Search

The diffusion of fingerprint verification systems for security applications makes it urgent to investigate the embedding of software-based presentation attack detection algorithms (PAD) into such systems. Companies and institutions need to know whether such integration would make the system more "secure" and whether the technology available is ready, and, if so, at what operational working conditions. Despite significant improvements, especially by adopting deep learning approaches to fingerprint PAD, current research did not state much about their effectiveness when embedded in fingerprint verification systems. We believe that the lack of works is explained by the lack of instruments to investigate the problem, that is, modeling the cause-effect relationships when two non-zero error-free systems work together. Accordingly, this paper explores the fusion of PAD into verification systems by proposing a novel investigation instrument: a performance simulator based on the probabilistic modeling of the relationships among the Receiver Operating Characteristics (ROC) of the two individual systems when PAD and verification stages are implemented sequentially. As a matter of fact, this is the most straightforward, flexible, and widespread approach. We carry out simulations on the PAD algorithms' ROCs submitted to the most recent editions of LivDet (2017-2019), the state-of-the-art NIST Bozorth3, and the top-level Veryfinger 12 matchers. Reported experiments explore significant scenarios to get the conditions under which fingerprint matching with embedded PAD can improve, rather than degrade, the overall personal verification performance.

The International Fingerprint Liveness Detection Competition is an international biennial competition open to academia and industry with the aim to assess and report advances in Fingerprint Presentation Attack Detection. The proposed "Liveness Detection in Action" and "Fingerprint representation" challenges were aimed to evaluate the impact of a PAD embedded into a verification system, and the effectiveness and compactness of feature sets for mobile applications. Furthermore, we experimented a new spoof fabrication method that has particularly affected the final results. Twenty-three algorithms were submitted to the competition, the maximum number ever achieved by LivDet., Preprint version of a paper accepted at IJCB 2021

We investigated the threat level of realistic attacks using latent fingerprints against sensors equipped with state-of-art liveness detectors and fingerprint verification systems which integrate such liveness algorithms. To the best of our knowledge, only a previous investigation was done with spoofs from latent prints. In this paper, we focus on using snapshot pictures of latent fingerprints. These pictures provide molds, that allows, after some digital processing, to fabricate high-quality spoofs. Taking a snapshot picture is much simpler than developing fingerprints left on a surface by magnetic powders and lifting the trace by a tape. What we are interested here is to evaluate preliminary at which extent attacks of the kind can be considered a real threat for state-of-art fingerprint liveness detectors and verification systems. To this aim, we collected a novel data set of live and spoof images fabricated with snapshot pictures of latent fingerprints. This data set provide a set of attacks at the most favourable conditions. We refer to this method and the related data set as "ScreenSpoof". Then, we tested with it the performances of the best liveness detection algorithms, namely, the three winners of the LivDet competition. Reported results point out that the ScreenSpoof method is a threat of the same level, in terms of detection and verification errors, than that of attacks using spoofs fabricated with the full consensus of the victim. We think that this is a notable result, never reported in previous work., Comment: Accepted for the 25th International Conference on Pattern Recognition (ICPR 2020)

In this paper, we investigate multiple snapshot fusion of textural features for palmvein recognition including identification and verification. Although the literature proposed several approaches for palmvein recognition, the palmvein performance is still affected by identification and verification errors. As well-known, palmveins are usually described by line-based methods which enhance the vein flow. This is claimed to be unique from person to person. However, palmvein images are also characterized by texture that can be pointed out by textural features, which relies on recent and efficient hand-crafted algorithms such as Local Binary Patterns, Local Phase Quantization, Local Tera Pattern, Local directional Pattern, and Binarized Statistical Image Features (LBP, LPQ, LTP, LDP and BSIF, respectively), among others. Finally, they can be easily managed at feature-level fusion, when more than one sample can be acquired for recognition. Therefore, multi-snapshot fusion can be adopted for exploiting these features complementarity. Our goal in this paper is to show that this is confirmed for palmvein recognition, thus allowing to achieve very high recognition rates on a well-known benchmark data set., Comment: 22 pages, 5 figures

