Search

Smartphone-based biometric authentication has been widely used in various applications. Among several biometric characteristics, fingerphoto biometrics captured from smartphones are gaining popularity owing to their usability, scalability across different smartphones, and reliable verification. However, fingerphoto verification systems are vulnerable to both direct and indirect attacks. In this work, we propose a novel method to generate morphing attacks on fingerphoto biometrics captured using smartphones. We introduce three different image-level fingerphoto morphing attack generation algorithms that can generate high-quality fingerphoto morphing images with minimum distortions. Extensive experiments were conducted on two datasets captured using different smartphones under various environmental conditions. The results demonstrate that the proposed morphing algorithms are highly vulnerable to commercial off-the-shelf and block-directional fingerprint verification systems. To effectively detect morphing attacks on fingerphoto biometrics, we propose the use of fingerphoto morphing attack detection algorithms that utilize both handcrafted and deep features. However, our detection results showed a high error rate in accurately detecting these types of attacks. [ABSTRACT FROM AUTHOR]

The vulnerability of face recognition systems to presentation attacks (also known as direct attacks or spoof attacks) has received a great deal of interest from the biometric community. The rapid evolution of face recognition systems into real-time applications has raised new concerns about their ability to resist presentation attacks, particularly in unattended application scenarios such as automated border control. The goal of a presentation attack is to subvert the face recognition system by presenting a facial biometric artifact. Popular face biometric artifacts include a printed photo, the electronic display of a facial photo, replaying video using an electronic display, and 3D face masks. These have demonstrated a high security risk for state-of-the-art face recognition systems. However, several presentation attack detection (PAD) algorithms (also known as countermeasures or antispoofing methods) have been proposed that can automatically detect and mitigate such targeted attacks. The goal of this survey is to present a systematic overview of the existing work on face presentation attack detection that has been carried out. This paper describes the various aspects of face presentation attacks, including different types of face artifacts, state-of-the-art PAD algorithms and an overview of the respective research labs working in this domain, vulnerability assessments and performance evaluation metrics, the outcomes of competitions, the availability of public databases for benchmarking new PAD algorithms in a reproducible manner, and finally a summary of the relevant international standardization in this field. Furthermore, we discuss the open challenges and future work that need to be addressed in this evolving field of biometrics. [ABSTRACT FROM AUTHOR]

With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods focus on 2D video and their performance in the presence of the challenges in 3D video, such as shadow areas associated with text and irregularly sized and shaped text, degrades. This paper proposes the first approach that successfully addresses the challenges of 3D video in addition to those of 2D. It employs a number of innovations, among which, the first is the Generalized Gradient Vector Flow (GGVF) for dominant points detection. The second is the Wavefront concept for text candidate point detection from those dominant points. In addition, an Adaptive B-Spline Polygon Curve Network (ABS-Net) is proposed for accurate text localization in 3D videos by constructing tight fitting bounding polygons using text candidate points. Extensive experiments on custom (3D video) and standard datasets (2D video and scene text) show that the proposed method is practical and useful, and overall outperforms existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The periocular region is used for authentication in the recent days under unconstrained acquisition in biometrics. This work presents two new feature extraction techniques to achieve robust and blur invariant biometric verification using periocular images captured using smartphones - (1) Deep Sparse Features (DSF) and (2) Deep Sparse Time Frequency Features (DeSTiFF). Both the approaches are based on extracting features via convolution of periocular images with a set of filters also referred as Deep Sparse Filters. The filters are learnt using natural image patches and sparse filtering approach. The DSF is obtained through convolution via Deep Sparse Filters. Further, convoluted responses are analyzed using Short Term Fourier Transform (STFT) to obtain time and frequency features of the images referred as DeSTIFF. The features obtained from the newly proposed feature extraction techniques are further represented in a collaborative subspace to achieve better verification performance. Both of the proposed feature extraction schemes are evaluated on two publicly available smartphone periocular databases and a new database (Visible Spectrum Periocular Image (VISPI) database) released with this article. The robustness of the proposed feature extraction is exemplified by comparing it with state-of-art approaches along with multiple deep networks where the improvement is evidently seen on large scale database with an average verification accuracy of Genuine Match Rate ≈ 98% at False Match Rate = 0.01%. We further support reproducible research by making the code and the database available for the academic research. • A new feature extraction scheme for periocular verification from smartphone data. • A new dataset of periocular images captured in 3 smartphones (publicly available). • Experimental evaluation and benchmarking with SOTA and deep learning approaches. • Measured quality metrics on newly introduced dataset. [ABSTRACT FROM AUTHOR]

