Showing papers on "Fingerprint recognition published in 2020"

Portable Food-Freshness Prediction Platform Based on Colorimetric Barcode Combinatorics and Deep Convolutional Neural Networks

Abstract: Artificial scent screening systems (known as electronic noses, E-noses) have been researched extensively. A portable, automatic, and accurate, real-time E-nose requires both robust cross-reactive sensing and fingerprint pattern recognition. Few E-noses have been commercialized because they suffer from either sensing or pattern-recognition issues. Here, cross-reactive colorimetric barcode combinatorics and deep convolutional neural networks (DCNNs) are combined to form a system for monitoring meat freshness that concurrently provides scent fingerprint and fingerprint recognition. The barcodes-comprising 20 different types of porous nanocomposites of chitosan, dye, and cellulose acetate-form scent fingerprints that are identifiable by DCNN. A fully supervised DCNN trained using 3475 labeled barcode images predicts meat freshness with an overall accuracy of 98.5%. Incorporating DCNN into a smartphone application forms a simple platform for rapid barcode scanning and identification of food freshness in real time. The system is fast, accurate, and non-destructive, enabling consumers and all stakeholders in the food supply chain to monitor food freshness.

A Novel Weber Local Binary Descriptor for Fingerprint Liveness Detection

Abstract: In recent years, fingerprint authentication systems have been extensively deployed in various applications, including attendance systems, authentications on smartphones, mobile payment authorizations, as well as various safety certifications. However, similar to the other biometric identification technologies, fingerprint recognition is vulnerable to artificial replicas made from cheap materials, such as silicon, gelatin, etc. Thus, it is especially necessary to distinguish whether a given fingerprint is a live or a spoof one prior to such authentication. In order to solve the problems above, a novel local descriptor named Weber local binary descriptor for fingerprint liveness detection (FLD) has been proposed in this paper. The method consists of two components: the local binary differential excitation component that extracts intensity-variance features and the local binary gradient orientation component that extracts orientation features. The co-occurrence probability of the two components is calculated to construct a discriminative feature vector, which is fed into support vector machine (SVM) classifiers. The effectiveness of the proposed method is intuitively analyzed on the image samples and numerically demonstrated by Mahalanobis distance. Experiments are performed on two public databases from FLD competitions from 2011 and 2013. The results have proved that the proposed method obtains the best detection accuracy among the existing image local descriptors in FLD.

Deep Residual Network With Adaptive Learning Framework for Fingerprint Liveness Detection

Abstract: Today, fingerprint recognition technology has aroused wide attention in the society, especially in the application of identity authentication with a smartphone as a carrier. However, the disadvantage of these devices is that the identification sensors are vulnerable to spoofing attacks from artificial replicas made from clay, gelatin, silicon, etc. To resolve it, a feasible anti-deception countermeasure, called fingerprint liveness detection (FLD), has been proposed. Different from most shallow feature methods, the deep convolutional neural network (DCNN)-based FLD methods have been widely explored with the properties of fast operation, few parameters, and end-to-end feature self-learning. Meanwhile, DCNN faces a pair of contradictory problems, on the one hand, the training accuracy will keep rising with the increasement of multilayer perceptron (MLP), finally tends to a stable value. Continue to increase the number of MLP, results will decline. Much research, on the other hand, shows that the number of MLP is the foundation for realizing a high performance detection. Hereby, we apply deep residual network (DRN) to FLD for the first time to solve the contradiction mentioned in this paper. Next, to eliminate the interference of invalid regions of given images, a region-of-interest (ROI) extraction algorithm is put forward. Afterward, to avoid the parameters learned plunging into local optimization, adaptive learning-based DRNs (ALDRNs), which automatically adjust the learning rate if those monitoring parameters (verification accuracy) are stable, are explored. Finally, we propose a novel texture enhancement based on the local gradient pattern (LGP) method to improve the generalization of a model classifier as well. Experimental results on three benchmark data sets: LivDet 2011, 2013, and 2015, show that our results outperform the state-of-the-art FLD methods.