We present a novel descriptor for crowd behavior analysis and anomaly detection. The goal is to measure by appropriate patterns the speed of formation and disintegration of groups in the crowd. This descriptor is inspired by the concept of one-dimensional local binary patterns: in our case, such patterns depend on the number of group observed in a time window. An appropriate measurement unit, named "trit" (trinary digit), represents three possible dynamic states of groups on a certain frame. Our hypothesis is that abrupt variations of the groups' number may be due to an anomalous event that can be accordingly detected, by translating these variations on temporal trit-based sequence of strings which are significantly different from the one describing the "no-anomaly" one. Due to the peculiarity of the rationale behind this work, relying on the number of groups, three different methods of people group's extraction are compared. Experiments are carried out on the Motion-Emotion benchmark data set. Reported results point out in which cases the trit-based measurement of group dynamics allows us to detect the anomaly. Besides the promising performance of our approach, we show how it is correlated with the anomaly typology and the camera's perspective to the crowd's flow (frontal, lateral)., Comment: Accepted for the 25th International Conference on Pattern Recognition (ICPR 2020)

One of the biggest problems of agriculture is the reckless use of pesticides and their incorrect application with consequent waste of product and environmental pollution. The spray application characterization is a good preventive technique to limit the volume of a distributed product, to perform a more efficient application and to restrict the spray drift. Since there is no specific sampling technique useful for every context, it is necessary that every methodology is known in all its aspects before being employed. The colorimetry, fluorimetry and spectrometry methods are very accurate, but they are costly and time-consuming compared to a Water-Sensitive Paper (WSP) assessment performed by an image analysis software. This kind of software can detect and estimate many drops features using an image often obtained from a scanner. The objective of work was to develop a MATLAB code to evaluate the spray distribution over WSPs. After a pre-processing step in which the WSPs were isolated inside the image, the individual drops were identified using the difference between their color (blue) and the remaining dry part of the paper (yellow). Once the surface of every drop was estimated, it was possible to assess the number of the drops per cm2, the Normal Median Diameter (NMD) and the Normal Volume Diameter (VMD).

In this study we investigate a textural processing method of electroencephalography (EEG) signal as an indicator to estimate the driver's vigilance in a hypothetical Brain-Computer Interface (BCI) system. The novelty of the solution proposed relies on employing the one-dimensional Local Binary Pattern (1D-LBP) algorithm for feature extraction from pre-processed EEG data. From the resulting feature vector, the classification is done according to three vigilance classes: awake, tired and drowsy. The claim is that the class transitions can be detected by describing the variations of the micro-patterns' occurrences along the EEG signal. The 1D-LBP is able to describe them by detecting mutual variations of the signal temporarily "close" as a short bit-code. Our analysis allows to conclude that the 1D-LBP adoption has led to significant performance improvement. Moreover, capturing the class transitions from the EEG signal is effective, although the overall performance is not yet good enough to develop a BCI for assessing the driver's vigilance in real environments., Comment: Accepted for the 25th International Conference on Pattern Recognition (ICPR 2020)

