Automatic Fingerprint Recognition Research Articles

MoSFPAD: An end-to-end ensemble of MobileNet and Support Vector Classifier for fingerprint presentation attack detection

Automatic fingerprint recognition systems are the most extensively used systems for person authentication although they are vulnerable to Presentation attacks. Artificial artifacts created with the help of various materials are used to deceive these systems causing a threat to the security of fingerprint-based applications. This paper proposes a novel end-to-end model to detect fingerprint Presentation attacks. The proposed model incorporates MobileNet as a feature extractor and a Support Vector Classifier as a classifier to detect presentation attacks in cross-material and cross-sensor paradigms. The feature extractor’s parameters are learned with the loss generated by the support vector classifier. The proposed model eliminates the need for intermediary data preparation procedures, unlike other static hybrid architectures. The performance of the proposed model has been validated on benchmark LivDet 2011, 2013, 2015, 2017, and 2019 databases, and overall accuracy of 98.64%, 99.50%, 97.23%, 95.06%, and 95.20% are achieved on these databases, respectively. The performance of the proposed model is compared with state-of-the-art methods and is able to reduce the average classification error of 3.63%, 1.86%, 1.83%, 0.05%, 0.93% on LivDet 2011, 2013, 2015, 2017, and 2019 databases, respectively for same and cross material protocols in intra-sensor paradigm. The proposed method also reduced the average classification error of 1.59%, 1.41%, and 2.29% for LivDet 2011, 2013, and 2017 databases, respectively for the cross-sensor paradigm. It is evident from the results that the proposed method outperforms state-of-the-art methods in intra-sensor as well as cross-sensor paradigms in terms of average classification error.

Standardized, Enhanced and Robust Automated Fingerprint Recognition using CNN

Abstract: In recent years, biometric authentication systems have seen rapid development in various industries, and they continue to provide high security functions for access control systems. Many types of unimodal biometric authentication systems have been developed. However, these systems can only provide a low to moderate range of security features. Therefore, a combination of two or more unimodal biometrics (multiple modalities) is required to achieve higher security capabilities. To achieve higher accuracy, this article uses generalized probabilistic learning model algorithm for processing finger vein images. Image preprocessing is done with the help of finger vein image database to prepare it for further processes of feature extraction and matching. It then uses generalized probabilistic learning model algorithm to find the feature points. algorithm is used to match the features to obtain the image information and determines the final identity according to the sparse distribution. Compared with other machine learning methods for finger vein detection, the proposed method has a higher accuracy rate.

A novel intelligent 12-layer convolutional neural network model for gender classification using fingerprint images

Fingerprints are widely used as effective personal authentication systems, because they constitute unique, robust, and risk-free evidence. Fingerprinting techniques refer to biometric procedures used for identifying individuals based on their physical characteristics. A fingerprint image contains ridges and valleys forming a directionally-oriented pattern. The robustness of the fingerprint authentication technique determines the quality of the fingerprint image. This study proposed an intelligent 12-layered Convolutional Neural Network (CNN) model using Deep learning (DL) for gender determination based on fingerprints. Further, the study compared the performance of this model to existing state-of-the-art methods. The primary goal of this study was to reduce the number of comparisons within a large database obtained from automatic fingerprint recognition systems. The classification process was found to be swifter and more accurate when analysis of the DL algorithm was performed. With reference to the criteria of precision, recall, and accuracy evaluation during classification, this proposed 12-layered CNN model outperformed the Residual Neural Network with 50 Layers (ResNet-50) and Dense Convolutional Network with 201 Layers (DenseNet-201) models. The accuracies obtained were 97.0%, 95.8%, 98.0%, and 96.8% for female-left, female-right, male-left, and male-right classes respectively, while achieving an overall accuracy of 94.0%.

