Fingerprint Classification Research Articles

Fingerprint classification and identification algorithms for criminal investigation: A survey

Fingerprint plays a fundamental role in community security and criminal investigation, such as forensic investigation, law enforcement, customs access and public security organs. This can also help to provide a more enjoyable and secure life to people. Various machine learning and neural network approaches have been proposed for fingerprint acquisition, detection, classification, and analysis. In this survey, we present an up-to-date literature evaluation of fingerprint classification algorithms and fingerprint application in the area of criminal investigation. Firstly, we discuss the characteristics of fingerprint and the application in criminal investigation. In addition, we analyze and compare machine learning algorithms of fingerprint in terms of classification, matching, feature extraction, fingerprint and finger-vein recognition, and spoof detection. Finally, we highlight the challenges in the fingerprint analysis and discuss the future directions.

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.

Indoor Wireless LAN Fingerprints Parameterisation and Classification in Academic Environments

Indoor Wireless LAN Fingerprints Parameterisation and Classification in Academic Environments

Real-time online fingerprint image classification using adaptive hybrid techniques

<p class="Abstract">This paper presents three different hybrid classification techniques applied for the first time in real-time online fingerprint classification. Classification of online real time fingerprints is a complex task as it involves adaptation and tuning of classifier parameters for better classification accuracy. To accomplish the optimal adaptation of parameters of functional link artificial neural network (FLANN) for real-time online fingerprint classification, proven and established optimizers, such as Biogeography based optimizer (BBO), Genetic algorithm (GA), and Particle swarm optimizer (PSO) are intelligently infused with it to form hybrid classifiers. The global features of the real-time fingerprints are extracted using a Gabor filter-bank and then passed into adaptive hybrid classifiers for the desired classification as per the Henry system. Three hybrid classifiers, the optimized weight adapted Biogeography based optimized functional link artificial neural network (BBO-FLANN), Genetic algorithm based functional link artificial neural network (GA-FLANN) and Particle swarm optimized functional link artificial neural network (PSO-FLANN), are explored for real-time online fingerprint classification, where the PSO-FLANN technique is showing superior performance as compared to GA-FLANN and BBO-FLANN techniques. The best accuracy observed by the application of PSO-FLANN, is 98% for real-time online fingerprint classification.</p>

FClassNet: a fingerprint classification network integrated with the domain knowledge

FClassNet: a fingerprint classification network integrated with the domain knowledge

Entropy-Based Clustering Algorithm for Fingerprint Singular Point Detection.

Fingerprints have long been used in automated fingerprint identification or verification systems. Singular points (SPs), namely the core and delta point, are the basic features widely used for fingerprint registration, orientation field estimation, and fingerprint classification. In this study, we propose an adaptive method to detect SPs in a fingerprint image. The algorithm consists of three stages. First, an innovative enhancement method based on singular value decomposition is applied to remove the background of the fingerprint image. Second, a blurring detection and boundary segmentation algorithm based on the innovative image enhancement is proposed to detect the region of impression. Finally, an adaptive method based on wavelet extrema and the Henry system for core point detection is proposed. Experiments conducted using the FVC2002 DB1 and DB2 databases prove that our method can detect SPs reliably.

P1-FP: Extraction, Classification, and Prediction of Website Fingerprints with Deep Learning

AbstractRecent advances in Deep Neural Network (DNN) architectures have received a great deal of attention due to their ability to outperform state-of-the-art machine learning techniques across a wide range of application, as well as automating the feature engineering process. In this paper, we broadly study the applicability of deep learning to website fingerprinting. First, we show that unsupervised DNNs can generate lowdimensional informative features that improve the performance of state-of-the-art website fingerprinting attacks. Second, when used as classifiers, we show that they can exceed performance of existing attacks across a range of application scenarios, including fingerprinting Tor website traces, fingerprinting search engine queries over Tor, defeating fingerprinting defenses, and fingerprinting TLS-encrypted websites. Finally, we investigate which site-level features of a website influence its fingerprintability by DNNs.

