Search

This paper demonstrates the possibilities of the computer identification of individuals based on their digitized scent signatures using comprehensive two-dimensional gas chromatography with mass spectrometry. This identification is performed by comparing an unknown digital scent sample with digital scent signatures in a database. The olfactronic identification of persons performed by computers follows the olfactoric identification currently performed by trained dogs. Olfactoric identification is considered a subjective method, and therefore it needs to be supported by an objective olfactronic method. The results obtained in this study demonstrate the advantages of olfactronic identification. In addition, the olfactronic identification method makes it possible to compare and store in the database hundreds or even thousands of digital scent signatures based on chemical compounds from samples. A higher recognition percentage of identification is achieved when applying two differently constructed signatures. This article shows that with this approach, the comparison algorithm can reach up to 95-percent correct identification for unknown samples. This is quite a novel point and the rationale of this work. In this study, 400 scent samples from 40 volunteers (20 women and 20 men) were analyzed, where ten scent samples were taken from each person. [ABSTRACT FROM AUTHOR]

One might think that the way through which gender is identified has changed profoundly with the introduction of civil status change procedures. However, if we imagine what the gender identification system could be in the future, if it were diverted and based on self-determination, we can compare it with medieval law. In practice, people took by then the initiative to change their social gender, and if this was challenged, it was done after the fact, because this gender transition led them to contravene other rules concerning marriage and legal inequalities between men and women. Gender judgement would then proceed in the past as well as in the future based on testimonies, rather than written documents.

The present article deals with identification of persons and the use of address forms in the Latvian language viewed sociolinguistically. The aim of the study is to analyse the connection between the identification of the addressee in the pre-communication phase and the use of address form. The aggregated material (approximately 300 speech facts) was recorded from different speech situations and television and radio broadcasts. The present research is based on direct observations, content analysis of essays (written by 100 students from two universities) on the choice between two singular personal pronouns of the Latvian language, tu being informal whereas jūs - polite and formal. Additionally, the data of questionnaire (distributed in 2018) is used. When analysing identification of persons attention is paid to the use of the first name, surname, and words describing their social identity. The term address form is used in the wide sense including pronominal address and patterns of address usage. The tendency to prefer the use of first name is observed in both cases of language means for identification of persons and address forms. For the sake of friendliness, kindness, closer relations (perhaps artificially closer), identifying the employee and addressing the communication partner by name spreads in communication service provider-client, doctor-patient, lecturer-student, teacher-high school student, etc. When analysing the use of address in Latvian, it can be established that both familiar people and strangers are also identified by other features related to their social identity - profession, position, gender, age and other indicators. It can be concluded that a first name is not always sufficient to identify a person. In many cases, the variants of the address agree with the designations that identify the person. However, not all designations that correspond to the social identity of the person being addressed are useful in the address function, for example some names of professions. The results of the content analysis of the essays show that the students, respectively, the authors of the essays, want to preserve the distinction between the two 2nd person pronouns and the traditions of the use of address in Latvian. [ABSTRACT FROM AUTHOR]

The Impostors method is one of the most successful solvers of author verification problems. Given a pair of texts, it aims to find whether the same author wrote them or not. This paper describes a proposed approach with the primary objective of achieving a higher classification accuracy. This higher accuracy is achieved by modifying the vector representations of input texts, such that the effect of them possibly being in different domains is reduced. Such vector modification factors are obtained by the addition of a computational step that empirically estimates the expected difference, or ratio, between the questioned texts' similarity scores against their in-domain samples. Our evaluation confirms that our proposed approach is capable of achieving higher classification accuracy than the original method. Despite the size of the evaluation dataset, some of the increases in the classification accuracy are large enough to allow for observing statistically significant, very significant, and highly significant gains. [ABSTRACT FROM AUTHOR]