The boosting on the need of security notably increased the amount of possible facial recognition applications, especially due to the success of the Internet of Things (IoT) paradigm. However, although handcrafted and deep learning-inspired facial features reached a significant level of compactness and expressive power, the facial recognition performance still suffers from intra-class variations such as ageing, facial expressions, lighting changes, and pose. These variations cannot be captured in a single acquisition and require multiple acquisitions of long duration, which are expensive and need a high level of collaboration from the users. Among others, self-update algorithms have been proposed in order to mitigate these problems. Self-updating aims to add novel templates to the users' gallery among the inputs submitted during system operations. Consequently, computational complexity and storage space tend to be among the critical requirements of these algorithms. The present paper deals with the above problems by a novel template-based self-update algorithm, able to keep over time the expressive power of a limited set of templates stored in the system database. The rationale behind the proposed approach is in the working hypothesis that a dominating mode characterises the features' distribution given the client. Therefore, the key point is to select the best templates around that mode. We propose two methods, which are tested on systems based on handcrafted features and deep-learning-inspired autoencoders at the state-of-the-art. Three benchmark data sets are used. Experimental results confirm that, by effective and compact feature sets which can support our working hypothesis, the proposed classification-selection approaches overcome the problem of manual updating and, in case, stringent computational requirements., This is an original manuscript of an article published by Elsevier in Pattern Recognition on 27 November 2019. Available online: https://doi.org/10.1016/j.patcog.2019.107121

The International Fingerprint liveness Detection Competition (LivDet) is an open and well-acknowledged meeting point of academies and private companies that deal with the problem of distinguishing images coming from reproductions of fingerprints made of artificial materials and images relative to real fingerprints. In this edition of LivDet we invited the competitors to propose integrated algorithms with matching systems. The goal was to investigate at which extent this integration impact on the whole performance. Twelve algorithms were submitted to the competition, eight of which worked on integrated systems., Preprint version of a paper accepted at ICB 2019

Nowadays, facial authentication systems are present in many daily life devices. Their performance is influenced by the appearance of the facial trait that changes according to many factors such as lighting, pose, variations over time and obstructions. Adaptive systems follow these variations by updating themselves through images acquired during system operations. Although the literature proposes many possible approaches, their evaluation is often left to data set not explicitly conceived to simulate a real application scenario. The substantial absence of an appropriate and objective evaluation set is probably the motivation of the lack of implementation of adaptive systems in real devices. This paper presents a facial dataset acquired by videos in the YouTube platform. The collected images are particularly suitable for evaluating adaptive systems as they contain many changes during the time-sequence. A set of experiments of the most representative self adaptive approaches recently appeared in the literature is also performed and discussed. They allow to give some initial insights about pros and cons of facial adaptive authentication systems by considering a medium-long term time window of the investigated systems performance.

The usual trend for the conventional palmvein recognition techniques is first to extract discriminative hand-crafted feature representations from the raw images, and then feed a classifier with them. Unfortunately, it is not yet clear how the effectiveness of such features may be held in case of a large user population or in environments where the variability among acquisitions of the same person may increase. In order to face with this problem, it may be considered that the use of multiple classifiers may increase the recognition performance with respect to that of the best individual classifier, and also may handle the problem of an effective feature extraction step. In this paper, we explore the ensemble classifier approach based on Random Subspace Method (RSM), where the basic feature space is derived after a preliminary feature reduction step on the source image, and compare results achieved with and without the use of hand-crafted features. Experimental results allow us concluding that this approach leads to better results under different environmental conditions.

Electric power systems are experiencing relevant changes involving the growing penetration of distributed generation and energy storage systems, the introduction of electric vehicles, the management of responsive loads, the proposals for new energy markets and so on. Such evolution is pushing for a paradigm shift: the management must move from traditional planning and manual intervention to full “smartization” of medium and low voltage networks. Peculiarities and criticalities of future power distribution networks originate from the complexity of the system that includes both the physical aspects of electric networks and the cyber aspects, like data elaboration, feature extraction, communication, supervision and control; only fully integrated advanced monitoring systems can foster this transition towards network automation. The design and development of such future networks require distinct kinds of expertise in the industrial and information engineering fields. In this context, this paper provides a comprehensive review of current challenges and multidisciplinary interactions in the development of smart distribution networks.

Palmvein recognition (identification or verification) is gaining ground as a biometric system for personal recognition applications, with an intensive investigation during the past few years. Some researchers have devoted attention to this field, but a lot of issues related to palmvein recognition are still open. This paper provides an overview of current palmvein recognition research, describing in particular the current state of biometric palmvein system components. The beginner researchers can find in this paper the more recent approaches at each stage of biometric palmvein recognition. Also, this overview points out current open issues that need to be addressed and investigated.

