and artifacts in the data, but also increase the data processing speed. Furthermore, the proposed P300 classification algorithm employed the parallel convolution method to improve the traditional convolutional neural network framework, which can increase the network depth and improve the network’s ability to classify P300 electroencephalogram signals. The proposed algorithm was evaluated by two datasets (the dataset from the competition and the dataset from the laboratory). The results show that, in the dataset I, the proposed P300 classification algorithm could obtain accuracy rates higher than 95%, and achieve one of the best performances in four classification algorithms, while, in the dataset II, the proposed P300 classification algorithm can get accuracy rates higher than 90%, and is superior to the other three algorithms in all ten subjects. These demonstrated the effectiveness of the proposed algorithm. The proposed classification algorithm can be applied in the actual brain–computer interface systems to help people with disability in the daily lives. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Improved Single Sample Per Person Face Recognition via Enriching Intra-Variation and Invariant Features
Appl. Sci. 2020, 10(2), 601; https://doi.org/10.3390/app10020601 - 14 Jan 2020
Abstract
Face recognition using a single sample per person is a challenging problem in computer vision. In this scenario, due to the lack of training samples, it is difficult to distinguish between inter-class variations caused by identity and intra-class variations caused by external factors [...] Read more.
Face recognition using a single sample per person is a challenging problem in computer vision. In this scenario, due to the lack of training samples, it is difficult to distinguish between inter-class variations caused by identity and intra-class variations caused by external factors such as illumination, pose, etc. To address this problem, we propose a scheme to improve the recognition rate by both generating additional samples to enrich the intra-variation and eliminating external factors to extract invariant features. Firstly, a 3D face modeling module is proposed to recover the intrinsic properties of the input image, i.e., 3D face shape and albedo. To obtain the complete albedo, we come up with an end-to-end network to estimate the full albedo UV map from incomplete textures. The obtained albedo UV map not only eliminates the influence of the illumination, pose, and expression, but also retains the identity information. With the help of the recovered intrinsic properties, we then generate images under various illuminations, expressions, and poses. Finally, the albedo and the generated images are used to assist single sample per person face recognition. The experimental results on Face Recognition Technology (FERET), Labeled Faces in the Wild (LFW), Celebrities in Frontal-Profile (CFP) and other face databases demonstrate the effectiveness of the proposed method. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Double Additive Margin Softmax Loss for Face Recognition
Appl. Sci. 2020, 10(1), 60; https://doi.org/10.3390/app10010060 - 19 Dec 2019
Abstract
Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line of research is to incorporate an angular margin in the [...] Read more.
Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line of research is to incorporate an angular margin in the original softmax loss functions for obtaining discriminative deep features during the training of DCNNs. In this paper we propose a novel loss function, termed as double additive margin Softmax loss (DAM-Softmax). The presented loss has a clearer geometrical explanation and can obtain highly discriminative features for face recognition. Extensive experimental evaluation of several recent state-of-the-art softmax loss functions are conducted on the relevant face recognition benchmarks, CASIA-Webface, LFW, CALFW, CPLFW, and CFP-FP. We show that the proposed loss function consistently outperforms the state-of-the-art. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Deep Learning for Facial Recognition on Single Sample per Person Scenarios with Varied Capturing Conditions
Appl. Sci. 2019, 9(24), 5474; https://doi.org/10.3390/app9245474 - 13 Dec 2019
Abstract
Single sample per person verification has received considerable attention because of its relevance in security, surveillance and border crossing applications. Nowadays, e-voting and bank of the future solutions also join this scenario, opening this field of research to mobile and low resources devices. [...] Read more.
Single sample per person verification has received considerable attention because of its relevance in security, surveillance and border crossing applications. Nowadays, e-voting and bank of the future solutions also join this scenario, opening this field of research to mobile and low resources devices. These scenarios are characterised by the availability of a single image during the enrolment of the users into the system, so they require a solution able to extract knowledge from previous experiences and similar environments. In this study, two deep learning models for face recognition, which were specially designed for applications on mobile devices and resources saving environments, were described and evaluated together with two publicly available models. This evaluation aimed not only to provide a fair comparison between the models but also to measure to what extent a progressive reduction of the model size influences the obtained results.The models were assessed in terms of accuracy and size with the aim of providing a detailed evaluation which covers as many environmental conditions and application requirements as possible. To this end, a well-defined evaluation protocol and a great number of varied databases, public and private, were used. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Real-Time Pre-Identification and Cascaded Detection for Tiny Faces
Appl. Sci. 2019, 9(20), 4344; https://doi.org/10.3390/app9204344 - 15 Oct 2019
Cited by 1
Abstract
Although the face detection problem has been studied for decades, searching tiny faces in the whole image is still a challenging task, especially in low-resolution images. Traditional face detection methods are based on hand-crafted features, but the features of tiny faces are different [...] Read more.