The present article analyses the case law of the Supreme Court of Cassation of the Republic of Serbia regarding the identification of persons conducted in pre-investigation proceedings and investigation by the police. The basic assumption is that the quality and precision of the criminal procedure rules and judgments of the Supreme Court of Cassation additionally determine the police actions in the conditions of expected harmonization of these rules with the most important scientific findings on factors ('system variables') that affect the accuracy of identification. To determine how the case law in Serbia treats certain assertions made in the requests for protection of legality regarding violations of criminal procedure regarding the identification of persons, the present article analyzed 33 judgments issued by the Supreme Court of Cassation regarding these requests in the period from 2013 to 2021. Based on the results of the analysis, recommendations regarding the improvement of the current criminal procedure rules referring to the identification of persons in Serbia were provided, and that by respecting research-informed standards for the collection, preservation, and presentation of identification evidence.

This paper proposes a novel architecture that utilises an attention mechanism in conjunction with multi-stream convolutional neural networks (CNN) to obtain high accuracy in human re-identification (Reid). The proposed architecture consists of four blocks. First, the pre-processing block prepares the input data and feeds it into a spatial-temporal two-stream CNN (STC) with two fusion points that extract the spatial-temporal features. Next, the spatial-temporal attentional LSTM block (STA) automatically fine-tunes the extracted features and assigns weight to the more critical frames in the video sequence by using an attention mechanism. Extensive experiments on four of the most popular datasets support our architecture. Finally, the results are compared with the state of the art, which shows the superiority of this approach. [ABSTRACT FROM AUTHOR]

Biometric recognition is often used for adults for a variety of purposes where an individual's identity must be ascertained. However, the biometric recognition of children is an unsolved challenge. Solving this challenge could protect children from identity theft and identity fraud, help in reuniting lost children with their parents, improve border control systems in combatting child trafficking, and assist in electronic record-keeping systems. In order to begin the development of biometric recognition systems for children, researchers collected fingerprint, iris, and outer ear shape biometric information from infants. Each modality provides different challenges. Where possible, the performance of existing hardware and software that was developed for adults was assessed with infants. Where necessary, novel hardware or software was developed. For the ear modality, existing hardware and software which have previously been applied to adults were applied to children. For the iris modality, existing hardware was used to acquire the images, while adjustments to the existing preprocessing algorithms were applied to cater for the localisation and segmentation of infant irises. For the fingerprint modality, novel hardware and image processing software were developed to acquire fingerprints from infants, and convert the images into a format which is backward compatible with existing international standards for minutiae extraction and comparison. The advantages and disadvantages of using each of these modalities during the first year of life were compared, based on both qualitative assessments of usage, and quantitative assessments of performance. While there is no conclusively best modality, recommendations of usage for each modality were provided.

Biometric radiographs have gained importance in recent times owing to the rise in crime and disaster incidents. In recent times, authentication and identification of a person has become an essential part of most of the computer vision automation systems. Conventional fingerprint, iris, face, palm prints fail to recognize the human when the external biometric parts have been damaged due to rashes, wounds, and severe burning. Security, robustness, privacy, and non-forgery are the critical aspects of any person authentication system. In such situations, identification based on radiographs of the skull, hand, and teeth are effective replacement methods. In this paper, a novel forensic hand radiograph based human authentication is proposed using a deep neural network. Three-layered convolutional deep neural network architecture is used for the feature extraction of hand radiographs and for recognition; KNN and SVM classifiers are used. As a part of the experimentation, a total of 750 hand radiographs acquired from 150 subjects of different age groups, professions, and gender are considered. The performance of the algorithm is evaluated based on cross-validation accuracy by varying striding pixels, polling window size, kernel size, and the number of filters. Our experiment reveals that hand radiographs contain biometric information that can be used to identify humans in disaster victim identification. The experimental study also indicates that the proposed approach is significantly effective than conventional methods for the person authentication using hand radiographs.