Fingerprint image classification using local diagonal and directional extrema patterns

Proper classification of fingerprints still poses difficult issues in large-scale databases due to ambiguity in intraclass and interclass structures, discontinuity in low-quality images, and ridges. To address these challenges, we propose a feature named local diagonal and directional extrema pattern (LDDEP) as a descriptor for classification of fingerprints. The proposed method utilizes first-order derivatives to find values and indices of local diagonal and directional extremas. The local extrema values are then compared with the central pixel intensity value to find the correlation with the neighbors. Eventually, the descriptor is generated with the help of the indices and local extrema values. Furthermore, the proposed descriptor is fed into K-nearest neighbor and support vector machine (SVM) for classifying the fingerprint images into four and five groups, respectively. The LDDEP descriptor is compared with the existing methods on two databases, namely National Institute of Standards Technology Special Database 4 (NIST SD 4) and Fingerprint Verification Competition (FVC). Our experiments have shown that, on the 4000 image NIST SD 4 test dataset, the proposed descriptor achieved a classification accuracy of 95.15% for five classes and 96.85% for four classes for half of the dataset, and an accuracy of 95.5% for five classes and 96.63% for four classes for the entire test dataset using SVM classifier. Similarly, FVC databases for the LDDEP descriptor gave classification accuracy of 98.2% using SVM classifier. The proposed method gave higher accuracies compared to the existing methods.

PH-Dependent Conformational Changes of KcsA Tetramer and Monomer Probed by Raman Spectroscopy.

KcsA is a tetrameric potassium channel formed out of four identical monomeric subunits used as a standard model for selective potassium transport and pH-dependent gating. Large conformational changes are reported for tetramer and monomer upon gating, and the response of the monomer being controversial with the two major studies partially contradicting each other. KcsA was analyzed as functional tetramers embedded in liposomes and as monomer subunits with confocal Raman microscopy under physiological conditions for the active and the closed channel state, using 532 nm excitation to avoid introducing conformational changes during the measurement. Channel function was confirmed using liposome flux assay. While the classic fingerprint region below 1800 rel. cm−1 in the Raman spectrum of the tetramer was unaffected, the CH-stretching region between 2800 and 3200 rel. cm−1 was found to be strongly affected by the conformation. No pH-dependency was observed in the Raman spectra of the monomer subunits, which closely resembled the Raman spectrum of the tetramer in its active conformation, indicating that the open conformation of the monomer and not the closed conformation as postulated may equal the relaxed state of the molecule.

Robust fingerprint classification with Bayesian convolutional networks

Fingerprint classification is vital for reducing the search time and computational complexity of the fingerprint identification system. The robustness of classifier relies on the strength of extracted features and the ability to deal with low-quality fingerprints. The proficiency to learn accurate features from raw fingerprint images rather than explicit feature extraction makes deep convolutional neural networks (DCNNs) attractive for fingerprint classification. The DCNNs use softmax for quantifying model confidence of a class for an input fingerprint image to make a prediction. However, the softmax probabilities are not a true representation of model confidence and often misleading in feature space that may not be represented with the available training examples. The primary goal of this study is to improve the efficacy of the fingerprint classification by dealing with false positives by employing Bayesian model uncertainty. The efficacy of the proposed method is shown through experimentations on NIST special database 4 (NIST-4) and fingerprint verification competition 2002 database 1-A (FVC DB1-A) 2002 and 2004 datasets. Results show that 0.8-1.0% of accuracy is improved with model uncertainty over the conventional DCNN.

Fingerprint Classification Using Kernel Smoothing Technique and Generalized Regression Neural Network and Probabilistic Neural Network

Fingerprint classification is a significant process by which identification procedure can be accelerated. Feature extraction might be afflicted with rotation. Thus, all images get through an introduced criterion to rectify rotated images. The core point of fingerprints is utilized widely in both classification and recognition process. In some cases, however, inaccurate location of it might contribute to incorrect categorization. Therefore, the common point is initiated for the purpose of better performance. Features are extracted according to the way ridges’ angles are distributed across images. Plus, kernel smoothing technique is used to enhance the process. Generalized regression neural network (GRNN) and Probabilistic neural network (PNN) are employed to classify fingerprints in four categories. Fingerprint verification competition (FVC) database is used to evaluate and train the networks. The simulation is performed by MATLAB and 97.4% accuracy is achieved for both GRNN and PNN.