Gait recognition is an emerging biometric technology that identifies people through the analysis of the way they walk. The challenge of model-free based gait recognition is to cope with various intra-class variations such as clothing variations, carrying conditions and angle variations that adversely affect the recognition performance. This paper proposes a method to select the most discriminative human body part based on group Lasso of motion to reduce the intra-class variation so as to improve the recognition performance. The proposed method is evaluated using CASIA Gait Dataset B. Experimental results demonstrate that the proposed technique gives promising results.

Recently, there has been a growing interest in the use of brain activity for biometric systems. However, so far these studies have focused mainly on basic features of the Electroencephalography. In this study we propose an approach based on phase synchronization, to investigate personal distinctive brain network organization. To this end, the importance, in terms of centrality, of different regions was determined on the basis of EEG recordings. We hypothesized that nodal centrality enables the accurate identification of individuals. EEG signals from a cohort of 109 64-channels EEGs were band-pass filtered in the classical frequency bands and functional connectivity between the sensors was estimated using the Phase Lag Index. The resulting connectivity matrix was used to construct a weighted network, from which the nodal Eigenvector Centrality was computed. Nodal centrality was successively used as feature vector. Highest recognition rates were observed in the gamma band (equal error rate ( ${\rm EER}) = 0.044$ ) and high beta band ( ${\rm EER} = 0.102$ ). Slightly lower recognition rate was observed in the low beta band ( ${\rm EER} = 0.144$ ), while poor recognition rates were observed for the others frequency bands. The reported results show that resting-state functional brain network topology provides better classification performance than using only a measure of functional connectivity, and may represent an optimal solution for the design of next generation EEG based biometric systems. This study also suggests that results from biometric systems based on high-frequency scalp EEG features should be interpreted with caution.

Growing interest is devoted to understanding how brain signals recorded from scalp electroencephalography (EEG) may represent unique fingerprints of individual neural activity. In this context, the present paper aims to investigate the impact of some of the most commonly used techniques to estimate functional connectivity on the ability to unveil personal distinctive patterns of inter-regional interactions. Different metrics, commonly used to estimate functional connectivity and derived centrality measures, were compared in terms of equal error rate. It is widely accepted that each metric carries specific information in respect to the underlying interactions network. Nevertheless, the reason why these metrics convey different subject specific information has not been investigated yet. Experimental results on two publicly available datasets suggest that different functional connectivity metrics define a peculiar subjective profile of connectivity and have different mechanisms to detect subject-specific patterns of inter-channel interactions. It is important to consider the effects that frequency content and spurious connectivity values may play in determining subject-specific characteristics.

Fingerprint Presentation Attack Detection (FPAD) deals with distinguishing images coming from artificial replicas of the fingerprint characteristic, made up of materials like silicone, gelatine or latex, and images coming from alive fingerprints. Images are captured by modern scanners, typically relying on solid-state or optical technologies. Since from 2009, the Fingerprint Liveness Detection Competition (LivDet) aims to assess the performance of the state-of-the-art algorithms according to a rigorous experimental protocol and, at the same time, a simple overview of the basic achievements. The competition is open to all academics research centers and all companies that work in this field. The positive, increasing trend of the participants number, which supports the success of this initiative, is confirmed even this year: 17 algorithms were submitted to the competition, with a larger involvement of companies and academies. This means that the topic is relevant for both sides, and points out that a lot of work must be done in terms of fundamental and applied research., Comment: presented at ICB 2018

Gait recognition aims to identify people through the analysis of the way they walk. The challenge of model-free based gait recognition is to cope with various intra-class variations such as clothing variations, carrying conditions, and angle variations that adversely affect the recognition performance. This chapter proposes a method to select the most discriminative human body part based on group Lasso of motion to reduce the intra-class variation so as to improve the recognition performance. The proposed method is evaluated using CASIA gait database (dataset B), and the experimental results suggest that our method yields 88.75 % of Correct Classification Rate (CCR) when compared to existing state-of-the-art methods.