Current biometrics rely on images obtained from the structural information of physiological characteristics, which is inherently a fatal problem of being vulnerable to spoofing. Here, we studied personal identification using the frequency-domain information based on human body vibration. We developed a bioacoustic frequency spectroscopy system and applied it to the fingers to obtain information on the anatomy, biomechanics, and biomaterial properties of the tissues. As a result, modulated microvibrations propagated through our body could capture a unique spectral trait of a person and the biomechanical transfer characteristics persisted for two months and resulted in 97.16% accuracy of identity authentication in 41 subjects. Ultimately, our method not only eliminates the practical means of creating fake copies of the relevant characteristics but also provides reliable features. [ABSTRACT FROM AUTHOR]

Person re-identification aims to identify pedestrians across non-overlapping camera views. Deep learning methods have been successfully applied to solving the problem and have achieved impressive results. However, these methods rely either on feature extraction or metric learning alone ignoring the joint benefit and mutual complementary effects of the person view-specific representation. In this paper, we propose a multi-view deep network architecture coupled with n-pair loss (JNPL) to eliminate the complex view discrepancy and learn nonlinear mapping functions that are view-invariant. We show that the problem of the large variation in viewpoints of a pedestrian can be well solved using a multi-view network. We simultaneously exploit the complementary representation shared between views and propose an adaptive similarity loss function to better learn a similarity metric. In detail, we first extract view-invariant feature representation from n-pair of images using multi-stream CNN and then aggregate these features for predictions. Given n-positive pairs and a negative example, the network aggregate the feature map of the n-positive pairs and predicts the identity of the person and at the same time learns features that discriminate positive pairs against the negative sample. Extensive evaluations on three large scale datasets demonstrate the substantial advantages of our method over existing state-of-art methods.

This article demonstrates the identification of 10 persons with 99% accuracy achieved by combining micro-Doppler signatures of sit-to-stand and stand-to-sit movements. Data from these movements are measured using two radars installed above and behind the person. Images of Doppler spectrograms generated using the measured data are combined and input to a convolutional neural network. Experimental results show the significantly better accuracy of the proposed method compared with conventional methods that do not perform data combination. The accuracy of identifying 10 participants having similar ages and physical features was 96–99%, despite the relatively small training set (number of training samples: 50–90 Doppler radar images per person). These results suggest that combining sit-to-stand and stand-to-sit movements provides sufficient information for accurate person identification and such information can be remotely acquired using Doppler radar measurements. [ABSTRACT FROM AUTHOR]

The Republic of Latvia must be ready to implement the asylum procedure quickly and efficiently, improving the identification process, as the influx of asylum seekers into the EU may recur. The aim of the research is to study the asylum seekers identification procedure, the factors affecting it, and the possibilities for improving this procedure, to determine nature of the authentication process of documents presented by asylum seekers, to identify authentication problems and to find possible solutions. As a result of the research, the authors have evaluated the process of asylum seekers identification and developed proposals for its improvement, described the factors affecting the authentication of asylum seekers' documents and evaluated the possibilities to exclude these factors. The method of scientific induction, graphical method, document analysis, monographic or descriptive method are used in the research. [ABSTRACT FROM AUTHOR]

The vision-aided pedestrian dead reckoning (PDR) systems have become increasingly popular, thanks to the ubiquitous mobile phone embedded with several sensors. This is particularly important for indoor use, where other indoor positioning technologies require additional installation or body attachment of specific sensors. This paper proposes and develops a novel 3-D passive vision-aided PDR system that uses multiple surveillance cameras and smartphone-based PDR. The proposed system can continuously track users’ movement on different floors by integrating results of inertial navigation and Faster Region-Based Convolutional Neutral Network (Faster R-CNN)-based real-time pedestrian detection, while utilizing existing camera locations and embedded barometers to provide floor/height information to identify user positions in 3-D space. This novel system provides a relatively low-cost and user-friendly solution, which requires no modifications to currently available mobile devices and also the existing indoor infrastructures at many public buildings for the purpose of 3-D indoor positioning. This paper shows the case of testing the prototype in a four-floor building, where it can provide the horizontal accuracy of 0.16 m and the vertical accuracy of 0.5 m. This level of accuracy is even better than required accuracy targeted by several emergency services, including the Federal Communications Commission (FCC). This system is developed for both Android and iOS-running devices. [ABSTRACT FROM AUTHOR]