Although the face detection problem has been studied for decades, searching tiny faces in the whole image is still a challenging task, especially in low-resolution images. Traditional face detection methods are based on hand-crafted features, but the features of tiny faces are different from those of normal-sized faces, and thus the detection robustness cannot be guaranteed. In order to alleviate the problem in existing methods, we propose a pre-identification mechanism and a cascaded detector (PMCD) for tiny-face detection. This pre-identification mechanism can greatly reduce background and other irrelevant information. The cascade detector is designed with two stages of deep convolutional neural network (CNN) to detect tiny faces in a coarse-to-fine manner, i.e., the face-area candidates are pre-identified as region of interest (RoI) based on a real-time pedestrian detector and the pre-identification mechanism, the set of RoI candidates is the input of the second sub-network instead of the whole image. Benefiting from the above mechanism, the second sub-network is designed as a shallow network which can keep high accuracy and real-time performance. The accuracy of PMCD is at least 4% higher than the other state-of-the-art methods on detecting tiny faces, while keeping real-time performance. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN
Appl. Sci. 2019, 9(13), 2709; https://doi.org/10.3390/app9132709 - 03 Jul 2019
Abstract
Periocular recognition remains challenging for deployments in the unconstrained environments. Therefore, this paper proposes an RGB-OCLBCP dual-stream convolutional neural network, which accepts an RGB ocular image and a colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OCLBCP) for periocular recognition in the [...] Read more.
Periocular recognition remains challenging for deployments in the unconstrained environments. Therefore, this paper proposes an RGB-OCLBCP dual-stream convolutional neural network, which accepts an RGB ocular image and a colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OCLBCP) for periocular recognition in the wild. The proposed network aggregates the RGB image and the OCLBCP descriptor by using two distinct late-fusion layers. We demonstrate that the proposed network benefits from the RGB image and thee OCLBCP descriptor can gain better recognition performance. A new database, namely an Ethnic-ocular database of periocular in the wild, is introduced and shared for benchmarking. In addition, three publicly accessible databases, namely AR, CASIA-iris distance and UBIPr, have been used to evaluate the proposed network. When compared against several competing networks on these databases, the proposed network achieved better performances in both recognition and verification tasks. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Hierarchical Feature Aggregation from Body Parts for Misalignment Robust Person Re-Identification
Appl. Sci. 2019, 9(11), 2255; https://doi.org/10.3390/app9112255 - 31 May 2019
Abstract
In this work, we focus on the misalignment problem in person re-identification. Human body parts commonly contain discriminative local representations relevant with identity recognition. However, the representations are easily affected by misalignment that is due to varying poses or poorly detected bounding boxes. [...] Read more.
In this work, we focus on the misalignment problem in person re-identification. Human body parts commonly contain discriminative local representations relevant with identity recognition. However, the representations are easily affected by misalignment that is due to varying poses or poorly detected bounding boxes. We thus present a two-branch Deep Joint Learning (DJL) network, where the local branch generates misalignment robust representations by pooling the features around the body parts, while the global branch generates representations from a holistic view. A Hierarchical Feature Aggregation mechanism is proposed to aggregate different levels of visual patterns within body part regions. Instead of aggregating each pooled body part features from multi-layers with equal weight, we assign each with the learned optimal weight. This strategy also mitigates the scale differences among multi-layers. By optimizing the global and local features jointly, the DJL network further enhances the discriminative capability of the learned hybrid feature. Experimental results on Market-1501 and CUHK03 datasets show that our method could effectively handle the misalignment induced intra-class variations and yield competitive accuracy particularly on poorly aligned pedestrian images. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Finger-Vein Verification Based on LSTM Recurrent Neural Networks
Appl. Sci. 2019, 9(8), 1687; https://doi.org/10.3390/app9081687 - 24 Apr 2019
Cited by 3
Abstract
Finger-vein biometrics has been extensively investigated for personal verification. A challenge is that the finger-vein acquisition is affected by many factors, which results in many ambiguous regions in the finger-vein image. Generally, the separability between vein and background is poor in such regions. [...] Read more.
Finger-vein biometrics has been extensively investigated for personal verification. A challenge is that the finger-vein acquisition is affected by many factors, which results in many ambiguous regions in the finger-vein image. Generally, the separability between vein and background is poor in such regions. Despite recent advances in finger-vein pattern segmentation, current solutions still lack the robustness to extract finger-vein features from raw images because they do not take into account the complex spatial dependencies of vein pattern. This paper proposes a deep learning model to extract vein features by combining the Convolutional Neural Networks (CNN) model and Long Short-Term Memory (LSTM) model. Firstly, we automatically assign the label based on a combination of known state of the art handcrafted finger-vein image segmentation techniques, and generate various sequences for each labeled pixel along different directions. Secondly, several Stacked Convolutional Neural Networks and Long Short-Term Memory (SCNN-LSTM) models are independently trained on the resulting sequences. The outputs of various SCNN-LSTMs form a complementary and over-complete representation and are conjointly put into Probabilistic Support Vector Machine (P-SVM) to predict the probability of each pixel of being foreground (i.e., vein pixel) given several sequences centered on it. Thirdly, we propose a supervised encoding scheme to extract the binary vein texture. A threshold is automatically computed by taking into account the maximal separation between the inter-class distance and the intra-class distance. In our approach, the CNN learns robust features for vein texture pattern representation and LSTM stores the complex spatial dependencies of vein patterns. So, the pixels in any region of a test image can then be classified effectively. In addition, the supervised information is employed to encode the vein patterns, so the resulting encoding images contain more discriminating features. The experimental results on one public finger-vein database show that the proposed approach significantly improves the finger-vein verification accuracy. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Unsupervised Learning of Total Variability Embedding for Speaker Verification with Random Digit Strings
Appl. Sci. 2019, 9(8), 1597; https://doi.org/10.3390/app9081597 - 17 Apr 2019
Cited by 1
Abstract
Recently, the increasing demand for voice-based authentication systems has encouraged researchers to investigate methods for verifying users with short randomized pass-phrases with constrained vocabulary. The conventional i-vector framework, which has been proven to be a state-of-the-art utterance-level feature extraction technique for speaker verification, [...] Read more.