WiFi and Vision-Integrated Fingerprint for Smartphone-Based Self-Localization in Public Indoor Scenes

Abstract: Smartphone-based indoor localization systems are increasingly needed in various types of applications. This article proposes a novel WiFi and vision-integrated fingerprint (Wi-Vi fingerprint) for accurate and robust indoor localization. The method consists of two steps of fingerprint mapping and fingerprint localization. In the mapping step, the Wi-Vi fingerprints for all the sampling sites are computed by using EXIT signs as landmarks. In the localization step, a multiscale localization strategy is proposed, which includes coarse localization from weighted access points (WAPs)-based WiFi matching, the Gaussian weighted KNN (GW-KNN)-based image-level localization from holistic visual features, and finally, the metric localization for refinement. The proposed method has been tested in an indoor office building of 12 000 m2 and a mega-mall of 7200 m2 with different types of smartphones. The experimental results demonstrate that the proposed method can achieve 95% and 98% site recognition rates from image-level localization. The final localization errors after metric localization are less than a half meter on average.

Discrete Transforms and Matrix Rotation Based Cancelable Face and Fingerprint Recognition for Biometric Security Applications.

Abstract: The security of information is necessary for the success of any system. So, there is a need to have a robust mechanism to ensure the verification of any person before allowing him to access the stored data. So, for purposes of increasing the security level and privacy of users against attacks, cancelable biometrics can be utilized. The principal objective of cancelable biometrics is to generate new distorted biometric templates to be stored in biometric databases instead of the original ones. This paper presents effective methods based on different discrete transforms, such as Discrete Fourier Transform (DFT), Fractional Fourier Transform (FrFT), Discrete Cosine Transform (DCT), and Discrete Wavelet Transform (DWT), in addition to matrix rotation to generate cancelable biometric templates, in order to meet revocability and prevent the restoration of the original templates from the generated cancelable ones. Rotated versions of the images are generated in either spatial or transform domains and added together to eliminate the ability to recover the original biometric templates. The cancelability performance is evaluated and tested through extensive simulation results for all proposed methods on a different face and fingerprint datasets. Low Equal Error Rate (EER) values with high AROC values reflect the efficiency of the proposed methods, especially those dependent on DCT and DFrFT. Moreover, a comparative study is performed to evaluate the proposed method with all transformations to select the best one from the security perspective. Furthermore, a comparative analysis is carried out to test the performance of the proposed schemes with the existing schemes. The obtained outcomes reveal the efficiency of the proposed cancelable biometric schemes by introducing an average AROC of 0.998, EER of 0.0023, FAR of 0.008, and FRR of 0.003.

Contactless Fingerprint Recognition Based on Global Minutia Topology and Loose Genetic Algorithm

Abstract: Contactless fingerprint recognition is highly promising and an essential component in the automatic fingerprint identification system. However, due to the inherent characteristic of perspective distortions of contactless fingerprints, achieving a highly accurate contactless fingerprint recognition system is very challenging. In this paper, we propose a robust contactless fingerprint recognition method based on global minutia topology and loose genetic algorithm. In order to avoid the inaccurate minutiae alignment problem suffered in conventional transformation-based methods, the minutiae correspondence is established by optimizing an energy function of the similarity matrix. We define an innovative similarity matrix based on both minutiae and minutia-pairs, which takes the global minutia topology into account. By adopting a distortion-free feature of ridge count to define the similarity, the problem of perspective distortions is effectively overcome. To solve the optimization, we propose a new genetic algorithm (GA) named loose GA with new mutation and crossover operators. We also propose a strict minutia-pair expanding algorithm to enhance the reliability of the minutiae correspondence. For recognition, a metric for measuring comparison scores which takes advantage of both the global topological similarity and the number of corresponding minutiae is proposed. We evaluate our method using two contactless fingerprint benchmark databases and achieve competitive performances in comparison with the state-of-the-art methods.

Fractal Coding-Based Robust and Alignment-Free Fingerprint Image Hashing

Abstract: Biometric image hashing techniques have been widely studied and seen progressive advancements. However, only a handful of available solutions provide two-factor cancelability while simultaneously satisfying the tradeoff among all criteria of template protection mechanisms. In this paper, we propose a novel scheme for generating a secure and robust hash from a fingerprint image using Fourier-Mellin transform and fractal coding. First, due to its invariance property, Fourier-Mellin transform is incorporated into the domain fingerprint minutiae blocks to provide feature alignment, therein generating a fixed-length minutiae representation for comparison. Then, dimensionality reduction and texture compression are exploited using fractal coding to generate a robust and compact hash for improved security and recognition. The experimental results demonstrate a favorable recognition performance on benchmarked state-of-the-art schemes from FVC2002 and FVC2004 fingerprint databases. The analyses prove our method’s robustness and resiliency to security and privacy attacks. Our method also satisfies the revocability and unlinkability criteria of cancelable biometrics.

