False Match Rate Research Articles

Collaborative representation of blur invariant deep sparse features for periocular recognition from smartphones

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

A Novel Fingerprint Recovery Scheme using Deep Neural Network-based Learning

Minutiae used in most fingerprint recognition devices is robust to presentation attack, but generates a high false match rate. Thus, it is applied along with orientation map or skeleton images. There has been plenty of research on security vulnerability of minutiae, whereas few research has been conducted on orientation map or skeleton images. This study analyzes vulnerability of presentation attack for skeleton images. For this purpose, it proposes a new algorithm of recovering fingerprints with the use of machine learning and skeleton image features of fingerprints. In the proposed method, we suggest the new machine learning Pix2Pix model to generate more natural images. The suggested model is developed in the way of adding a latent vector to the conventional image-to-image translation model Pix2Pix. In the experiment, fingerprints were recovered with the use of the proposed Pix2Pix model, and it was found that a fingerprint recognition device which recognized the recovered fingerprints had a high success rate of recognition. Therefore, it was proved that a fingerprint recognition device using skeleton images as well was vulnerable to presentation attack. It is expected that the algorithm proposed in this study will be very useful to many different application areas related to image processing, including biometrics, fingerprint recognition and recovery, and image surveillance.

Identifying Individual Jaguars and Ocelots via Pattern‐Recognition Software: Comparing HotSpotter and Wild‐ID

ABSTRACTCamera‐trapping is widespread in wildlife studies, especially for species with individually unique markings to which capture–recapture analytical techniques can be applied. The large volume of data such studies produce have encouraged researchers to increasingly look to computer‐assisted pattern‐recognition software to expedite individual identifications, but little work has been done to formally assess such software for camera‐trap data. We used 2 sets of camera‐trap images—359 images of jaguars (Panthera onca) and 332 images of ocelots (Leopardus pardalis) collected from camera traps deployed in 4 study sites in Orange Walk District, Belize, in 2015 and 2016—to compare the accuracy of 2 such programs, HotSpotter and Wild‐ID, and assess the effect of image quality on matching success. Overall, HotSpotter selected a correct match as its top rank 71–82% of the time, whereas the rate for Wild‐ID was 58–73%. Positive matching rates for both programs were highest for high‐quality images (85–99%) and lowest for low‐quality images (28–52%). False match rates were very low for HotSpotter (0–2%) but these were greater in Wild‐ID (6–28%). When lower ranks were also considered, both programs performed similarly (overall 22–24% nonmatches for HotSpotter, 17–26% nonmatches for Wild‐ID). We found that in both programs, images more often matched to other images of the same quality; therefore, including multiple reference images of an individual, of different qualities, improves matching success. These programs do not provide fully automatic identification of individuals and human involvement is still required to confirm matches, but we found that they are effective tools to expedite processing of camera‐trap data. We also offer usage recommendations for researchers to maximize the benefits of these tools. © 2020 The Wildlife Society.

ALGORITHM OF CROSS LANGUAGE FUZZY SEARCH BASED ON HASH-VECTORS FOR AUTOMATIC COMPARISON OF PERSONAL NAMES

The algorithm of cross language fuzzy search based on hash vectors for automatic matching of personal names is proposed. In the response mode for an input request, names in Latin spelling and a given value for the similarity measure, the algorithm determines the set of output Cyrillic names contained in the database of the information search system. The principal feature of the proposed algorithm is the rejection of the direct translation of personal names. Instead, the hashing mechanism of personal names is used, followed by mapping them into the same hidden vector space where the computational procedures of the decision-making system are built. In the process of research, it was solved a number of actual intermediate tasks. Thus, the decomposition algorithms of the explored database, the generation and clustering of the dictionary of basic morphemes are an instrument that is of independent value in solving the problem of automatically translating names from a foreign language, the translation rules of which are unknown – the socalled generalized transcription. After mapping names into a vector space, the matching operation is reduced to assessing the similarity between vectors. As a measure of similarity, several quantities were considered in the study. The most convenient measure of similarity is the cosine similarity, the critical value of which was obtained by plotting the FMR (False Match Rate) and FNMR (False Non-Match Rate) graphs. The developed algorithm is universal with respect to the languages used, that is, it does not depend on a specific alphabet. In the practical implementation of the developed algorithm, a series of experimental studies was carried out using a database containing more than 2.5 million names.