Sweat Gland Extraction From Optical Coherence Tomography Using Convolutional Neural Network

As the Level 3 features of fingerprint, sweat pores have attracted attention in the field of fingerprint recognition and have been successfully applied to automatic fingerprint recognition systems. Traditional surface sweat pores become unclear or disappeared when the finger is contaminated, dried, or damaged. These unstable factors create major challenges in collecting sweat pores. Subcutaneous sweat glands belong to the internal tissues of fingers, which are stable and immune to external disturbances. This study investigated the extraction of subcutaneous sweat glands from fingertip volume data collected by optical coherence tomography (OCT). First, an improved multitask V-Net is proposed to extract subcutaneous sweat glands from OCT volume data. The network has an encoding path for features extraction and two decoding paths for extracting sweat gland boundaries and regions, respectively. The multitask scheme is designed to enhance the boundary and shape information of sweat glands and to prevent false extraction caused by interference from other tissues. Second, three mapping methods are proposed to address the problem of different spatial orientations of sweat glands. These three mapping methods, namely, global direct mapping (GDM), local direct mapping (LDM), and cylindrical fitting mapping (CFM), are used to map sweat glands to the surface fingerprint. Experiments are conducted in terms of sweat gland extraction, mapping, and matching. The qualitative and quantitative results show that the proposed network for sweat glands extraction outperforms other methods and that the LDM and CFM methods derive more accurate positions of sweat glands on the surface fingerprint than GDM. In the matching experiment, the equal error rate (EER) of dual-decoding V-Net (DDVN) reached 0.58%, which verified the recognition ability of sweat glands and the effectiveness of the proposed network.

Fingerprint Presentation Attack Detector Using Global-Local Model.

The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This article thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module; 2) the local module; and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by ~10% in terms of TDR (91.19% versus 80.74%).

Robust Fingerprint Minutiae Extraction and Matching Based on Improved SIFT Features

Minutiae feature extraction and matching are not only two crucial tasks for identifying fingerprints, but also play an eminent role as core components of automated fingerprint recognition (AFR) systems, which first focus primarily on the identification and description of the salient minutiae points that impart individuality to each fingerprint and differentiate one fingerprint from another, and then matching their relative placement in a candidate fingerprint and previously stored fingerprint templates. In this paper, an automated minutiae extraction and matching framework is presented for identification and verification purposes, in which an adaptive scale-invariant feature transform (SIFT) detector is applied to high-contrast fingerprints preprocessed by means of denoising, binarization, thinning, dilation and enhancement to improve the quality of latent fingerprints. As a result, an optimized set of highly-reliable salient points discriminating fingerprint minutiae is identified and described accurately and quickly. Then, the SIFT descriptors of the local key-points in a given fingerprint are matched with those of the stored templates using a brute force algorithm, by assigning a score for each match based on the Euclidean distance between the SIFT descriptors of the two matched keypoints. Finally, a postprocessing dual-threshold filter is adaptively applied, which can potentially eliminate almost all the false matches, while discarding very few correct matches (less than 4%). The experimental evaluations on publicly available low-quality FVC2004 fingerprint datasets demonstrate that the proposed framework delivers comparable or superior performance to several state-of-the-art methods, achieving an average equal error rate (EER) value of 2.01%.

A Robust Automatic Fingerprint Recognition System Using Multi-Connection Hopfield Neural Network

Automatic fingerprint recognition has received significant attention because of its excellent fingerprint stability characteristics. Fingerprints will now explode in popularity as online stores allow payments and secure smartphones. The main objective of this study is to develop a fingerprint recognition system to identify individuals by using a new method, termed as ‘Multi-Connection Hopfield Neural Network’. This might pave the way for the development of a more robust fingerprint recognition system that is more accurate and capable of working in noisy environments. Furthermore, such a system makes operations less complex and saves memory by employing additional tranches of auto-associative memory. This study uses three databases, namely FVC-2004, International NIST-4, and internal database, containing 80, 2000, and 2000 fingerprint images. The proposed fingerprint recognition system achieves 99.65% accuracy without noise. This study also shows that the proposed system works well in the presence of noise and achieves 96.07% accuracy in the presence of 50% random noise.