Cancelable face and fingerprint recognition based on the 3D jigsaw transform and optical encryption

Abstract: Biometric systems are widely used now for security applications. Two major problems are encountered in biometric systems: the security problem and the dependence on a single biometric for verification. The security problem arises from the utilization of the original biometrics in databases. So, if these databases are attacked, the biometrics are lost forever. Hence, there is a need to secure original biometrics by keeping them away from utilization in biometric databases. Cancelable biometrics is an emerging security trend in the field of biometric authentication. Cancelable biometric systems depend on the transformation of biometric features into new formats so that users can replace their biometric templates in the same or different systems. In this paper, we present a proposed cancelable face and fingerprint recognition algorithm based on the 3D jigsaw transform and optical encryption. The algorithm adopts the Fractional Fourier Transform (FRFT) in the optical encryption scheme with a single random phase mask. This structure can be implemented all optically with a single lens. The proposed cancelable biometric recognition algorithm employs an optical image encryption scheme that depends on two cascaded stages of 2D-FRFT with separable kernels in both dimensions. The two stages are separated with a random phase mask. A preceding bit plane permutation process is performed on the obtained biometrics prior to the FRFT operation to achieve a high level of security. To validate the proposed algorithm for cancelable biometric recognition, different sets of face and fingerprint images are used. A comparative study is presented between the proposed algorithm and the optical Double Random Phase Encoding (DRPE) algorithm. The simulations results obtained for performance evaluation show that the proposed algorithm is safe, reliable, and feasible. It has good encryption and cancelability that reveal good performance.

A Flexible Touch-Based Fingerprint Acquisition Device and a Benchmark Database Using Optical Coherence Tomography

Abstract: Optical coherence tomography (OCT) is a high-resolution imaging technology probing the internal structure of multilayered tissues. Since it provides subsurface fingerprint information that is identical to the surface texture but unaffected by any surface defects, OCT-based fingerprints open up a new domain for establishing robust and high-security automatic fingerprint identification systems (AFISs). However, the development of OCT-based fingerprint recognition is hindered by the lack of public OCT-based fingerprint database for algorithm analysis and testing. This article, for the first time, established an OCT-based fingerprint database with thousands of fingers using our custom-built acquisition device. The website of this data set is https://github.com/CV-SZU/ . Moreover, the images included in the database were selected after quality evaluation based on image resolution, image size, effective measured area, and the number of extractable features. Finally, case studies, including antispoofing, multiple subsurface fingerprint reconstruction, and fingerprint verification, were discussed based on the developed database. The database can serve as a benchmark for developing effective antispoofing, live detection, and high-accurate fingerprint recognition algorithms. It will significantly promote the research in the area of fingerprint biometric and will also advance the development of commercial products.

Convolutional neural networks approach for multimodal biometric identification system using the fusion of fingerprint, finger-vein and face images.

Abstract: In recent years, the need for security of personal data is becoming progressively important. In this regard, the identification system based on fusion of multibiometric is most recommended for significantly improving and achieving the high performance accuracy. The main purpose of this paper is to propose a hybrid system of combining the effect of tree efficient models: Convolutional neural network (CNN), Softmax and Random forest (RF) classifier based on multi-biometric fingerprint, finger-vein and face identification system. In conventional fingerprint system, image pre-processed is applied to separate the foreground and background region based on K-means and DBSCAN algorithm. Furthermore, the features are extracted using CNNs and dropout approach, after that, the Softmax performs as a recognizer. In conventional fingervein system, the region of interest image contrast enhancement using exposure fusion framework is input into the CNNs model. Moreover, the RF classifier is proposed for classification. In conventional face system, the CNNs architecture and Softmax are required to generate face feature vectors and classify personal recognition. The score provided by these systems is combined for improving Human identification. The proposed algorithm is evaluated on publicly available SDUMLA-HMT real multimodal biometric database using a GPU based implementation. Experimental results on the datasets has shown significant capability for identification biometric system. The proposed work can offer an accurate and efficient matching compared with other system based on unimodal, bimodal, multimodal characteristics.