Finger vein recognition is gaining popularity in the field of biometrics, yet the inter-operability of finger vein patterns has received limited attention. This study aims to fill this gap by introducing a cross-device finger vein dataset and evaluating the performance of finger vein recognition across devices using a classical method, a convolutional neural network, and our proposed patch-based convolutional auto-encoder (CAE). The findings emphasise the importance of standardisation of finger vein recognition, similar to that of fingerprints or irises, crucial for achieving inter-operability. Despite the inherent challenges of cross-device recognition, the proposed CAE architecture in this study demonstrates promising results in finger vein recognition, particularly in the context of cross-device comparisons. [ABSTRACT FROM AUTHOR]

• Machine learning models tailored for compressive strength of GD-reinforced CCs (GDRCCs). • Unique dataset covering GD properties and fabrication details of GDRCCs was compiled. • Artificial neural network excelled in prediction performance among investigated models. • The influencing factors on the compressive strength of GDRCCs were analyzed. • GDs lateral size, together with w/c and curing time, were the most influential factors. The potential reinforcement effect of graphene derivatives (GDs) on cementitious composites (CCs) has attracted significant attention. Previous studies, however, have produced varied results regarding the impact of GDs on CCs. This can be attributed to differences in the properties of GDs and the fabrication details of CCs reinforced by GDs. Experiments to explore these factors are both time-consuming and cost-ineffective. Additionally, no predictive model currently exists for assessing the influence of GDs on the compressive strength of CCs. In terms of Machine Learning (ML), most existing models focus on continuous parameters, including mixture design properties of CCs and reinforcing filler content, but ignore discontinuous parameters such as dispersion technique of GDs in CCs, curing type, and type of GDs. Compiling a unique dataset, this study tailors ML models to comprehensively explore the effect of GDs inclusion on the compressive strength of CCs, considering continuous and discontinuous parameters, including GD properties, fabrication details, and mixture design properties. The most used dispersion techniques and types of GDs were divided into different categories in this study. Moreover, the dataset included cement strength grade and fineness modules to distinguish between the effect of cement types' variety and GDs. Finally, the backwards elimination technique confirmed the necessity of such a customized dataset for trustworthy predictions. Artificial neural networks (ANN), decision trees, and support vector regressors could successfully investigate the impact of GDs' inclusion on the compressive strength of CCs, with ANN demonstrating superior prediction performance. Among the GDs properties, sensitivity analysis revealed that lateral size had the highest effect. Among the fabrication conditions, the dispersion technique had the greatest effect. Considering all investigated parameters, the water-to-cement ratio was considered the most influential, followed by lateral size and curing time. A low w/c significantly reduces the strength growth rate due to poor dispersion of GDs. [ABSTRACT FROM AUTHOR]

Classification of photos captured by different photographers is an important and challenging problem in knowledge-based and image processing. Monitoring and authenticating images uploaded on social media are essential, and verifying the source is one key piece of evidence. We present a novel framework for classifying photos of different photographers based on the combination of local features and deep learning models. The proposed work uses focused and defocused information in the input images to extract contextual information. The model estimates the weighted gradient and calculates entropy to strengthen context features. The focused and defocused information is fused to estimate cross-covariance and define a linear relationship between them. This relationship results in a feature matrix fed to Knowledge Enforcement Network (KEN) for obtaining representative features. Due to the strong discriminative ability of deep learning models, we employ the lightweight and accurate MobileNetV2. The output of KEN and MobileNetV2 is sent to a classifier for photographer classification. Experimental results of the proposed model on our dataset of 46 photographer classes (46234 images) and publicly available datasets of 41 photographer classes (218303 images) show that the method outperforms the existing techniques by 5%–10% on average. The dataset created for the experimental purpose will be made available upon publication. [ABSTRACT FROM AUTHOR]