Recently, the increasing demand for voice-based authentication systems has encouraged researchers to investigate methods for verifying users with short randomized pass-phrases with constrained vocabulary. The conventional i-vector framework, which has been proven to be a state-of-the-art utterance-level feature extraction technique for speaker verification, is not considered to be an optimal method for this task since it is known to suffer from severe performance degradation when dealing with short-duration speech utterances. More recent approaches that implement deep-learning techniques for embedding the speaker variability in a non-linear fashion have shown impressive performance in various speaker verification tasks. However, since most of these techniques are trained in a supervised manner, which requires speaker labels for the training data, it is difficult to use them when a scarce amount of labeled data is available for training. In this paper, we propose a novel technique for extracting an i-vector-like feature based on the variational autoencoder (VAE), which is trained in an unsupervised manner to obtain a latent variable representing the variability within a Gaussian mixture model (GMM) distribution. The proposed framework is compared with the conventional i-vector method using the TIDIGITS dataset. Experimental results showed that the proposed method could cope with the performance deterioration caused by the short duration. Furthermore, the performance of the proposed approach improved significantly when applied in conjunction with the conventional i-vector framework. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
Attention-Based LSTM Algorithm for Audio Replay Detection in Noisy Environments
Appl. Sci. 2019, 9(8), 1539; https://doi.org/10.3390/app9081539 - 13 Apr 2019
Abstract
Even though audio replay detection has improved in recent years, its performance is known to severely deteriorate with the existence of strong background noises. Given the fact that different frames of an utterance have different impacts on the performance of spoofing detection, this [...] Read more.
Even though audio replay detection has improved in recent years, its performance is known to severely deteriorate with the existence of strong background noises. Given the fact that different frames of an utterance have different impacts on the performance of spoofing detection, this paper introduces attention-based long short-term memory (LSTM) to extract representative frames for spoofing detection in noisy environments. With this attention mechanism, the specific and representative frame-level features will be automatically selected by adjusting their weights in the framework of attention-based LSTM. The experiments, conducted using the ASVspoof 2017 dataset version 2.0, show that the equal error rate (EER) of the proposed approach was about 13% lower than the constant Q cepstral coefficients-Gaussian mixture model (CQCC-GMM) baseline in noisy environments with four different signal-to-noise ratios (SNR). Meanwhile, the proposed algorithm also improved the performance of traditional LSTM on audio replay detection systems in noisy environments. Experiments using bagging with different frame lengths were also conducted to further improve the proposed approach. Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Open AccessArticle
A Novel Heart Rate Robust Method for Short-Term Electrocardiogram Biometric Identification
Appl. Sci. 2019, 9(1), 201; https://doi.org/10.3390/app9010201 - 08 Jan 2019
Cited by 6
Abstract
In the past decades, the electrocardiogram (ECG) has been investigated as a promising biometric by exploiting the subtle discrepancy of ECG signals between subjects. However, the heart rate (HR) for one subject may vary because of physical activities or strong emotions, leading to [...] Read more.
In the past decades, the electrocardiogram (ECG) has been investigated as a promising biometric by exploiting the subtle discrepancy of ECG signals between subjects. However, the heart rate (HR) for one subject may vary because of physical activities or strong emotions, leading to the problem of ECG signal variation. This variation will significantly decrease the performance of the identification task. Particularly for short-term ECG signal without many heartbeats, the hardly measured HR makes the identification task even more challenging. This study aims to propose a novel method suitable for short-term ECG signal identification. In particular, an improved HR-free resampling strategy is proposed to minimize the influence of HR variability during heartbeat processing. For feature extraction, the Principal Component Analysis Network (PCANet) is implemented to determine the potential difference between subjects. The proposed method is evaluated using a public ECG-ID database that contains various HR data for some subjects. Experimental results show that the proposed method is robust to HR change and can achieve high subject identification accuracy (94.4%) on ECG signals with only five heartbeats. Thus, the proposed method has the potential for application to systems that use short-term ECG signals for identification (e.g., wearable devices). Full article
(This article belongs to the Special Issue Advanced Biometrics with Deep Learning)
Show Figures

Figure 1

Back to TopTop