The similarities among different acquisitions of the same fingerprint have never been taken into account, so far, in the feature space designed to detect fingerprint presentation attacks. Actually, the existence of such resemblances has only been shown in a recent work where the authors have been able to describe what they called the “user-specific effect”. We present in this paper a first attempt to take advantage of this in order to improve the performance of a FPAD system. In particular, we conceived a binary code of three bits aimed to “detect” such effect. Coupled with a classifier trained according to the standard protocol followed, for example, in the LivDet competition, this approach allowed us to get a better accuracy compared to that obtained with the “generic users” classifier alone.

Recently, the use of brain activity as biometric trait for automatic users recognition has been investigated. EEG (Electroencephalography) signal is more often used in the medical field for diagnostic purposes. However, early EEG studies adopted similar signal properties and processing tools to study individual distinctive characteristics. As a matter of fact, features related mostly to a single region of the scalp were used, thus losing information on possible links among brain areas. In this work we approached the investigation of the EEG signal as possible biometric by focusing on two recent methods based on functional connectivity, which, in contrast with previous approaches, tend to estimate the complex interactions between EEG signals by measuring the time-series statistical interdependence. Thanks to their potential complementary, we explored their fusion by feature-level and match score-level approaches. Experimental results have shown a performance improvement with respect to that of the individual systems.

Electric power systems are experiencing relevant changes involving the growing penetration of distributed generation and energy storage systems, the introduction of electric vehicles, the management of responsive loads, the proposals for new energy markets and so on. Such an evolution is pushing a paradigm shift that is one of the most important challenges in power network design: the management must move from traditional planning and manual intervention to full “smartization” of medium and low voltage networks. Peculiarities and criticalities of future power distribution networks originate from the complexity of the system which includes both the physical aspects of electric networks and the cyber aspects, like data elaboration, feature extraction, communication, supervision and control; only fully integrated advanced monitoring systems can foster this transition towards network automation. The design and development of such future networks require distinct kinds of expertise in the industrial and information engineering fields. In this context, this paper provides a comprehensive review of current challenges and multidisciplinary interactions in the development of smart distribution networks. The aim of this paper is to discuss, in an integrated and organized manner, the state of the art while focusing on the need for interaction between different disciplines and highlighting how innovative and future-proof outcomes of both research and practice can only emerge from a coordinated design of all the layers in the smart distribution network architecture.

Systems for still-to-video face recognition (FR) seek to detect the presence of target individuals based on reference facial still images or mug-shots. These systems encounter several challenges in video surveillance applications due to variations in capture conditions (e.g., pose, scale, illumination, blur and expression) and to camera inter-operability. Beyond these issues, few reference stills are available during enrollment to design representative facial models of target individuals. Systems for still-to-video FR must therefore rely on adaptation, multiple face representation, or synthetic generation of reference stills to enhance the intra-class variability of face models. Moreover, many FR systems only match high quality faces captured in video, which further reduces the probability of detecting target individuals. Instead of matching faces captured through segmentation to reference stills, this paper exploits Adaptive Appearance Model Tracking (AAMT) to gradually learn a track-face-model for each individual appearing in the scene. The Sequential Karhunen-Loeve technique is used for online learning of these track-face-models within a particle filter-based face tracker. Meanwhile, these models are matched over successive frames against the reference still images of each target individual enrolled to the system, and then matching scores are accumulated over several frames for robust spatiotemporal recognition. A target individual is recognized if scores accumulated for a track-face-model over a fixed time surpass some decision threshold. The main advantage of AAMT over traditional still-to-video FR systems is the greater diversity of facial representation that may be captured during operations, and this can lead to better discrimination for spatiotemporal recognition. Compared to state-of-the-art adaptive biometric systems, the proposed method selects facial captures to update an individual's face model more reliably because it relies on information from tracking. Simulation results obtained with the Chokepoint video dataset indicate that the proposed method provides a significantly higher level of performance compared state-of-the-art systems when a single reference still per individual is available for matching. This higher level of performance is achieved when the diverse facial appearances that are captured in video through AAMT correspond to that of reference stills. HighlightsPropose a face recognition system using Adaptive Appearance Model Tracking (AAMT).AAMT learns face models online and matches these models against reference stills.AAMT incorporates greater diversity of facial representation in the models.AAMT selects facial captures more reliably to update an individual's face model.Provides a higher level of performance in still-to-video face recognition.