As one of the most important areas of public safety and security, intelligent video surveillance is an indispensable part of the urban Internet of Things infrastructure. Person re-identification (person re-ID), which aims to track and recognize a person in a multi-camera scene, is mostly viewed as an image retrieval problem, and this task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images, and CNNs are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. We incorporate the deformable convolution module to the traditional baseline to enhance the transformation modeling capability without additional supervision. The new module can readily replace their plain counterparts in the existing CNNs and can be easily trained end-to-end by standard backpropagation. Experiments on two large-scale re-ID datasets confirm the performance of our approach. The experiments also show that learning dense spatial transformation in deep CNNs is effective for person re-ID task and has a bright future in the intelligent video surveillance area.

Falls are one of the greatest risks for older adults living alone at home. This paper presents a novel visual-based fall detection approach to support independent living for older adults through analysing the motion and shape of the human body. The proposed approach employs a new set of features to detect a fall. Motion information of a segmented silhouette when extracted can provide a useful cue for classifying different behaviours, while variation in shape and the projection histogram can be used to describe human body postures and subsequent fall events. The proposed approach presented here extracts motion information using best-fit approximated ellipse and bounding box around the human body, produces projection histograms and determines the head position over time, to generate 10 features to identify falls. These features are fed into a multilayer perceptron neural network for fall classification. Experimental results show the reliability of the proposed approach with a high fall detection rate of 99.60% and a low false alarm rate of 2.62% when tested with the UR Fall Detection dataset. Comparisons with state of the art fall detection techniques show the robustness of the proposed approach.

Automatic identity recognition in fast, reliable and non-intrusive way is one of the most challenging topics in digital world of today. A possible approach to identity recognition is the identification by voice. Characteristics of speech relevant for automatic speaker recognition can be affected by external factors such as noise and channel distortions, but also by speaker-specific conditions—emotional or health states. The improvement of a speaker recognition system by different model training strategies are addressed in this paper in order to obtain the best performance of the system with only a limited amount of neutral and emotional speech data. The models adopted are a Gaussian Mixture Model and i-vectors whose inputs are Mel Frequency Cepstral Coefficients, and the experiments have been conducted on the Russian Language Affective speech database. The results show that the appropriate use of emotional speech in speaker model training improves the robustness of a speaker recognition system – both when tested on neutral and emotional speech. [ABSTRACT FROM AUTHOR]

Existing efforts on person reidentification (re-ID) either ignore the structural interactions among person images or require a highly crafted re-ID structure as a priori information. In contrast, our approach formulates person re-ID as a deep structured prediction problem that outperforms the state-of-the-art methods by utilizing neural-style-transfer-based structure sampling and fully parameterized energy networks. [ABSTRACT FROM AUTHOR]

Confirming the identity of the accused is a critical component of many criminal trials. However, recent evidence suggests this process is highly error prone and leads to unacceptably high rates of wrongful conviction (Innocence Project, 2015). When photographic identification evidence is ambiguous, facial mapping practitioners may be called upon to make comparisons between images of the culprit and the accused. This practice assumes that the techniques employed are reliable and can be used to assist the court in making identity confirmation decisions. However, previous experimental work in this area has established that many of these techniques are unreliable (Kleinberg, Vanezis & Burton, 2007; Strathie, McNeill & White, 2012). We extend these findings by examining another facial mapping technique that uses gridlines, drawn between face-pairs, as a potential face matching aid (Oxlee, 2007). Results show that a simple side-by-side presentation of face-pairs without gridlines produces most accurate responding. Moreover, the application of the grideline technique increases the likelihood that two different face pairs will judged to be the same. These findings suggest that continuing to admit facial mapping evidence in court is likely to increase, rather than decrease, the incidence of wrongful conviction.