Issues Related to Face Recognition Accuracy Varying Based on Race and Skin Tone

Face recognition technology has recently become controversial over concerns about possible bias due to accuracy varying based on race or skin tone. We explore three important aspects of face recognition technology related to this controversy. Using two different deep convolutional neural network face matchers, we show that for a fixed decision threshold, the African-American image cohort has a higher false match rate (FMR), and the Caucasian cohort has a higher false nonmatch rate. We present an analysis of the impostor distribution designed to test the premise that darker skin tone causes a higher FMR, and find no clear evidence to support this premise. Finally, we explore how using face recognition for one-to-many identification can have a very low false-negative identification rate and still present concerns related to the false-positive identification rate. Both the ArcFace and VGGFace2 matchers and the MORPH dataset used in our experiments are available to the research community so that others should be able to reproduce or reanalyze our results.

Study for Integration of Multi Modal Biometric Personal Identification Using Heart Rate Variability (HRV) Parameter

Authentication and Identification is primary part of biometric technology. Currently, electrocardiogram (ECG) is not only being used as a diagnostic tool for clinical purposes, but also as a new biometric tool for high level security system because of its liveliness and uniqueness that is hard to imitate and manipulate. There are many fiducial (signal mark) that is classified from ECG morphology (QRS Complex, P, T waves) has already been researched for this purpose. For non fiducial, many researches are focus on dynamic character from heartbeat (ECG Signal). Heart Rate Variability (HRV) analysis is part of non fiducial classifier. This paper reviews Heart Rate Variability analysis (time and frequency domain) as part of multi matches, one of scenario from multimodal biometric. Sample of person’s heartbeat signal is taken from ECG Database MIT-BIH (MIT and Harvard) and the result of every parameter will be analyzed by Biometric Performance Standards Tools (ISO/IEC IS 19795-1) such as: False Non-Match Rate (FNMR), False Match Rate (FMR) and Thresholds EER (Equal Error Rate). Analysis should show accuracy of multi matches Heart Rate Variability (HRV). As integrator tool, LabView is used to collect offline ECG, process the data and generate HRV Analysis.

Modelling and Simulation of Robust Biometric Fingerprint Recognition Algorithm

Fingerprint is a type of biometrics that is used for human recognition because it is rich in details called minutiae. The focus of this paper is to develop an algorithm for fingerprint recognition through extracting and matching of fingerprint image minutiae. In order to achieve accurate results, the fingerprint is first pre-processed to enhance its quality. An alignment-based matching algorithm was developed for minutia matching. This algorithm is capable of finding the correspondences between the input minutia pattern and the stored template minutia pattern without resorting to exhaustive search. The performance of the developed system was evaluated with matrix laboratory (MATLAB) software along with fingerprint from the standard FVC2000 fingerprint database and fingerprints from different people at university of Uyo. From the curves of false match rate (FMR) and false non match rate (FNMR) against similarity score, a threshold value of 0.4 was obtained as guided by the equal error rate (EER) value. For verification and identification testing, the developed system was able to accurately differentiate between genuine users and imposter irrespective of the orientation and noise level of the fingerprints.

Feasibility and acceptability of an iris biometric system for unique patient identification in routine HIV services in Kenya

BackgroundUse of routine HIV programme data for surveillance is often limited due to inaccuracies associated with patient misclassification which can be addressed by unique patient identification.We assessed the feasibility and acceptability of integrating an iris recognition biometric identification system into routine HIV care services at 4 sites in Kenya. MethodsPatients who had recently tested HIV-positive or were engaged in care were enrolled. Images of the iris were captured using a dual-iris camera connected to a laptop. A prototype iris biometric identification system networked across the sites, analysed the iris patterns; created a template from those patterns; and generated a 12-digit ID number based on the template. During subsequent visits, the patients’ irises were re-scanned, and the pattern was matched to stored templates to retrieve the ID number. ResultsOver 55 weeks 8,614 (98%) of 8,794 new patients were assigned a unique ID on their first visit. Among 6,078 return visits, the system correctly re-identified patients’ IDs 5,234 times (86%). The false match rate (a new patient given the ID of another patient) was 0·5% while the generalized false reject rate (re-scans assigned a new ID) was 4·7%. Overall, 9 (0·1%) agreed to enrol but declined to have an iris scan. The most common reasons cited for declining an iris scan were concerns about privacy and confidentiality. ConclusionImplementation of an iris recognition system in routine health information systems is feasible and highly acceptable as part of routine care in Kenya. Scale-up could improve unique patient identification and tracking, enhancing disease surveillance activities.