Systems for still-to-video face recognition (FR) are typically used to detect target individuals in watch-list screening applications. These surveillance applications are challenging because the appearance of faces change according to capture conditions, and very few reference stills are available a priori for enrollment. To improve performance, an adaptive appearance model tracker (AAMT) is proposed for on-line learning of a track-face-model linked to each individual appearing in the scene. Meanwhile, these models are matched over successive frames against stored reference stills images of each target individual (enrolled to the system) for robust spatiotemporal FR. Compared to the gallery-face-models produced by self-updating FR systems, the track-face-models (produced by the AAMT-FR system) are updated from facial captures that are more reliably selected, and can incorporate greater intra-class variations from the operational environment. Track-face-models allow selecting facial captures for modeling more reliably than self-updating FR systems, and can incorporate a greater diversity of intra-class variation from the operational environment. Performance of the proposed approach is compared with several state-of-the-art FR systems on videos from the Chokepoint dataset when a single reference template per target individual is stored in the gallery. Experimental results show that the proposed system can achieve a significantly higher level of FR performance, especially when the diverse facial appearances captured through AAMT correspond to that of reference stills.

Performance of state-of-the-art face recognition (FR) systems is known to be significantly affected by variations in facial appearance, caused mainly by changes in capture conditions and physiology. While individuals are often enrolled to a FR system using a limited number of reference face captures, adapting facial models through re-enrollment or through self-updating with highly confident operational captures has been shown to maintain or improve performance. However, frequent re-enrollment and updating can become very costly, and facial models may be corrupted if misclassified face captures are used for self-updating. This chapter presents an overview of adaptive FR systems that perform self-updating of facial models using operational (unlabelled) data. Adaptive template matching systems are first revised, with a particular focus on system complexity control using template management techniques. A new context-sensitive self-updating approach is proposed to self-update only when highly confident operational data depict new capture conditions. This allows to enhance the modelling of intra-class variations, while mitigating the growth of the system by filtering out redundant information, thus reducing the need to use costly template management techniques during operations. A particular implementation is proposed, where highly confident templates are added according to variations in illumination conditions detected using a global luminance distortion measures. Experimental results using three publicly available FR databases indicate that this approach enables to maintain a level of classification performance comparable to standard self-updating template matching systems, while significantly reducing the memory and computational complexity over time.

Nowadays face recognition systems have many application fields. Unfortunately, lighting variations and ageing effects are still open issues. Moreover, face changes over time due to ageing. A further problem is due to occlusions, for example the glass presence. Re-enrolling user’s face is time-consuming and does not solve above problems. Therefore, unsupervised template update has been proposed, and named self update. Basically, this algorithm adapts/modifies templates or face models by collecting samples during system operations. The most effective variant of self update is based on the collection of multiple templates. However, this approach has been evaluated and tested in conditions under which the possible number of collectable templates is uncostrained. Actually, available resources are limited in memory and computational power, thus it is likely that it is not possible to have more than a pre-set number of templates. In this paper, we propose a classification-selection approach, based on the combination of self update and C-means algorithms, which keeps constant the number of templates and improve the ratio between intra-class variations and inter-class variations for each user. Experimental results show the effectiveness of this method with respect to standard self update.