Finger Print Authentication on Web-Services One Step to Next Security

The system that automatically identifies the anthropometric fingerprint is one of the systems that interact directly with the user, which every day will be provided with a diverse database. This requires the system to be optimized to handle the process to meet the needs of users such as fast processing time, almost absolute accuracy, no errors in the real process. Therefore, in this paper, we propose the application of machine learning methods to develop fingerprint classification algorithms based on the singularity feature. The goal of the paper is to reduce the number of comparisons in automatic fingerprint recognition systems with large databases. The combination of using computer vision algorithms in the image pre-processing stage increases the calculation time, improves the quality of the input images, making the process of feature extraction highly effective and the classification process fast and accurate. The classification results on 3 datasets with the criteria for Precision, Recall, Accuracy evaluation and ROC analysis of algorithms show that the Random Forest (RF) algorithm has the best accuracy (≥96.75%) on all 3 databases, Support Vector Machine (SVM) has the best results (≥95.5%).

Cross-Sensor Pore Detection in High-Resolution Fingerprint Images

With the emergence of high-resolution fingerprint sensors, there has been a lot of focus on level-3 fingerprint features, especially the pores, for the next generation automated fingerprint recognition systems (AFRS). Following the success of deep learning in various computer vision tasks, researchers have developed learning-based approaches for detection of pores in high-resolution fingerprint images. Generally, learning-based approaches provide better performance than hand-crafted feature-based approaches. However, domain adaptability of the existing learning-based pore detection methods has never been studied. In this paper, we study this aspect and propose an approach for pore detection in cross-sensor scenarios. For this purpose, we have generated an in-house 1000 dpi fingerprint dataset with ground truth pore coordinates (referred to as IITI-HRFP-GT), and evaluated the performance of the existing learning-based pore detection approaches. The core of the proposed approach for detection of pores in cross-sensor scenarios is DeepDomainPore, which is a residual learning-based convolutional neural network (CNN) trained for pore detection. The domain adaptability in DeepDomainPore is achieved by embedding a gradient reversal layer between the CNN and a domain classifier network. The proposed approach achieves state-of-the-art performance in a cross-sensor scenario involving public high-resolution fingerprint datasets with 88.12% true detection rate and 83.82% F-score.

A multi-task fully deep convolutional neural network for contactless fingerprint minutiae extraction

With the outbreak and wide spread of novel coronavirus (COVID-19), contactless fingerprint recognition has attracted more attention for personal recognition because it can provide significantly higher user convenience and hygiene than the traditional contact-based fingerprint recognition. However, it is still challenging to achieve a highly accurate recognition due to the low ridge-valley contrast and pose variances of contactless fingerprints. Minutiae points are a kind of ridge flow discontinuities, and robust and accurate extraction is an important step for most automatic fingerprint recognition algorithms. Most of existing methods are based on two stages which locate the minutiae points first and then compute their directions. The two-stage method cannot make full use of location and direction information. In this paper, we propose a multi-task fully deep convolutional neural network for jointly learning the minutiae location detection and its corresponding direction computation which operates directly on the whole gray scale contactless fingerprints. The proposed method consists of offline training and online testing stages. In the training stage, a fully deep convolutional neural network is built for the tasks of minutiae detection and its direction regression, with an attention mechanism to make the direction regression branch concentrate on the minutiae points. A new loss function is proposed to jointly learn the tasks of minutiae detection and its direction regression from the whole fingerprints. In the testing stage, the trained network is applied on the whole contactless fingerprint to generate the minutiae location and direction maps. The proposed multi-task leaning method performs better than the individual single task and it operates directly on the raw gray-scale contactless fingerprints without preprocessing. The results on three contactless fingerprint datasets show the proposed algorithm performs better than other minutiae extraction algorithms and the commercial software.