Objective Identification of Bullets Based on 3D Pattern Matching and Line Counting Scores

In firearm identification, a firearm examiner looks at a pair of fired bullets or cartridge cases using a comparison microscope and determines from this visual analysis if they were both fired from the same firearm. In the particular case of fired bullets, the individual firearm signature takes the form of a striated pattern. Over the time, the firearm examiner’s community developed two distinct approaches for bullet identification: pattern matching and line counting. More recently, the emergence of technology enabling the capture of surface topographies down to a submicron depth resolution has been a catalyst for the field of computerized objective ballistic identification. Objectiveness is achieved through the statistical analysis of various scores of known matches and known nonmatches exhibit pair comparison, which in turn implies the capture of large quantities of bullets and cartridge cases topographies. The main goal of this study was to develop an objective identification method for bullets fired from conventionally rifled barrels, and to test this method on public and proprietary bullet 3D image datasets captured at different lateral resolutions. Two newly developed bullet identification scores, the Line Counting Score (LCS) and the Pattern Matching Score, computed on 3D topographies yielded perfect match versus nonmatch separation for three different sets used in the standard Hamby–Brundage Test. A similar analysis performed using a larger, more-realistic set, enabled us to define a discriminative line at a false match rate of 1/10[Formula: see text]000 on a 2D plot that shows both identification scores for matches and nonmatches. The LCS is shown to produce a better sensitivity than the standard consecutive matching striae criteria for the more-realistic dataset. A likelihood function was also computed from a linear combination of both scores, and a conservative approach based on extreme value theory is proposed to extrapolate this function in the score domain where nonmatch data are not available. This study also provides a better understanding of the limitations of studies that involve very few firearms.

Smudge Noise for Quality Estimation of Fingerprints and its Validation

Automated biometric identification systems are inherently challenged to optimize false (non-)match rates. This can be addressed either by directly improving comparison subsystems, or indirectly by allowing only “good quality” biometric queries to be compared. We are interested in the latter, where the challenge lies in relating the “good quality” of a query to its utility with respect to a comparison subsystem. First, we propose a new general robust biometric quality validation scheme (RBQ VS) that, mimicking the use-case, robustly quantifies comparison improvement obtained by employing a specific quality estimator. For this purpose, we robustify an existing validation scheme by repeated random subsampling cross-validation. Second, specifically for the task of fingerprint comparison, we propose a novel biometric feature for quality estimation. Since comparison subsystems based on fingerprint minutiae, which are ridge endings and bifurcations, appear to miss minutiae or detect spurious minutiae, especially in the presence of smudge noise, we propose an algorithm aiming at measuring corruption by smudge. To this end, we employ a recently developed three parts image-decomposition and link our new smudge noise quality estimator (SNoQE) to the structure of the texture part found. At last, using the FVC databases and an NIST database, we compare the SNoQE with the popular NFIQ 2.0 estimator, and its predecessor. Experimental results show that the single-feature SNoQE can compete with the multi-feature NFIQ 2.0 and, in fact, adds new information not sufficiently reproduced by the NFIQ 2.0. Indeed, a simple combination of SNoQE and NFIQ 2.0 tends to outperform on all databases included in the comparison study. An implementation of the RBQ VS and the SNoQE can be found online.