A spoof or fake is a counterfeit biometric that is used in an attempt to circumvent a biometric sensor. Liveness detection distinguishes between live and fake biometric traits. Liveness detection is based on the principle that additional information can be garnered above and beyond the data procured by a standard authentication system, and this additional data can be used to determine if a biometric measure is authentic.

In order to render a biometric system robust against malicious tampering, it is important to understand the different types of attack and their impact as observed by the liveness and matching scores. In this study, we consider zero-effort impostor attack (referred to as the Z-attack), nonzero-effort impostor attack such as presentation attack or spoofing (S-attack), and other categories of attack involving tampering at the template level (U- and T-attacks). In order to elucidate the impact of all possible attacks, we (1) introduce the concepts of source of origin and symmetric biometric matchers, and (2) subsequently group the attacks into four categories. These views not only improve the understanding of the nature of different attacks but also turn out to ease the design of the classification problem. Following this analysis, we design a novel classification scheme that can take full advantage of the attack-specific data characteristics. Two realisations of the scheme, namely, a mixture of linear classifiers, and a Gaussian Copula-based Bayesian classifier, turn out to outperform a strong baseline classifier based on SVM, as supported by fingerprint spoofing experiments.

The widespread use of personal verification systems based on fingerprints has shown some security weaknesses. Gian Luca Marcialis, assistant professor at the Department of electrical and electronic engineering in the University of Cagliari reports on the first international fingerprint liveness detection competition 2009 – LivDet 2009.

Person re-identification from facial captures remains a challenging problem in video surveillance, in large part due to variations in capture conditions over time. The facial model of a target individual is typically designed during an enrolment phase, using a limited number of reference samples, and may be adapted as new reference videos become available. However incremental learning of classifiers in changing capture conditions may lead to knowledge corruption. This paper presents an active framework for an adaptive multi-classifier system for video-to-video face recognition in changing surveillance environments. To estimate a facial model during the enrolment of an individual, facial captures extracted from a reference video are employed to train an individual-specific incremental classifier. To sustain a high level of performance over time, a facial model is adapted in response to new reference videos according the type of concept change. If the system detects that the facial captures of an individual incorporate a gradual pattern of change, the corresponding classifier(s) are adapted through incremental learning. In contrast, to avoid knowledge corruption, if an abrupt pattern of change is detected, a new classifier is trained on the new video data, and combined with the individual’s previously-trained classifiers. For validation, a specific implementation is proposed, with ARTMAP classifiers updated using an incremental learning strategy based on Particle Swarm Optimization, and the Hellinger Drift Detection Method is used for change detection. Simulation results produced with Faces in Action video data indicate that the proposed system allows for scalable architectures that maintains a significantly higher level of accuracy over time than a reference passive system and an adaptive Transduction Confidence Machine-kNN classifier, while controlling computational complexity.

Adapting classification systems according to new input data streams raises several challenges in changing environments. Although several adaptive ensemble-based strategies have been proposed to preserve previously-acquired knowledge and reduce knowledge corruption, the fusion of multiple classifiers trained to represent different concepts can increase the uncertainty in prediction level, since only a sub-set of all classifier may be relevant. In this paper, a new score-level fusion technique, called $S_{wavg_h}$ , is proposed where each classifier is dynamically weighted according to the similarity between an input pattern and the histogram representation of each concept present in the ensemble. During operations, the Hellinger distance between an input and the histogram representation of every previously-learned concept is computed, and the score of every classifier is weighted dynamically according to the resemblance to the underlying concept distribution. Simulation produced with synthetic problems indicate that the proposed fusion technique is able to increase system performance when input data streams incorporate abrupt concept changes, yet maintains a level of performance that is comparable to the average fusion rule when the changes are more gradual.