Probably many people have heard stories about spiritualism, s?ances in entire darkness, and mediumship claiming to establish contact to deceased persons. Much less known is that this is not just a historic or fictional matter, but today it is still possible to experience such s?ances, with some mediums even holding s?ances open to the public. There, various phenomena can be witnessed, which are a serious challenge for the rational mind. This article does not want to engage in the discussion between skeptical mainstream science and convinced psi-researchers about the authenticity of these phenomena, but it rather follows an undogmatic, curiositydriven approach: Let us see what kind of data audio measurements can provide in this field! Ideally, there is something into it, both for psi-research as well as for audio signal processing. [ABSTRACT FROM PUBLISHER]

This paper focuses on identification of persons entering objects of crucial infrastructure and subsequent detection of movement in parts of objects. It explains some of the technologies and approaches to processing specific image information within existing building apparatus. The article describes the proposed algorithm for detection of persons. It brings a fresh approach to detection of moving objects (groups of persons involved) in enclosed areas focusing on securing freely accessible places in buildings. Based on the designed algorithm of identification with presupposed utilisation of 3D application, motion trajectory of persons in delimited space can be automatically identified. The application was created in opensource software tool using the OpenCV library.

Ridge frequency is an important parameter in fingerprint image processing and feature extraction. However, ridge frequency estimation is a difficult task in noisy fingerprint images. A simple and accurate method for the computation of fingerprint ridge frequency using the Fourier spectrum is proposed. The results of the experiments conducted on a collection of fingerprints as well as a quantitative method for performance evaluation based on a Gabor filter-bank are presented. The proposed method is robust with respect to noise and reliable frequency images are obtained.

Eye movements are a relatively novel data source for biometric identification. When video cameras applied to eye tracking become smaller and more efficient, this data source could offer interesting opportunities for the development of eye movement biometrics. In this paper, we study primarily biometric identification as seen as a classification task of multiple classes, and secondarily biometric verification considered as binary classification. Our research is based on the saccadic eye movement signal measurements from 109 young subjects. In order to test the data measured, we use a procedure of biometric identification according to the one-versus-one (subject) principle. In a development from our previous research, which also involved biometric verification based on saccadic eye movements, we now apply another eye movement tracker device with a higher sampling frequency of 250 Hz. The results obtained are good, with correct identification rates at 80–90% at their best. [ABSTRACT FROM AUTHOR]

Due to the ability of millimeter waves (mmWs) to penetrate dielectric materials, such as plastic, polymer, and clothes, the mmW imaging technology has been widely used for the detection of concealed weapons and objects. The use of mmW images has also recently been proposed for biometric person recognition to overcome certain limitations in image acquisition at visible frequencies. This paper proposes a biometric person recognition system based on the shape information extracted from real mmW images. To this aim, we report experimental results using the mmW images with different body shape-based feature approaches, such as contour coordinates, shape contexts, Fourier descriptors, and row and column profiles. We also study various distance-based and classifier-based matching schemes. Experimental results suggest the potential of performing person recognition through mmW imaging using only shape information, a functionality that could be integrated in the security scanners deployed in airports. [ABSTRACT FROM PUBLISHER]

Biometric identification is one of the most secure existing identification methods. Algorithms based on eye tracking techniques are being studied now by many authors as eye trackers had become more accessible during the last few years. This paper is related to a biometric identification approach and a problem of providing accurate identification results by using low-frequency eye tracker. This paper presents a review of the related works in the field as well as a general classification of different identification types. We stated a formal description of a saccade and an analyzed fragment of the gaze trajectory containing a saccade, which is based on the finite differences method, and revealed features of the eye movements that can be used for the identification purpose. Two classifiers are proposed and compared based on the experimental results obtained for them. [ABSTRACT FROM PUBLISHER]

Biometric recognition systems have been widely used globally. However, one effective and highly accurate biometric authentication method, palmprint recognition, has not been popularly applied as it should have been, which could be due to the lack of small, flexible and user-friendly acquisition systems. To expand the use of palmprint biometrics, we propose a novel palmprint acquisition system based on the line-scan image sensor. The proposed system consists of a customized and highly integrated line-scan sensor, a self-adaptive synchronizing unit, and a field-programmable gate array controller with a cross-platform interface. The volume of the proposed system is over 94% smaller than the volume of existing palmprint systems, without compromising its verification performance. The verification performance of the proposed system was tested on a database of 8000 samples collected from 250 people, and the equal error rate is 0.048%, which is comparable to the best area camera-based systems. [ABSTRACT FROM AUTHOR]