A novel method based on deep learning for aligned fingerprints matching

In this study, a novel method based on deep learning for aligned fingerprints matching is proposed. According to the characteristics of fingerprint images, a convolutional network, Finger ConvNet, is designed. In addition, a new joint supervision signal is used to train Finger ConvNet to obtain deep features. Experimental studies are performed on public fingerprint datasets, the ID Card fingerprint dataset and the Ten-Finger Fingerprint Card fingerprint dataset. Furthermore, four performance indicators, the false matching rate (FMR), false non-matching rate (FNMR), equal error rate (EER) and receiver operating characteristic (ROC) curve, are measured. The experimental results demonstrate the effectiveness of the proposed method, which achieved a competitive effect in comparison with conventional fingerprint matching algorithms in fingerprint verification tasks using the FVC2000, FVC2002, and FVC2004 datasets. Moreover, the matching speed of the proposed method was almost 5 times faster than the fastest conventional fingerprint matching algorithms. In addition, it can be used as a fast matching method to filter out many templates with low scores by setting a threshold according to the matching scores and thus accelerate the process in identification tasks.

Combined training strategy for low‐resolution face recognition with limited application‐specific data

Application-specific data for certain biometric applications are often not sufficiently available. The authors present a solution for face recognition with limited application-specific data. Existing methods often use a classifier with convolutional neural networks (CNNs) as feature extractors. The CNNs are trained with massive general (i.e. not application specific) data and the classifier is trained with application-specific data. Alternatively, the authors propose a combined training strategy to train the classifier on a balanced mixture of general and application-specific data, such that the recognition performance is maximised. The proposed method largely alleviates the needs for application-specific data. To prove its effectiveness, they apply the proposed method to low-resolution face recognition. Specifically, they use the heterogeneous joint Bayesian (HJB) classifier that is capable of comparing features from the same modality but with different characteristics. To further boost performance, the authors augment the training data by pre-processing it to resemble application-specific data. They conducted extensive experiments on challenging datasets, namely, SCface and COX. The results show that the proposed method improves the true match rate on SCface at a false match rate of 10% by ∼11% and the true match rate on COX at a false match rate of 1% by ∼12%.

Effect of pupil dilation on off-angle iris recognition

Due to the less constrained setup in standoff iris recognition systems, it is likely to capture nonideal iris images with gaze angle, pupil dilation, reflections, and occlusions. The combined effect of pupil dilation and gaze angle on iris recognition is examined. We first highlight the effects on synthetic images generated with a biometric eye model using a ray-tracing algorithm. Then, we quantify the effects of pupil dilation and gaze angle on the real frontal and off-angle images at different dilation levels. Our experiments reveal that the larger differences in dilation levels and gaze angles between the compared iris images increase the Hamming distance. Even if the linear rubber-sheet normalization helps to minimize the dilation effect in frontal images, it cannot fully eliminate it in off-angle iris images because of not only the pupil dilation and three-dimensional iris texture but also the corneal refraction distortion and limbus occlusion. We also observe that the gaze angle is the main reason for the performance degradation in steeper off-angle images, where the effect of the dilation is limited. In addition, since the iris region in off-angle and dilated iris images is smaller than that in frontal and constricted iris images, their interclass Hamming distance distribution is shifted toward the intraclass distribution, which may increase the false match rate.

Improving the Continuum of Care by Bridging the Gap between Prehospital and Hospital Discharge Data through Stepwise Deterministic Linkage

Objective: To describe the process, benefits, and challenges of linking Arizona’s prehospital registry to hospital discharge data. Methods: Data were queried from the Arizona Prehospital Information and Emergency Medical Services Registry System (AZ-PIERS) and the Arizona Hospital Discharge Database (HDD) for the calendar year 2015. To maximize the number of matched records, the databases were deterministically linked in 17 steps using different combinations/variations of patient personal identifiers. Random samples of at least 1% of matched pairs from each of 16 linkage steps (excluding Step 1) were manually reviewed to assess the rate of false positive matches. Results: A total of 626,413 records were reported to AZ-PIERS in 2015. Of those, 503,715 qualified for linkage. These records were matched against 3,125,689 discharge records reported to the HDD in 2015. The first step, which involved exact matching on first name, last name, date of birth, gender, and date of incident/date of admission, yielded a linkage of 64.6% (n = 325,156). The 16 successive steps yielded a further linkage of 26.6% (n = 134,006) for a total linkage of 91.2% (n = 459,162). The manual review indicated an overall false positive match rate for the 16 reviewed steps of 6.96% (n = 99). The 2 steps with the highest false positive match rates were Step 16 (43.02%, n = 77) and Step 17 (31.43%, n = 11). Conclusion: It is feasible to link prehospital and hospital data using stepwise deterministic linkage; this method returns a high linkage rate with a low false positive error rate. Data linkage is vital to identifying and bridging gaps in the continuum of care and is a useful tool in statewide and agency-specific research and quality improvement.