The use of deep convolutional neural networks (CNNs) for single image super-resolution (SISR) in the recent years has led to numerous vision-based applications. Complementing the growing interest in the computer vision community embracing such networks, there is an unmet demand of reduced computational complexity. Despite being state-of-the-art for SISR tasks, CNN-based models need to be compact and efficient to account for applications running on low-cost deployment devices that have limited computation resources. While it is common to note that many state-of-the-art SISR approaches stack large number of convolutional layers in order to enhance their SR performance, there is proportional increase in the computational complexity. We propose a computationally efficient, compact and enhanced progressive network for SISR task which we hereafter refer as ComPrESRNet. The architectural changes employs a progressive learning strategy with a novel design of Enhanced densely connected parallel residual network (EDPRN) which simultaneously extracts rich features from the low-resolution (LR) observation while reducing the total number of parameters to 2.61M making it compact in nature that is suitable for low computational platform. The novelty of the proposed model stems from the inclusion of (i) densely connected ResBlock to extract rich features in the LR observation, (ii) extended global residual learning approach which stabilizes the training process effectively and also helps network to further improve the SR performance and (iii) progressive upscaling module which can generate an SR image of size × 4 and × 8 of original LR image. The robustness of the proposed method is further demonstrated on four different benchmark testing datasets consisting of natural scenes and urban landscape to exemplify the different applications. The superior performance over other state-of-the-art methods is also illustrated in this work for an upscaling factor × 4 and × 8 despite the lower computational complexity. The code of the paper is available at https://github.com/Vishal2188/Compactand-Progressive-Networkfor-Enhanced-SISR---ComPrESRNet. [ABSTRACT FROM AUTHOR]

With the increasing demand for fruits in the consumer market and to fulfill the needs of consumers, fruits are deliberately resorted to ripen artificially using industrial‐grade Calcium Carbide (CaC2) which has carcinogenic properties. The preferences to employ imaging sensing technology across the electromagnetic spectrum have gained noteworthy attention in recent times. This work presents the study to distinguish between natural and artificially ripened bananas using a multispectral imaging approach. Specifically, we carry out the analysis using multispectral images collected for natural and artificially ripened bananas in eight narrow spectrum bands spanning from visible (VIS) to near‐infrared (NIR) wavelength. Further, to present the contribution of each individual spectral band, we propose a scheme that extracts the relevant features from "convolution 5 (conv5)" and "fully connected 6 (fc6)" layers of convolutional neural network (CNN) based on AlexNet architecture and processes these features independently with collaborative representation classifier (CRC) in a robust manner. Essentially, we demonstrate the experimental classification accuracy based on multispectral images comprised of 5760 sample images using 10‐fold cross‐validation. Based on the proposed scheme, the highest average classification accuracy of about 88.82 ± 1.65% is obtained using our proposed approach presenting the significance of our work. Practical applications: The practical application of our proposed approach is to distinguish between natural and artificially ripened banana fruits in a market chain. Further, the approach is non‐invasive and non‐destructive based on multispectral imaging which has the potential to carry out real‐time quality analysis of bananas, especially to detect adulteration. [ABSTRACT FROM AUTHOR]

Identity documents (or IDs) play an important role in verifying the identity of a person with wide applications in banks, travel, video‐identification services and border controls. Replay or photocopied ID cards can be misused to pass ID control in unsupervised scenarios if the liveness of a person is not checked. To detect such presentation attacks on ID card verification process when presented virtually is a critical step for the biometric systems to assure authenticity. In this paper, a pixel‐wise supervision on DenseNet is proposed to detect presentation attacks of the printed and digitally replayed attacks. The authors motivate the approach to use pixel‐wise supervision to leverage minute cues on various artefacts such as moiré patterns and artefacts left by the printers. The baseline benchmark is presented using different handcrafted and deep learning models on a newly constructed in‐house database obtained from an operational system consisting of 886 users with 433 bona fide, 67 print and 366 display attacks. It is demonstrated that the proposed approach achieves better performance compared to handcrafted features and Deep Models with an Equal Error Rate of 2.22% and Bona fide Presentation Classification Error Rate (BPCER) of 1.83% and 1.67% at Attack Presentation Classification Error Rate of 5% and 10%. [ABSTRACT FROM AUTHOR]

Since the labels for medical images are challenging to collect in real scenarios, especially for rare diseases, fully supervised methods cannot achieve robust performance for clinical anomaly detection. Recent research tried to tackle this problem by training the anomaly detection framework using only normal data. Reconstruction-based methods, e.g., auto-encoder, achieved impressive performances in the anomaly detection task. However, most existing methods adopted the straightforward backbone architecture (i.e., encoder-and-decoder) for image reconstruction. The design of a skip connection, which can directly transfer information between the encoder and decoder, is rarely used. Since the existing U-Net has demonstrated the effectiveness of skip connections for image reconstruction tasks, in this paper, we first use the dynamic gating strategy to achieve the usage of skip connections in existing reconstruction-based anomaly detection methods and then propose a novel gating highway connection module to adaptively integrate skip connections into the framework and boost its anomaly detection performance, namely GatingAno. Furthermore, we formulate an auxiliary task, namely histograms of oriented gradients (HOG) prediction, to encourage the framework to exploit contextual information from fundus images in a self-driven manner, which increases the robustness of feature representation extracted from the healthy samples. Last but not least, to improve the model generalization for anomalous data, we introduce an adversarial strategy for the training of our multi-task framework. Experimental results on the publicly available datasets, i.e., IDRiD and ADAM, validate the superiority of our method for detecting abnormalities in retinal fundus images. The source code is available at https://github.com/WentianZhang-ML/GatingAno. • A gating highway connection module is proposed, which can be applied in a reconstruction-based anomaly detection method to exploit and constrain the intrinsic features during training for better anomaly detection performance. • We integrate histograms of oriented gradients (HOG) prediction as an auxiliary task in the reconstruction network to improve its sensitivity to abnormal images. • Adversarial learning is combined in our multi-task encoder–decoder network in the training phase to improve generalization ability for anomaly detection. • We evaluate our model on two publicly available datasets. The experimental results on image-level and pixel-level tasks prove the effectiveness of gating highway connections, HOG prediction, and adversarial learning for anomaly detection. [ABSTRACT FROM AUTHOR]