Toward Hardware-Rooted Smartphone Authentication

In recent years, an enormous amount of research has been carried out in an attempt to identify smartphones through modeling the manufacturing imperfections of their built-in transducers, which spawned a rich set of hardware fingerprinting methods. However, the vast majority of the work in this area has focused on device tracking and identification. For adversarial settings like forensics and authentication, it remains unclear whether these methods will provide reliable identification results when the outputs of transducers are tampered by adversaries intentionally. In this article, we look into the authentication scenario and investigate the feasibility of using a hardware fingerprint as the unique identity of a smartphone. We discuss various security issues underlying hardware-rooted smartphone authentication and outline two specific attacks that need to be taken into account while designing such a system. We also describe several desirable properties that a fingerprinting method should have in order to be applicable for the authentication scenario. Several classic fingerprinting methods are studied, and their security and usability are analyzed.

A common convolutional neural network model to classify plain, rolled and latent fingerprints

Fingerprint classification helps in reducing the number of comparisons during the matching stage in automatic fingerprint identification system. In this study, a convolutional neural network model is proposed for classification of plain, rolled and latent fingerprints. We first propose a new convolutional neural network model initialised with random weights and train the model on fingerprint images. Then we fine-tune two pre-trained convolutional neural network models on fingerprint images. Finally, we compare these three models: two pre-trained models and a custom convolutional neural network model initialised with random weights. We show that pre-trained models can achieve the state-of-the-art results on other similar tasks with no or little fine-tuning. We also show that training data size and depth of the network have a serious impact on the overall performance of deep networks. Dropout is used to enhance the performance of deep networks where the labelled training data is not of sufficient size. All the three models trained on NIST DB4 fingerprint and IIIT-D latent fingerprint databases report good accuracy. By only fine-tuning the pre-trained convolutional neural network model, we get the accuracy of 99%, easily out-performing the state-of-the-art.

Pre-History of DNA ‘Fingerprinting’ in India

This paper shows how fingerprinting was birthed in colonial India as a response to the requirements of governing the native population whom the British colonialists presumed to be untrustworthy and deceptive. It further shows how fingerprint was developed into a technology of unique human identification by Henry Faulds and Francis Galton in England and the way in which a fingerprint classification system was developed by Edward Henry along with Azizul Haque and Hem Chandra Bose in India. The paper goes on to link the historical development in human fingerprint identification and classification with the contemporary developments in DNA fingerprinting and databasing.

Indoor Smartphone Localization: A Hybrid WiFi RTT-RSS Ranging Approach

Real-time locating and tracking Technology plays a significant role in location-based IoT applications. With the extensive installation of WiFi access points, the WiFi based indoor positioning approach has become one of the most widely used location technologies. However, due to the limitations of wireless signals, the classic WiFi-based method has become labor-intensive. Recently, the WiFi-based two-way ranging approach was introduced into the 802.11-REVmc2 protocol, which is built on a new packet type known as fine timing measurement (FTM) frame. In this work, we introduce the round-trip time measurement with clock skew and analyze the distribution of the round trip time (RTT) ranging error. A calibration method is presented to eliminate the RTT range offset at the transmitter end. We also develop an integrated ranging algorithm based on the WiFi round trip time range and received signal strength to enhance the scalability and robustness of the positioning system. The experimental results demonstrate that the proposed fusion method achieves remarkable improvement in scalability and precision in both static and dynamic tests, including outdoor and indoor environments. Compared with the classic fingerprinting approach, the performance of the system is remarkably improved, and achieves an average positioning accuracy of 1.435 m with an update rate of every 0.19 s.

Fingerprint Smoothing Using Different Interpolation Techniques

Classical fingerprint analysts use binary images in the minutiae recognition and extraction processes. These obtained images do not have a sufficient quality that allows the extraction of the robust primitives, either during the contours detection or during skeletonization. In this study, a mathematical approach for the fingerprint curves modeling have been performed. The adopted smoothing technique is based on two geometric interpolation types adapted to fingerprint images. The obtained results reveal that the Bezier curve method has an error lower than that by the cubic spline method. The Bézier curve method has a RMS value of 0.035 pixels and an average maximum error of the order of 0.33 pixels. On the other hand, the cubic spline method has a RMS value about of 0.043 pixels and an average maximum error about of 0.37 pixels. We can see that the proposed method facilitates the design process of real-world objects and makes the fingerprint curves smooth.