Learning Face Image Quality From Human Assessments

Face image quality can be defined as a measure of the utility of a face image to automatic face recognition. In this paper, we propose (and compare) two methods for learning face image quality based on target face quality values from: 1) human assessments of face image quality (matcher-independent) and 2) quality values computed from similarity scores (matcher-dependent). A support vector regression model trained on face features extracted using a deep convolutional neural network (ConvNet) is used to predict the quality of a face image. The proposed methods are evaluated on two unconstrained face image databases, Labeled Faces in the Wild and IARPA Janus Benchmark-A (IJB-A), which both contain facial variations encompassing a multitude of quality factors. Evaluation of the proposed automatic face image quality measures shows we are able to reduce the false non-match rate at 1% false match rate by at least 13% for two face matchers (a commercial off-the-shelf matcher and a ConvNet matcher) by using the proposed face quality to select subsets of face images and video frames for matching templates (i.e., multiple faces per subject) in the IJB-A protocol. To the best of our knowledge, this is the first work to utilize human assessments of face image quality in designing a predictor of unconstrained face quality that is shown to be effective in cross-database evaluation.

Deep Feature Fusion for Iris and Periocular Biometrics on Mobile Devices

The quality of iris images on mobile devices is significantly degraded due to hardware limitations and less constrained environments. Traditional iris recognition methods cannot achieve high identification rate using these low-quality images. To enhance the performance of mobile identification, we develop a deep feature fusion network that exploits the complementary information presented in iris and periocular regions. The proposed method first applies maxout units into the convolutional neural networks (CNNs) to generate a compact representation for each modality and then fuses the discriminative features of two modalities through a weighted concatenation. The parameters of convolutional filters and fusion weights are simultaneously learned to optimize the joint representation of iris and periocular biometrics. To promote the iris recognition research on mobile devices under near-infrared (NIR) illumination, we publicly release the CASIA-Iris-Mobile-V1.0 database, which in total includes 11 000 NIR iris images of both eyes from 630 Asians. It is the largest NIR mobile iris database as far as we know. On the newly built CASIA-Iris-M1-S3 data set, the proposed method achieves 0.60% equal error rate and 2.32% false non-match rate at false match rate $=10^{-5}$ , which are obviously better than unimodal biometrics as well as traditional fusion methods. Moreover, the proposed model requires much fewer storage spaces and computational resources than general CNNs.

SKA-PS: Secure key agreement protocol using physiological signals

In this paper, we propose SKA-PS, a novel Secure Key Agreement protocol using Physiological Signals, for Body Area Networks (BANs). Our protocol generates symmetric cryptographic keys using the physiological parameters derived from the physiological signals of the users, such as electrocardiogram, photoplethysmogram and blood pressure. In our construction, we reduce the problem of secure key agreement into the problem of set reconciliation by representing the physiological parameter sequences generated from the physiological signals of the BAN users with appropriate sets. When properly selected parameters are applied, biosensors of the same BAN user can agree on symmetric cryptographic keys with remarkably high true match and low false match rates (as much as 100% and 0.46% for pairwise execution, and 100% and 0.26% for group execution, respectively), and low communication, computational and storage costs. We implemented our model in an embedded system, thus the results show real implementation outcomes. Moreover, we comparatively analyze the performance of SKA-PS with two existing bio-cryptographic key agreement protocols and show that SKA-PS outperforms both in all performance metrics.