The intention of this position paper is to comment on the joint European Data Protection Supervisor (EDPS)‐Agencia Española de Protección de Datos (aepd) publication '14 Misunderstandings with regard to Biometric Identification and Authentication' that was published in June 2020 and to provide additional input to help with the better understanding of the issues raised in that publication. In particular, it aims to highlight some important missing information in the aforementioned publication. It is hoped that this paper will help with any future revision of the EDPS‐aepd publication, such that it includes a full picture of the current state of the art in biometrics and the availability of standards and privacy enhancing techniques. [ABSTRACT FROM AUTHOR]

In current Optical Coherence Tomography (OCT)-based fingerprint recognition systems, Presentation Attack Detection (PAD) and subsurface fingerprint reconstruction are treated as two independent branches, resulting in high computation and system building complexity. Therefore, this paper proposes a uniform representation model for simultaneous PAD and subsurface fingerprint reconstruction. A novel semantic segmentation network using attention mechanisms was designed to extract and segment multiple subsurface structures from real finger slices (i.e., B-scans). The latent codes derived from the network are directly used to effectively detect PA because they contain abundant subsurface biological information, which is independent of PA materials and has strong robustness for unknown PAs. Segmented subsurface structures were adopted to reconstruct multiple subsurface 2D fingerprints. Extensive experiments were carried out on an in-house database, which is the largest public OCT-based fingerprint database with 2449 volumes. PAD performance was evaluated by comparing the results of the existing methods with those of other segmentation networks. The proposed uniform representation model can obtain an accuracy (Acc) of 96.63%, which achieves a state-of-the-art performance. The effectiveness of subsurface reconstruction was evaluated from the segmentation and recognition results. In the segmentation experiments, the proposed method achieved the best results with an Intersection of Union (mIOU) of 0.834 and a Pixel Accuracy of 0.937. By comparing the recognition performance on surface 2D fingerprints (e.g., commercial and high-resolution), the lowest results with an Equal Error Rate (EER) of 2.25% by minutiae matching and an EER of 5.42% by pore matching are achieved, which indicates the excellent reconstruction capability of the proposed uniform representation model. • A uniform representation model for OCT-based fingerprint PAD and reconstruction. • A novel semantic segmentation network applying biological structure features. • High security PAD is achieved without using any presentation attacks for training. • Reliable reconstruction result is obtained with subsurface biological information. [ABSTRACT FROM AUTHOR]

Biometric verification systems are currently being deployed in numerous large-scale and everyday applications. It is hence of the utmost importance to protect the privacy of the enrolled subjects. Biometric template protection schemes are designed to protect biometric reference data in an irreversible and unlinkable manner, while maintaining key system properties like the accuracy or the speed. In past years, template protection schemes based on Bloom filters have been introduced and applied to various biometric characteristics. While the irreversibility and unlinkability of Bloom filter-based protection schemes have been shown, their application to any given unprotected template is not straightforward. In this article we present a methodology for the estimation of the main parameters of such schemes, based on a statistical analysis of the unprotected templates. Furthermore, in order to increase verification accuracy and privacy protection, a general approach for a protected weighted feature level fusion is proposed. In order to avoid biased results, the soundness of the estimation methodologies is confirmed for face, iris, fingerprint and fingervein over two totally different sets of publicly available databases. In addition, we show how the weighted feature level fusion preserves the accuracy of the unprotected score level fusion, while it adds privacy protection to the system. [ABSTRACT FROM AUTHOR]