Towards More Accurate Contactless Fingerprint Minutiae Extraction and Pose-Invariant Matching

Abstract: Contactless fingerprint identification offers significantly higher user convenience, hygiene and has attracted increasing attention for the deployments. However, the presentation of fingers towards the contactless fingerprint sensors is hard to control and often results in unwanted pose changes that significantly degrade the contactless fingerprint matching accuracy. In order to address such problems and improve the fingerprint matching accuracy, this paper proposes $a$ more precise minutiae extraction and pose-compensation approach. As compared with the conventional minutiae extraction approaches, our deep neural network-based approach does not require any image enhancement and is robust to spurious minutiae. All the minutiae extracted from our network are subjected to $a$ three stage pose compensation framework: $a$ ) view angle estimation based on the location of core point, $b$ ) ellipsoid model formulation which simulates and compensate finger pose, $c$ ) intersection area estimation and alignment between different view angles. The proposed ellipsoid model is adaptive to both the silhouette of 2D contactless fingerprint image and the estimated view angle. The corresponding area between the different view angles can be theoretically estimated using this model and incorporated to align two contactless fingerprints for achieving superior matching accuracy. Our reproducible experimental results presented in this paper using public databases, and $a$ database acquired during this work, validate the effectiveness of the proposed framework over the commercial software and earlier methods.

Adversarial attacks on fingerprint liveness detection

Abstract: Deep neural networks are vulnerable to adversarial samples, posing potential threats to the applications deployed with deep learning models in practical conditions. A typical example is the fingerprint liveness detection module in fingerprint authentication systems. Inspired by great progress of deep learning, deep networks-based fingerprint liveness detection algorithms spring up and dominate the field. Thus, we investigate the feasibility of deceiving state-of-the-art deep networks-based fingerprint liveness detection schemes by leveraging this property in this paper. Extensive evaluations are made with three existing adversarial methods: FGSM, MI-FGSM, and Deepfool. We also proposed an adversarial attack method that enhances the robustness of adversarial fingerprint images to various transformations like rotations and flip. We demonstrate these outstanding schemes are likely to classify fake fingerprints as live fingerprints by adding tiny perturbations, even without internal details of their used model. The experimental results reveal a big loophole and threats for these schemes from a view of security, and enough attention is urgently needed to be paid on anti-adversarial not only in fingerprint liveness detection but also in all deep learning applications.

Synchronous Fingerprint Acquisition System Based on Total Internal Reflection and Optical Coherence Tomography

Abstract: The research of external fingerprint collected by total internal reflection (TIR) has been carried out for decades and the research of internal fingerprint collected by optical coherence tomography (OCT) has just begun. The internal fingerprint can be hardly affected by the finger surface status, due to its strong antiinterference and antispoofing ability, which can serve as a powerful supplement to external fingerprint. However, matching fingerprints acquired in different ways can lead to a drop in fingerprint recognition accuracy due to the differences in fingerprint quality, distortions, and detection areas. Whether the internal fingerprint can be used to replace the external fingerprint for direct identification has been hampered by lacking comparison tools to study potential correlation with each other. To study the connection between internal and external fingerprints, a synchronous acquisition system that achieves the same fingerprint area measurement at the same time is necessary. The integration of different optical paths of TIR and OCT as well as the consequent distortion correction of two totally different imaging ways are two challenging problems. This article presents a fingerprint acquisition system that synchronously acquires the external fingerprint and internal fingerprint with TIR and OCT, respectively. By using a self-designed trapezoidal prism, optical paths of TIR and OCT were integrated. Furthermore, a distortion correction method based on a grid calibration plate is used to remove distortions caused by two imaging methods. The fingerprint quality statistics are illustrated in 264 sets of fingerprint data sets. Identification results show synchronous acquisition and distortion correction of the proposed system are efficient.

PoreNet: CNN-Based Pore Descriptor for High-Resolution Fingerprint Recognition

Abstract: With the development of high-resolution fingerprint scanners, high-resolution fingerprint-based biometric recognition has received increasing attention in recent years. This paper presents a pore feature-based approach for biometric recognition. Our approach employs a convolutional neural network (CNN) model, DeepResPore, to detect pores in the input fingerprint image. Thereafter, a CNN-based descriptor is computed for a patch around each detected pore. Specifically, we have designed a residual learning-based CNN, referred to as PoreNet that learns distinctive feature representation from pore patches. For verification, a matching score is generated by comparing the pore descriptors, obtained from a pair of fingerprint images, in a bi-directional manner using the Euclidean distance. The proposed approach for high-resolution fingerprint recognition achieves 2.27% and 0.24% equal error rates (EERs) on partial (DBI) and complete (DBII) fingerprints of the benchmark PolyU HRF dataset. Most importantly, it achieves lower FMR1000 and FMR10000 values than the current state-of-the-art approach on both the datasets. Further, this is the first study to report the performance of a learning-based fingerprint recognition approach on cross-sensor fingerprint images.