A comparative study on handcrafted features v/s deep features for open-set fingerprint liveness detection

Abstract A fingerprint liveness detector is a pattern classifier that is used to distinguish a live finger from a fake (spoof) one in the context of an automated fingerprint recognition system. As liveness detectors or presentation attack detectors are vulnerable to presentation attacks, the security and reliability of fingerprint recognition are compromised. Presentation attack detection mechanisms rely on handcrafted or deep features to classify an image as live or spoof. In addition, to strengthen the security, fingerprint liveness detectors should be robust to presentation attacks fabricated using unknown fabrication materials or fingerprint sensors. In this paper, we conduct a comprehensive study on the impact of handcrafted and deep features from fingerprint images on the classification error rate of the fingerprint liveness detection task. We use LBP, LPQ and BSIF as handcrafted features and VGG-19 and Residual CNN as deep feature extractors for this study. As the problem is targeted as an open-set problem, the emphasis is on achieving better robustness and generalization capability. In our observation, handcrafted features outperformed their deep counterparts in two of the three cases under the within-dataset environment. In the cross-sensor environment, deep features obtained a better accuracy, and in the cross-dataset environment, handcrafted features obtained a lower classification error rate.

3D Fingerprint Recognition based on Ridge-Valley-Guided 3D Reconstruction and 3D Topology Polymer Feature Extraction.

An automated fingerprint recognition system (AFRS) for 3D fingerprints is essential and highly promising for biometric security. Despite the progress in developing 3D AFRSs, achieving high-quality real-time reconstruction and high-accuracy recognition of 3D fingerprints remain two challenging issues. To address them, we propose a robust 3D AFRS based on ridge-valley (RV)-guided 3D fingerprint reconstruction and 3D topology polymer (TTP) feature extraction. The former considers the unique fingerprint characteristics of the RV and achieves real-time reconstruction. Unlike traditional triangulation-based methods that establish correspondences between points by cross-correlation-based searching, we propose to establish RV correspondences (RVCs) between ridges/valleys by defining and calculating a RVC matrix based on the topology of RV curves. To enhance depth reconstruction, curve-based smoothing is proposed to refine our novel RV disparity map. The TTP feature codes the 3D topology by projecting the 3D minutiae onto multiple planes and extracting their corresponding 2D topologies and has proven to be effective and efficient for 3D fingerprint recognition. Comprehensive experimental results demonstrate that our method outperforms the state-of-the-art methods in terms of both reconstruction and recognition accuracy. Also, due to its very short running time, it is appropriate for practical applications.

Deep Learning Algorithms based Fingerprint Authentication: Systematic Literature Review

Deep Learning algorithms (DL) have been applied in different domains such as computer vision, image detection, robotics and speech processing, in most cases, DL demonstrated better performance than the conventional machine learning algorithms (shallow algorithms). The artificial intelligence research community has leveraged the robustness of the DL because of their ability to process large data size and handle variations in biometric data such as aging or expression problem. Particularly, DL research in automatic fingerprint recognition system (AFRS) is gaining momentum starting from the last decade in the area of fingerprint pre-processing, fingerprints quality enhancement, fingerprint feature extraction, security of fingerprint and performance improvement of AFRS. However, there are limited studies that address the application of DL to model fingerprint biometric for different tasks in the fingerprint recognition process. To bridge this gap, this paper presents a systematic literature review and an insightful meta-data analysis of a decade applications of DL in AFRS. Discussion on proposed model’s tasks, state of the art study, dataset, and training architecture are presented. The Convolutional Neural Networks models were the most saturated models in developing fingerprint biometrics authentication. The study revealed different roles of the DL in training architecture of the models: feature extractor, classifier and end-to-end learning. The review highlights open research challenges and present new perspective for solving the challenges in the future. The author believed that this paper will guide researchers in propose novel fingerprint authentication scheme.

One-Class Fingerprint Presentation Attack Detection Using Auto-Encoder Network.

Automated Fingerprint Recognition Systems (AFRSs) have been threatened by Presentation Attack (PA) since its existence. It is thus desirable to develop effective presentation attack detection (PAD) methods. However, the unpredictable PAs make PAD be a challenging problem. This paper proposes a novel One-Class PAD (OCPAD) method for Optical Coherence Technology (OCT) images based fingerprint PA detection. The proposed OCPAD model is learned from a training set only consists of Bonafides (i.e. real fingerprints). The reconstruction error and latent code obtained from the trained auto-encoder network in the proposed model is taken as the basis for the following spoofness score calculation. To get more accurate reconstruction error, we propose an activation map based weighting model to further refine the accuracy of reconstruction error. We test different statistics and distance measures and finally use a decision level fusion to make the final prediction. Our experiments are performed using a dataset with 93200 bonafide scans and 48400 PA scans. The results show that the proposed OCPAD can achieve a True Positive Rate (TPR) of 99.43% when the False Positive Rate (FPR) equals to 10% and a TPR of 96.59% when FPR=5%, which significantly outperformed a feature based approach and a supervised learning based model requiring PAs for training.