Human occupancy detection and localization are important in a variety of smart building applications including building security, assisted living monitors, and energy-efficient heating ventilation and air cooling and lighting. Current implementation of such systems is limited by motion–sensor technologies, e.g., passive infrared (PIR) and ultrasonic sensors, which substitute as occupancy detectors but ultimately suffer from an inability to detect stationary objects. Capacitive sensing can detect stationary objects, but the technology has almost exclusively been developed for short-range human detection and localization, e.g., touch-screen human interfacing of smart devices. This paper presents a transmitter–receiver platform for research and development of capacitive sensing for long-range human occupancy detection and localization. During testing, the system revealed a detection range of 3.5 m, a typical room dimension in homes. Further, tests of a multitransmitter single-receiver system in a 3.2~\text m \times 3.2 m space showed the system’s potential for occupant localization. Ultimately, this system represents an alternative to PIR and ultrasonic motion sensors, and has the potential to increase smart building system implementation. [ABSTRACT FROM AUTHOR]

Localization, tracking, and recognition of objects and humans are basic tasks that are of high value in the applications of ambient intelligence. Sensing floors were introduced to address these tasks in a non-intrusive way. To recognize the humans moving on the floor, they are usually first localized, and then a set of gait features are extracted (stride length, cadence, and pressure profile over a footstep). However, recognition generally fails when several people stand or walk together, preventing successful tracking. This paper presents a detection, tracking, and recognition technique which uses objects’ weight. It continues working even when tracking individual persons becomes impossible. Inspired by computer vision, this technique processes the floor pressure-image by segmenting the blobs containing objects, tracking them, and recognizing their contents through a mix of inference and combinatorial search. The result lists the probabilities of assignments of known objects to observed blobs. The concept was successfully evaluated in daily life activity scenarii, involving multi-object tracking and recognition on low-resolution sensors, crossing of user trajectories, and weight ambiguity. This technique can be used to provide a probabilistic input for multi-modal object tracking and recognition systems. [ABSTRACT FROM PUBLISHER]

This article examines in great detail the most relevant security and privacy issues affecting the protocols used by contactless chips integrated in ePassports, and presents all relevant literature together with some new attacks and insights that could help in improving future standards and the next generations of ePassports. [ABSTRACT FROM AUTHOR]

The availability of electronic health data favors scientific advance through the creation of repositories for secondary use. Data anonymization is a mandatory step to comply with current legislation. A service for the pseudonymization of electronic healthcare record (EHR) extracts aimed at facilitating the exchange of clinical information for secondary use in compliance with legislation on data protection is presented. According to ISO/TS 25237, pseudonymization is a particular type of anonymization. This tool performs the anonymizations by maintaining three quasi-identifiers (gender, date of birth, and place of residence) with a degree of specification selected by the user. The developed system is based on the ISO/EN 13606 norm using its characteristics specifically favorable for anonymization. The service is made up of two independent modules: the demographic server and the pseudonymizing module. The demographic server supports the permanent storage of the demographic entities and the management of the identifiers. The pseudonymizing module anonymizes the ISO/EN 13606 extracts. The pseudonymizing process consists of four phases: the storage of the demographic information included in the extract, the substitution of the identifiers, the elimination of the demographic information of the extract, and the elimination of key data in free-text fields. The described pseudonymizing system was used in three telemedicine research projects with satisfactory results. A problem was detected with the type of data in a demographic data field and a proposal for modification was prepared for the group in charge of the drawing up and revision of the ISO/EN 13606 norm. [ABSTRACT FROM PUBLISHER]