Enhancing the Physical Layer Security of OFDM-PONs With Hardware Fingerprint Authentication: A Machine Learning Approach

Abstract: We propose and demonstrate an identity authentication method in the orthogonal frequency division multiplexing passive optical network (OFDM-PON) by recognizing device fingerprints of optical network units (ONUs). Signal decomposition methods based on wavelet transform are implemented to extract feature matrixes during the pre-process of samples, and then a trained 2-D convolutional neural network (2D-CNN) is applied to classify and identify these feature matrixes. Experimental results show that the identity of legitimate ONUs can be successfully recognized and 97.41% identification accuracy is achieved. A rogue ONU can be detected with an identification accuracy of 100%, which indicates that the ability of PONs to resist identity spoofing attack is effectively improved. The robustness of the scheme is also verified. With the proposed strategy, the security level of PON system at the physical layer can be increased markedly.

Can a CNN Automatically Learn the Significance of Minutiae Points for Fingerprint Matching

Abstract: Most automated fingerprint recognition systems use minutiae points for comparing fingerprints. In the parlance of Computer Vision, minutiae can be viewed as handcrafted features, i.e., features that have been proposed by human experts for the task of fingerprint recognition. In this work, we raise the following question: Can a machine learning system automatically determine the significance of minutiae points for fingerprint matching? To this effect, a patch-based Siamese Convolutional Neural Network (CNN), which does not explicitly rely on the extraction of minutiae points, is designed and trained from scratch. The purpose of this network is to learn the most effective features for matching fingerprint images. The features learned by this network are analyzed using Gradient-weighted Class Activation Mapping (Grad-CAM) to determine if they correlate with the locations of minutiae points. Our experiments suggest that the proposed network automatically learns to focus on minutiae points, when available, for fingerprint matching. Thus, an automated learner without any explicit domain knowledge establishes the significance of minutiae points for fingerprint matching.

Fingerprint Synthesis: Search with 100 Million Prints

Abstract: Evaluation of large-scale fingerprint search algorithms has been limited due to lack of publicly available datasets. To address this problem, we utilize a Generative Adversarial Network (GAN) to synthesize a fingerprint dataset consisting of 100 million fingerprint images. In contrast to existing fingerprint synthesis algorithms, we incorporate an identity loss which guides the generator to synthesize fingerprints corresponding to more distinct identities. The characteristics of our synthesized fingerprints are shown to be more similar to real fingerprints than existing meth- ods via eight different metrics (minutiae count - block and template, minutiae direction - block and template, minutiae convex hull area, minutiae spatial distribution, block minutiae quality distribution, and NFIQ 2.0 scores). Additionally, the synthetic fingerprints based on our approach are shown to be more distinct than synthetic fingerprints based on published methods through search results and imposter distribution statistics. Finally, we report for the first time in open literature, search accuracy against a gallery of 1 00 million fingerprints (NIST SD4 Rank-1 accuracy of 89.7%).

A Score-Level Fusion of Fingerprint Matching With Fingerprint Liveness Detection

Abstract: Fingerprint-based recognition is widely deployed in different domains. However, the traditional fingerprint recognition systems are vulnerable to presentation attack, which utilizes an artificial replica of the fingerprint to deceive the sensors. In such scenarios, Fingerprint Liveness Detection (FLD) is required to ensure the actual presence of a live fingerprint. In this paper, a fingerprint matching method fused with liveness detection is proposed. Firstly, the similarity between two fingerprint images is calculated based on Octantal Neatest-Neighborhood Structure (ONNS), where the closest minutia to the central minutia is found from each sector of octant. Secondly, the FLD score of the fingerprint image is obtained by using the modified Residual Network (Slim-ResCNN). Finally, a score-level fusion is performed on the results of fingerprint matching and FLD by generating interaction features and polynomial features as the score feature vector. To classify whether a fingerprint image is a genuine live fingerprint or a spoof attack (including impostor live and fake fingerprints), the score feature vector is processed using logistic regression (LR) classifiers. The proposed method won the first place in the Fingerprint Liveness Detection Competition 2019 with an overall accuracy of 96.88%, which indicates it can effectively protect the fingerprint recognition systems from spoof attacks.