Unique Patient Identification: Feasibility and Acceptability of an Iris Recognition Biometric System in Routine HIV Services

Background: Use of routine health programme data for surveillance and quality improvement is often limited due to inaccuracies associated with patient misidentification which can be addressed by unique patient identification. We assessed the feasibility and acceptability of integrating an iris recognition biometric identification system into routine HIV testing (HTC) and treatment services at 4 sites in Kenya. Methods: Patients who had recently tested HIV-positive or were engaged in care were enrolled. An electronic version of the national HTC intake form was administered. Images of the iris were captured using a dual-iris camera connected to a laptop. A prototype iris biometric identification system networked across the sites, analysed the iris patterns; created a template from those patterns; and generated a 12-digit ID number based on the template. During subsequent visits, the patients' irises were re-scanned, and the pattern was matched to stored templates to retrieve the ID number. Findings: Over 55 weeks 8,614 (98%) of 8,794 new patients were assigned a unique ID on their first visit. Among 6,078 return visits, the system correctly re-identified patients' IDs 5,234 times (86%). The false match rate (a new patient given the ID of another patient) was 0·5% while the generalized false reject rate (re-scans assigned a new ID) was 4·7%. Overall, 9 (0·1%) agreed to enroll but declined to have an iris scan. The most common reasons cited for declining an iris scan were concerns about privacy and confidentiality. Interpretation: Implementation of an iris recognition system in routine health information systems is feasible and highly acceptable as part of routine care in Kenya. Scale-up could improve unique patient identification and tracking, enhancing disease surveillance activities. Funding Statement: Data collection was funded under the US National Institutes of Health (NIH) research grant (A1099974 S1). Further funding for analyses and manuscript preparation was provided by the NIH Fogarty International Centre grant (D43 TW009580). Declaration of Interest: The authors declare no competing interests. Ethics Approval Statement: Ethical review and approval was obtained from the University of Washington Institutional Review Board and the Kenyatta National Hospital-University of Nairobi Ethical Review Committee.

Biometric Authentication Using the PPG: A Long-Term Feasibility Study.

The photoplethysmogram (PPG) is a biomedical signal that can be used to estimate volumetric blood flow changes in the peripheral circulation. During the past few years, several works have been published in order to assess the potential for PPGs to be used in biometric authentication systems, but results are inconclusive. In this paper we perform an analysis of the feasibility of using the PPG as a realistic biometric alternative in the long term. Several feature extractors (based on the time domain and the Karhunen–Loève transform) and matching metrics (Manhattan and Euclidean distances) have been tested using four different PPG databases (PRRB, MIMIC-II, Berry, and Nonin). We show that the false match rate (FMR) and false non-match rate (FNMR) values remain constant in different time instances for a selected threshold, which is essential for using the PPG for biometric authentication purposes. On the other hand, obtained equal error rate (EER) values for signals recorded during the same session range from 1.0% for high-quality signals recorded in controlled conditions to 8% for those recorded in conditions closer to real-world scenarios. Moreover, in certain scenarios, EER values rise up to 23.2% for signals recorded over different days, signaling that performance degradation could take place with time.

Self‐geometric relationship filter for efficient SIFT key‐points matching in full and partial palmprint recognition

Recently, palmprints have been broadly reported in the literature as an effective biometric modality. Although scale-invariant feature transform (SIFT)-based features have been proven to be robust against image transformations and deformations, SIFT has not been as successful as other methods in palmprint recognition. In fact, SIFT-based identification has been widely criticised in biometrics due to its high false matching rate. To overcome this weakness, a new filtering method for SIFT-based palmprint matching, called the self-geometric relationship-based filter (SGR-filter) is presented. While existing SIFT matching considers only the relationship between the SIFT points of the query image, on one hand, and their corresponding points in the reference image, on the other hand, SGR-filtering further takes into account the geometric relationship between SIFT points within the query image in comparison with the relationship of the corresponding matched points in the reference image. Assessed with the proposed SGR-filter on various datasets, the SIFT-based palmprint recognition system has been shown to deliver significantly higher performance when compared with the conventional SIFT matching as well as another related key-points filtering technique. Furthermore, experimental results on a number of different full and partial palmprint datasets have shown the superiority of the proposed system over state-of-the-art techniques.