Robust and high-security fingerprint recognition system using optical coherence tomography

Traditional fingerprint recognition systems are vulnerable to attacks, such as the use of artificial fingerprints, and poor performance will be achieved if the captured surface fingerprints are of low-quality. Developing high-security and robust fingerprint recognition systems is of increasing concern in modern society. The introduction of optical coherence tomography (OCT) for fingerprint imaging opens up a new research domain for fingerprint recognition due to its ability to capture the depth information of skin layers. This paper proposes a fingerprint recognition system based on OCT. The research first establishes a database with normal, worn-out, artificial and degraded fingerprints imaged by our custom-built, in-house OCT device. Then, we propose to reconstruct three layers of subsurface fingerprints by considering diverse skin layer information. For each of the subsurface fingerprints divided according to the physical structure of the fingertip, we propose a simple yet effective projection-based reconstruction method. Finally, a pixel-level fusion strategy based on the local image quality is proposed to the fuse the three levels of subsurface fingerprints for robust fingerprint recognition. In our experiments, we show that as much diverse fingerprint information can be retained as possible by the proposed subsurface fingerprint reconstruction method. We also demonstrate the effectiveness and efficiency of the proposed method by comparing it with existing state-of-the-art internal fingerprint reconstruction approaches. The robustness and high anti-spoofing ability of the proposed system is verified by comparing the matching performance evaluated on the established OCT-based database and another database with the same fingerprints imaged by a commercial optical sensor. The best EER and FMR100 evaluated on OCT-based fingerprints are 0.42% and 0.36%, respectively. The best EER and FMR100 evaluated on traditional 2D surface fingerprints are 8.05% and 18.18%, respectively, which shows the vast potential of the proposed system in current automated fingerprint recognition systems (AFRSs).

Fingerprint pore matching using deep features

As a popular living fingerprint feature, sweat pore has been adopted to build robust high resolution automated fingerprint recognition systems (AFRSs). Pore matching is an important step in high resolution fingerprint recognition. This paper proposes a novel pore matching method with high recognition accuracy. The method mainly solves the pore representation problem in the state-of-the-art direct pore matching method. By making full use of the diversity and large quantities of sweat pores on fingerprints, deep convolutional networks are carefully designed to learn a deep feature (denoted as DeepPoreID) for each pore. The inter-class difference and intra-class similarity of pore patch pairs can be well solved using deep learning. The DeepPoreID is then used to describe the local feature for each pore and finally integrated into the classical direct pore matching method. More specifically, pore patches, which are cropped from both Query and Template fingerprint images, are imported into the well-trained networks to generate DeepPoreID for pore representation. The similarity between those DeepPoreIDs are then obtained by calculating the Euclidian Distance between them. Subsequently, one-to-many coarse pore correspondences are established via comparing their similarity. Finally, classical Weighted RANdom SAmple Consensus (WRANSAC) is employed to pick true pore correspondences from coarse ones. The experiments carried on the two public high resolution fingerprint database have shown the effectiveness of the proposed DeepPoreID, especially for fingerprint matching with small image size. Meanwhile, better recognition accuracy is achieved by the proposed method when compared with the existing state-of-the-art methods. About 35% rise in equal error rate (EER) and about 30% rise in FMR1000 when compared with the best result evaluated on the database with image size of 320 × 240 pixels.