On Matching Finger-Selfies Using Deep Scattering Networks

Abstract: With the advancements in technology, smartphones’ capabilities have increased immensely. For instance, the smartphone cameras are being used for face and ocular biometric-based authentication. This research proposes finger-selfie based authentication mechanism, which uses a smartphone camera to acquire a selfie of a finger. In addition to personal device-level authentication, finger-selfies may also be matched with livescan fingerprints present in the legacy/national ID databases for remote or touchless authentication. We propose an algorithm which comprises segmentation, enhancement, Deep Scattering Network based feature extraction, and Random Decision Forest to authenticate finger-selfies. This paper also presents one of the largest finger-selfie database with over 19, 400 images. The images in the IIIT-D Smartphone Finger-selfie Database v2 are captured using multiple smartphones and include variations due to background, illumination, resolution, and sensors. Results and comparison with existing algorithms show the efficacy of the proposed algorithm which yields equal error rates in the range of 2.1 – 5.2% for different experimental protocols.

An Efficient Multi-Modal Biometric Sensing and Authentication Framework for Distributed Applications

Abstract: Multimodal biometrics is an emerging technology for distributed data security. Single and multi-user data authentication plays a vital role in commercial or e-governance applications. Many approaches have been implemented in literature to secure the single user data using biometric security systems. Most of these systems are based on static initialization parameters and fixed multi-modal biometric features for data authentication. Also, traditional multi-modal biometric based data authentication schemes are independent of dynamic variation in integrity verification. In order to overcome these problems, a new multi-user based multi-modal authentication framework is designed and implemented on large image data types. In this framework, different biometric features such as IRIS, facial and fingerprint features are used to find the unique integrity of user for data authentication and security process. A new integrity computational algorithm and encryption technique are implemented to provide the strong data integrity verification and data security in distributed applications. Experimental results show that the proposed multi-modal integrity-based encryption model has nearly 7% of computational integrity bit change and 5% of runtime on large dataset.

Presentation Attack Detection for Finger Recognition

Abstract: Whereas other biometric characteristics, such as the face, are readily available for an eventual attacker through social media or easy to capture with a conventional smartphone, vein patterns can only be acquired with dedicated sensors. This fact makes them relevant not only for recognition purposes but especially for Presentation Attack Detection (PAD), for instance, in combination with fingerprint recognition. In this chapter, we make use of this combination and present a finger vein-based PAD algorithm to detect presentation attacks targeting fingerprint recognition. The experiments are carried out on a newly collected database, comprising 32 species of Presentation Attack Instruments ranging from printed artefacts to more sophisticated fingerprint overlays. The results show that our method preserves a convenient usage while detecting around 90% of the attacks. However, thin and transparent fingerprint overlays remain very challenging.

Ultrasonic fingerprint sensor for under-display applications

Abstract: Disclosed are methods, devices, apparatuses, and systems for an under-display ultrasonic fingerprint sensor. A display device may include a platen, a display underlying the platen, and an ultrasonic fingerprint sensor underlying the display, where the ultrasonic fingerprint sensor is configured to transmit and receive ultrasonic waves via an acoustic path through the platen and the display. A light-blocking layer and/or an electrical shielding layer may be provided between the ultrasonic fingerprint sensor and the display, where the light-blocking layer and/or the electrical shielding layer are in the acoustic path. A mechanical stress isolation layer may be provided between the ultrasonic fingerprint sensor and the display, where the mechanical stress isolation layer is in the acoustic path.

A review on presentation attack detection system for fake fingerprint

Abstract: Fingerprint recognition systems are susceptible to artificial spoof fingerprint attacks, like molds manufactured from polymer, gelatin or Play-Doh. Presentation attack is an open issue for fingerpr...