Signature-based detection is no longer an effective way to detect and block malware; whitelisting is much more effective. Whitelisting can vastly reduce an organization's attack surface, letting defenders focus on more advanced threats. It also can force attackers to use expensive exploits to execute code remotely and can make it difficult for attackers to maintain persistence. Many organizations already own tools to implement whitelisting, so the only cost is the time and effort to properly implement them. [ABSTRACT FROM PUBLISHER]

Humans are able to recognize small number of people they know well by the way they walk. This ability represents basic motivation for using human gait as the means for biometric identification. Such biometric can be captured at public places from a distance without subject's collaboration, awareness or even consent. Although current approaches give encouraging results, we are still far from effective use in practical applications. In general, methods set various constraints to circumvent the influence factors like changes of view, walking speed, capture environment, clothing, footwear, object carrying, that have negative impact on recognition results. In this paper we investigate the influence of walking speed variation to different visual based gait recognition approaches and propose normalization based on geometric transformations, which mitigates its influence on recognition results. With the evaluation on MoBo gait dataset we demonstrate the benefits of using such normalization in combination with different types of gait recognition approaches. [ABSTRACT FROM AUTHOR]

Advances in cameras and web technology have made it easy to capture and share large amounts of video data over to a large number of people. A large number of cameras oversee public and semi-public spaces today. These raise concerns on the unintentional and unwarranted invasion of the privacy of individuals caught in the videos. To address these concerns, automated methods to de-identify individuals in these videos are necessary. De-identification does not aim at destroying all information involving the individuals. Its ideal goals are to obscure the identity of the actor without obscuring the action. This paper outlines the scenarios in which de-identification is required and the issues brought out by those. We also present an approach to de-identify individuals from videos. Our approach involves tracking and segmenting individuals in a conservative voxel space involving x, y, and time. A de-identification transformation is applied per frame using these voxels to obscure the identity. Face, silhouette, gait, and other characteristics need to be obscured, ideally. We show results of our scheme on a number of videos and for several variations of the transformations. We present the results of applying algorithmic identification on the transformed videos. We also present the results of a user-study to evaluate how well humans can identify individuals from the transformed videos. [ABSTRACT FROM PUBLISHER]

Face recognition is widely considered as one of the most promising biometric techniques, allowing high recognition rates without being too intrusive. Many approaches have been presented to solve this special pattern recognition problem, also addressing the challenging cases of face changes, mainly occurring in expression, illumination, or pose. On the other hand, less work can be found in literature that deals with partial occlusions (i.e., sunglasses and scarves). This paper presents FAce Recognition against Occlusions and Expression Variations (FARO) as a new method based on partitioned iterated function systems (PIFSs), which is quite robust with respect to expression changes and partial occlusions. In general, algorithms based on PIFSs compute a map of self-similarities inside the whole input image, searching for correspondences among small square regions. However, traditional algorithms of this kind suffer from local distortions such as occlusions. To overcome such limitation, information extracted by PIFS is made local by working independently on each face component (eyes, nose, and mouth). Distortions introduced by likely occlusions or expression changes are further reduced by means of an ad hoc distance measure. In order to experimentally confirm the robustness of the proposed method to both lighting and expression variations, as well as to occlusions, FARO has been tested using AR-Faces database, one of the main benchmarks for the scientific community in this context. A further validation of FARO performances is provided by the experimental results produced on Face Recognition Grand Challenge database. [ABSTRACT FROM AUTHOR]

Authentication of handwritten signatures is becoming increasingly important. With a rapid increase in the number of people who access Tablet PCs and PDAs, online signature verification is one of the most promising techniques for signature verification. This paper proposes a new algorithm that performs a Monte Carlo based Bayesian scheme for online signature verification. The new algorithm consists of a learning phase and a testing phase. In the learning phase, semi-parametric models are trained using the Markov Chain Monte Carlo (MCMC) technique to draw posterior samples of the parameters involved. In the testing phase, these samples are used to evaluate the probability that a signature is genuine. The proposed algorithm achieved an EER of 1.2% against the MCYT signature corpus where random forgeries are used for learning and skilled forgeries are used for evaluation. An experimental result is also reported with skilled forgery data for learning. [ABSTRACT FROM PUBLISHER]