Multi-task CNN for restoring corrupted fingerprint images

Fingerprint image enhancement is one of the fundamental modules in an automated fingerprint recognition system (AFRS). While the performance of AFRS advances with sophisticated fingerprint matching algorithms, poor fingerprint image quality remains a major issue to achieve accurate fingerprint recognition. In this paper, we present a multi-task convolutional neural network (CNN) based method to recover fingerprint ridge structures from corrupted fingerprint images. By learning from the noises and corruptions caused by various undesirable conditions of finger and sensor, the proposed CNN model consists of two streams that reconstruct the fingerprint image and orientation field simultaneously. The enhanced fingerprint is further refined using the orientation field information. Moreover, we create a deliberately corrupted fingerprint image dataset associated with ground truth images to facilitate the supervised learning of the proposed CNN model. Experimental results show significant improvement on both image quality and fingerprint matching accuracy after applying the proposed fingerprint image enhancement technique to several well-known fingerprint datasets.

Analysis of Fingerprint Recognition System Using Neural Network

Fingerprint identification has a substantial efficacy in forensic science and aids criminal investigations. Fingerprints are distinctive and remain enduring throughout a person’s life. The automatic fingerprint recognition systems are based on ridges and their characteristics known as minutiae. Hence it is extremely important to mark these minutiae accurately and reject the false ones. In this work, we have used ridge termination and ridge bifurcation as minutiae for fingerprint recognition systems. At the time of the analysis of algorithms, the approaches of attributes impart better results. The recognition rate is increased & the error rate diminishes with the aid of this technique. The most important step here in automatic fingerprint matching is to securely extract the minutiae from the captured fingerprint binary images. There are already a variety of techniques are available for extracting fingerprint minutiae. The recognition rate of this intended method of fingerprint recognition system using neural networks is 91.10%. From the extricate outcome, we may infer about a very affirmative impact of neural networks on the comprehensive recognition rate, specifically in low excellence images.

Fingerprints Classification through Image Analysis and Machine Learning Method

The system that automatically identifies the anthropometric fingerprint is one of the systems that interact directly with the user, which every day will be provided with a diverse database. This requires the system to be optimized to handle the process to meet the needs of users such as fast processing time, almost absolute accuracy, no errors in the real process. Therefore, in this paper, we propose the application of machine learning methods to develop fingerprint classification algorithms based on the singularity feature. The goal of the paper is to reduce the number of comparisons in automatic fingerprint recognition systems with large databases. The combination of using computer vision algorithms in the image pre-processing stage increases the calculation time, improves the quality of the input images, making the process of feature extraction highly effective and the classification process fast and accurate. The classification results on 3 datasets with the criteria for Precision, Recall, Accuracy evaluation and ROC analysis of algorithms show that the Random Forest (RF) algorithm has the best accuracy (≥96.75%) on all 3 databases, Support Vector Machine (SVM) has the best results (≥95.5%) 2 / 3 databases.

High-accurate and robust fingerprint anti-spoofing system using Optical Coherence Tomography

Traditional commercial automated fingerprint recognition systems (AFRSs) are vulnerable to fake attacks by the use of artificial fingerprints, due to its limitation on resolution and the difficulty of obtaining depth information. Developing new systems with strong anti-spoofing ability are of increasing concern in the current digital age. Inspired by the observation and comparison of fingertip skin structure and the one dimensional (1D) depth signals derived from OCT acquisition images between real finger and artificial fingerprints, two novel anti-spoofing features, namely depth-double-peak feature and sub-single-peak feature, were specifically defined. Depth-double-peak feature refers that there must be two and only two peaks in the 1D depth signal which reflects the double-peak structure of real fingertip skin. While sub-single-peak feature means that there must be a peak in the 1D depth signal intercepted before the maximum peak which distinguishes the extra layer covered on a real finger. Real and fake images could be presented by these two features and classified by a pre-learned threshold. Four types of artificial fingerprint, i.e., Normal Thickness Fingerprint Layer (NTFL), thin Fingerprint Layer (TFL), Ultra-Thin Fingerprint Layer (UTFL and Artificial Fingers Model (AFM) were collected to verify system robustness. 30 sets of real finger data (each set includes 400 images) and 60 sets of artificial fingerprint data (15 sets of each type) were collected by our designed OCT device. Experimental results show that our proposed anti-spoofing system could achieve 100% accuracy over all four types of artificial fingerprints and outperform the other automated anti-spoofing method in comparison.