Fingerprint Biometrics From Newborn to Adult: A Study From a National Identity Database System

Abstract: In this work, we evaluate the use of fingerprints to identify people from a very young age. Although it is well known that fingerprints are stable all along life, and even before born fingerprint patterns are fully developed, automatic identification (or comparison) systems are developed generally for adult fingerprints. Our interest is not only to study the feasibility of using child fingerprints for automatic identification but to determine if that is possible with the existing software and hardware. There are two related questions that we do answer in this work. First, starting at what age are digitally acquired fingerprints good enough for automatic comparison. Second, what is the performance when comparing fingerprints from children against fingerprints from adults. In order to answer these questions, we have run a set of experiments on a database composed of more than 200K fingerprints from approximately 134K identities. We show that, after applying a growth factor to scale minors fingerprints to an adult size, good accuracy can be obtained from ages starting at one year old, and that fingerprints of children and adults can be compared without a significant loss of accuracy (with respect to adult vs adult). We consider this study extremely useful for both researchers and decision makers, as it is a testimony that even without additional developments, fingerprints from children can be used for automatic comparison on real scenarios.

Deep Convolutional Neural Network for Double-Identity Fingerprint Detection

Abstract: Automatic human recognition using ubiquitous fingerprint sensors is the most widely used modality in modern biometric based security systems. The double-identity fingerprint is a fake fingerprint created by aligning two fingerprints for maximum ridge similarity and then joining them along an estimated cutline such that relevant features of both fingerprints are present on either sides of the cutline. The fake fingerprint containing the features of the criminal and his innocuous accomplice can be enrolled with an electronic machine readable travel document and later used to cross the automated border gates by claiming identity of the accomplice. In this letter, we have developed a deep convolutional neural network (CNN)-based patch-learning approach to estimate the cutline by training the network to identify and learn the pattern around the region of the joint fingerprint. This is a recent, new fingerprint alteration technique, and due to the unavailability of any such public database, we have generated a new database of 450 double-identity fingerprints. Experimental results show that the deep learning based approach is able to predict the cutline with an equal error rate, which is the best when compared with many other popular handcrafted features for double-identity fingerprint detection.

Liveness is Not Enough: Enhancing Fingerprint Authentication with Behavioral Biometrics to Defeat Puppet Attacks

Abstract: Fingerprint authentication has gained increasing popularity on mobile devices in recent years. However, it is vulnerable to presentation attacks, which include that an attacker spoofs with an artificial replica. Many liveness detection solutions have been proposed to defeat such presentation attacks; however, they all fail to defend against a particular type of presentation attack, namely puppet attack, in which an attacker places an unwilling victim’s finger on the fingerprint sensor. In this paper, we propose FINAUTH, an effective and efficient software-only solution, to complement fingerprint authentication by defeating both synthetic spoofs and puppet attacks using fingertip-touch characteristics. FINAUTH characterizes intrinsic fingertip-touch behaviors including the acceleration and the rotation angle of mobile devices when a legitimate user authenticates. FINAUTH only utilizes common sensors equipped on mobile devices and does not introduce extra usability burdens on users. To evaluate the effectiveness of FINAUTH, we carried out experiments on datasets collected from 90 subjects after the IRB approval. The results show that FINAUTH can achieve the average balanced accuracy of 96.04% with 5 training data points and 99.28% with 100 training data points. Security experiments also demonstrate that FINAUTH is resilient against possible attacks. In addition, we report the usability analysis results of FINAUTH, including user authentication delay and overhead.

Radio Frequency Fingerprint Identification Based on Deep Complex Residual Network

Abstract: Radio frequency fingerprint identification is a non-password authentication method based on the physical layer hardware of the communication device. Deep learning methods provide new ideas and techniques for radio frequency fingerprint identification. As a bridge between electromagnetic signal recognition and deep learning, the electromagnetic signal recognition method based on statistical constellation still needs to go through data preprocessing and feature engineering, which is contrary to the end-to-end learning method emphasized by deep learning. Moreover, in the process of converting electromagnetic signal waveform data into images, there is inevitably information loss. Establishing a universal radio frequency fingerprint recognition model suitable for wireless communication scenarios is not only conducive to optimizing the communication system, but also can reduce the cost and time of model selection. Therefore, how to design a deep learning radio frequency fingerprint recognition model suitable for wireless communication is an important problem for researchers. Aiming at the problem that the existing radio frequency fingerprint extraction and identification methods have low recognition rate of communication radiation source individuals, a radio frequency fingerprint identification method based on deep complex residual network is proposed. Through the deep complex residual network, the radio frequency fingerprint feature extraction of the communication radiation source individual is integrated with the recognition process, and an end-to-end deep learning model suitable for wireless communication is established, which greatly improves the identification accuracy of the communication radiation source individuals compared with typical constellation based methods.