• Presents a new approach for Generalizable Morphing Attack Detection by learning residuals from Encoder-Decoder network. • Proposes to explore complementary color spaces for learning morphing cues in an end-to-end manner. • Extensive experiments on 5 different databases with 2 landmark-based & 3 Generative Adversarial Network (GAN) based morphing. • Detailed explainability analysis of proposed approach using three different Class Activation Maps (CAM) for MAD. Face recognition systems (FRS) are vulnerable to different kinds of attacks. Morphing attack combines multiple face images to obtain a single face image that can verify equally against all contributing subjects. Various Morphing Attack Detection (MAD) algorithms have been proposed in recent years albeit limited generalizability. We present a new approach for MAD in this work with better generalization than state-of-the-art (SOTA) algorithms. We propose an end-to-end multi-stage encoder-decoder network for learning the residuals of morphing process to detect attacks. Leveraging the residuals, we learn an efficient classifier using cross-entropy loss and asymmetric loss. The use of asymmetric loss in our approach is motivated by imbalanced distribution of morphs and bona fides. An extensive set of experiments are conducted on five different datasets consisting of two landmark based and three Generative Adversarial Network (GAN) based morphs in various settings such as digital, print-scan and print-scan-compression. We first demonstrate a near-ideal performance of the proposed MAD with Detection Equal Error Rate (D-EER) of 0% in the best case and 2.58% in the worst case in the digital domain in closed-set protocol, i.e., known attacks. Further, we demonstrate the applicability of the proposed approach on 60 different combinations where the testing set contains unknown morphing attacks in open-set protocol to illustrate the generalization ability of our proposed approach. Through training the proposed approach on landmark-based morph generation data alone, we obtain an EER of 3.59% in the best case and 12.89% in the worst case for morphed images in the digital domain, reducing the error rates from 45.67% and 30.23% respectively, in open-set protocol. We further present an extensive analysis of the proposed approach through Class Activation Maps (CAM) to explain the decisions using by making use of three complementary CAM analysis. [ABSTRACT FROM AUTHOR]

The prime limitation of optical sensors is the need for external sources of illumination while capturing the scene. This prevents them from recognizing objects in extreme conditions, such as insufficient illumination or severe weather (e.g., under fog or smoke). The thermal imaging sensors have been introduced to circumvent this deficiency, which acquires the image based on thermal radiation emitted by the objects. The technological advancement in thermal imaging enables the visualization of objects beyond the visible range that promotes its use in many principal applications, such as military, medical, agriculture, etc. However, hardware point of view, the cost of a thermal camera is prohibitively higher than that of an equivalent optical sensor. This led to employ software-driven approaches called super-resolution (SR) to enhance the resolution of given thermal images. We propose a deep neural network architecture referred to as "ThermISRnet" as the extension of our earlier winner architecture in the Perception Beyond the Visible Spectrum (PBVS) thermal SR challenge. We use a progressive upscaling strategy with asymmetrical residual learning in the network, which is computationally efficient for different upscaling factors such as ×2, ×3, and ×4. The proposed architecture consists of different modules for low- and high-frequency feature extraction along with upsampling blocks. The effectiveness of the proposed architecture in ThermISRnet is verified by evaluating it with different datasets. The obtained results indicate superior performance as compared to other state-of-the-art SR methods. [ABSTRACT FROM AUTHOR]

Augmented and virtual reality deployment is finding increasing use in novel applications. Some of these emerging and foreseen applications allow the users to access sensitive information and functionalities. Head Mounted Displays (HMD) are used to enable such applications and they typically include eye facing cameras to facilitate advanced user interaction. Such integrated cameras capture iris and partial periocular region during the interaction. This work investigates the possibility of using the captured ocular images from integrated cameras from HMD devices for biometric verification, taking into account the expected limited computational power of such devices. Such an approach can allow user to be verified in a manner that does not require any special and explicit user action. In addition to our comprehensive analyses, we present a light weight, yet accurate, segmentation solution for the ocular region captured from HMD devices. Further, we benchmark a number of well-established iris and periocular verification methods along with an in-depth analysis on the impact of iris sample selection and its effect on iris recognition performance for HMD devices. To the end, we also propose and validate an identity-preserving synthetic ocular image generation mechanism that can be used for large scale data generation for training purposes or attack generation purposes. We establish the realistic image quality of generated images with high fidelity and identity preserving capabilities through benchmarking them for iris and periocular verification. • Exploring biometric verification from the eye-facing camera in head mounted displays. • Benchmarking a range of iris and periocular recognition approaches. • Presenting and evaluating highly-efficient eye regions segmentation solution. • Realistic and identity-preserving generation of eye images from semantic segmentation. [ABSTRACT FROM AUTHOR]