Fingerprint Classification Based on Orientation Field

Fingerprint Classification Based on Orientation Field

LICIC: Less Important Components for Imbalanced Multiclass Classification

Multiclass classification in cancer diagnostics, using DNA or Gene Expression Signatures, but also classification of bacteria species fingerprints in MALDI-TOF mass spectrometry data, is challenging because of imbalanced data and the high number of dimensions with respect to the number of instances. In this study, a new oversampling technique called LICIC will be presented as a valuable instrument in countering both class imbalance, and the famous “curse of dimensionality” problem. The method enables preservation of non-linearities within the dataset, while creating new instances without adding noise. The method will be compared with other oversampling methods, such as Random Oversampling, SMOTE, Borderline-SMOTE, and ADASYN. F1 scores show the validity of this new technique when used with imbalanced, multiclass, and high-dimensional datasets.

Smartphone-Based Indoor Localization within a 13th Century Historic Building.

Within this work we present an updated version of our indoor localization system for smartphones. The pedestrian’s position is given by means of recursive state estimation using a particle filter to incorporate different probabilistic sensor models. Our recently presented approximation scheme of the kernel density estimation allows to find an exact estimation of the current position, compared to classical methods like weighted-average. Absolute positioning information is given by a comparison between recent Wi-Fi measurements of nearby access points and signal strength predictions. Instead of using time-consuming approaches like classic fingerprinting or measuring the exact positions of access points, we use an optimization scheme based on a set of reference measurements to estimate a corresponding Wi-Fi model. This work provides three major contributions to the system. The most essential contribution is the novel state transition based on continuous walks along a navigation mesh, modeling only the building’s walkable areas. The localization system is further updated by incorporating a threshold-based activity recognition using barometer and accelerometer readings, allowing for continuous and smooth floor changes. Within the scope of this work, we tackle problems like multimodal densities and sample impoverishment (system gets stuck) by introducing different countermeasures. For the latter, a simplification of our previous solution is presented for the first time, which does not involve any major changes to the particle filter. The goal of this work is to propose a fast to deploy localization solution, that provides reasonable results in a high variety of situations. To stress our system, we have chosen a very challenging test scenario. All experiments were conducted within a 13th century historic building, formerly a convent and today a museum. The system is evaluated using 28 distinct measurement series on four different test walks, up to 310 length and 10 duration. It can be shown, that the here presented localization solution is able to provide a small positioning error, even under difficult conditions and faulty measurements. The introduced filtering methods allow for a real fail-safe system, while the optimization scheme enables an on-site setup-time of less then 120 for the building’s 2500 m2 walkable area.

Comparison of microridges in juvenile and adult sunfish, Lepomis gibbosus

AbstractMicroridges are F‐actin‐based surface protrusions of the superficial layer cells of fish epidermis. Microridge patterns progress in complexity during fish embryogenesis, often transitioning from abundant surface microvilli to the classical fingerprint arrangement. This progression suggests pattern changes may also occur during later stages of fish development. Fluorescent labelling of F‐actin and morphometric analysis were therefore used to assess changes in epidermal microridge patterns in juvenile and adult sunfish (Lepomis gibbosus). The microridge patterns found in adult pumpkinseed were similar to that described for many fishes, consisting of whorls or complex multi‐branched ridges. The microridge patterns of the scales from three different‐sized groups of juvenile pumpkinseed were distinctly different from that of adult, however, and were present mainly as unbranched concentric or nearly concentric rings in the two larger juvenile groups. In the smallest juveniles, microridges were often apparent as fragmented ridges with abundant actin puncta. Larger juveniles sometimes displayed mixed patterns, with some microridges similar to that of both adult and juvenile patterns. The results show a transition from simple microridge patterns in juvenile pumpkinseeds to distinctly different, diverse and more complex patterns in adults. The different pattern types may reflect particular microridge functions relevant to fish size and age.