Recent experiments, reported in the third edition of Fingerprint Liveness Detection competition (LivDet 2013), have clearly shown that fingerprint liveness detection is a very difficult and challenging task. Although the number of approaches is large, none of them can be claimed as able to detect liveness of fingerprint traits with an acceptable error rate. In our opinion, in order to investigate at which extent this error can be reduced, novel feature sets must be proposed, and, eventually, integrated with existing ones. In this paper, a novel fingerprint liveness descriptor named “BSIF” is described, which, similarly to Local Binary Pattern and Local Phase Quantization-based representations, encodes the local fingerprint texture on a feature vector. Experimental results on LivDet 2011 data sets appear to be encouraging and make this descriptor worth of further investigations.

The vitality detection of fingerprints is currently acknowledged as a serious issue for personal identity verification systems. This problem, raised some years ago, is related to the fact that the 3d shape pattern of a fingerprint can be reproduced using artificial materials. An image quite similar to that of true, alive, fingerprint, is derived if such “fake fingers” are submitted to an electronic scanner. Since introducing hardware dedicated to liveness detection in scanners is expensive, software-based solutions, based on image processing algorithms, have been proposed as alternative. So far, proposed approaches are based on features exploiting characteristics of a live finger (e.g., finger perspiration). Such features can be named live-based, or vitality-based features. In this paper, the authors propose and motivate the use of a novel kind of features exploiting characteristics noticed in the reproduction of fake fingers, that they named fake-based features. Then the authors propose a possibile implementation of this kind of features based on the power spectrum of the fingerprint image. The proposal is compared and integrated with several live-based features at the state-of-the-art, and shows very good liveness detection performances. Experiments are carried out on a data set much larger than commonly adopted ones, containing images from three different optical sensors.

Self-update is the most commonly adopted biometric template update technique in which the system adapts itself to the confidently classified samples. However, the recent works indicate that self-update has limited capability to capture samples representing significant intra-class variations. As an alternative, a biometric template update technique based on the graph-based representation is proposed. This technique can potentially capture samples with significant variations, resulting in efficient adaptation. Until now, the efficacy of these adaptation techniques has been proven only on the basis of experimental evaluations on small data sets. The contribution of this paper lies in (a) conceptual explanation of the functioning of self-update and graph-based techniques to template adaptation leading to efficacy of the latter and (b) evaluation of the performance of these adaptation techniques in comparison to the baseline system without adaptation. Experiments are conducted on the large DIEE data set, explicitly collected for this aim. Reported results validate the superiority of the graph-based technique over self-update.

Adaptive biometric systems have received a recent spurt in biometric community. These systems have the additional capability to adapt themselves using biometric data available during the system's operation. Although several studies have been proposed in this field, no conclusive evidences can be drawn about the expected performance gain on making the biometric system adaptive. This is due to the adoption of different and inappropriate databases, protocols and tools for evaluating adaptive biometric systems. This paper presents a benchmarking study to facilitate fair comparison and independent replication of the results from different research groups. To this aim, this paper describes DIEE multi-modal database consisting of face and fingerprint biometrics and a protocol tailored for adapting as well as evaluating adaptive biometric systems. In addition, several tools for evaluating and visualising the performance gain on making the biometric system adaptive are provided as well. To the best of our knowledge, this is the first attempt to benchmark database, protocol and tools for evaluating adaptive biometric systems operating in verification mode.

A spoof or fake is a counterfeit biometric that is used in an attempt to circumvent a biometric sensor Liveness detection distinguishes between live and fake biometric traits. Liveness detection is based on the principle that additional information can be garnered above and beyond the data procured by a standard verification system, and this additional data can be used to verify if a biometric measure is authentic. The Fingerprint Liveness Detection Competition (LivDet) goal is to compare both software-based (Part 1) and hardware-based (Part 2) fingerprint liveness detection methodologies and is open to all academic and industrial institutions. Submissions for the third edition were much more than in the previous editions of LivDet demonstrating a growing interest in the area. We had nine participants (with eleven algorithms) for Part 1 and two submissions for Part 2.