Fig 15 - uploaded by Svetlana Yanushkevich
Content may be subject to copyright.
Robotic biometrics: talking robot head can be identified by facial expressions; this robot head was created in the Robotics Laboratory, Portland State University (courtesy Prof. M. Perkowski)
Source publication
Similar publications
Citations
... In a modeling system, the real biometrics can be partially or fully substituted with simulated data. This simulated, or synthesized, data is called synthetic biometric [47,48]. There are several reasons for using the synthetic data: ...
... A face model is a composition of the various sub-models (eyes, nose, etc.) The face model consists of the following facial sub-models: eye (shape, open, closed, blinking, iris size and movement, etc.), eyebrow (texture, shape, dynamics), mouth (shape, lip dynamics, tooth and tongue position), nose (shape, nostril dynamics), and ear (shape) [47]. A 3D face model includes two constituents: a face shape model (represented by a 3D geometric mesh) and a skin texture model (generated from 2D images). ...
... To add realism to the image, erosion, dilation, rendering, translation, and rotation operators are used. A similar approach to the continuous growing for initial random set of features using Gabor filters with polar transforms have been reported in [47]. This method itself can be used for designing fingerprint benchmarks with rather complex structural features. ...
This chapter focuses on the emerging applications of biometrics in biomedical and health care solutions. It includes surveys of recent pilot projects, involving new sensors of biometric data and new applications of human physiological and behavioral biometrics. It also shows the newand promising horizons of using biometrics in natural and contactless control interfaces for surgical control, rehabilitation and accessibility.
... This is one of the main current controversies surrounding the status of biometric data. The issue is much more nuanced than it could appear (Yanushkevich, Stoica, Shmerko, & Popel, 2005). First of all, there is not only one biometric and one modality, and it makes little sense to tackle this issue in general terms. ...
The word “biometrics” comes from the ancient Greek and literally means measure (metrics) of life (bio). Today biometrics are largely thought of as providing automated ways of managing and authenticating the identities of individuals. While biometric technologies offer certain advantages in many of their applications (e.g., a greater convenience-to-security ratio than traditional authenticators and identifiers such as complex passwords), these advantages should be carefully weighed against the reasons for ethical concern that biometrics may rise. They include both fundamental and specific ethical issues. Fundamental ethical issues are related to the central question whether biometrics are per se demeaning and abusive of human dignity. Specific ethical issues concern questions related to privacy and data protection, to surveillance, and to large-scale applications. After confronting these ethical issues with the principles set by the Universal Declaration on Bioethics and Human Rights, the conclusion will indicate the potential contribution of biometric technology to the development of human rights.
... This finding agrees with Schmidt and Lee [33], who contend that the relative force produced by muscles is an invariant feature of motor programs associated with a unique pattern of activity. Signature writing can be considered an example of such a learned motor program [34], rationalizing the observed within-individual kinetic consistency. Our finding also aligns with [35] which examined the variation of handwriting grip patterns with age, from childhood through to adulthood. ...
Grip kinetics and their variation are emerging as important considerations in the clinical assessment of handwriting pathologies, fine motor rehabilitation, biometrics, forensics and ergonomic pen design. This study evaluated the intra- and inter-participant variability of grip shape kinetics in adults during signature writing. Twenty (20) adult participants wrote on a digitizing tablet using an instrumented pen that measured the forces exerted on its barrel. Signature samples were collected over 10 days, 3 times a day, to capture temporal variations in grip shape kinetics. A kinetic topography (i.e., grip shape image) was derived per signature by time-averaging the measured force at each of 32 locations around the pen barrel. The normalized cross correlations (NCC) of grip shape images were calculated within- and between-participants. Several classification algorithms were implemented to gauge the error rate of participant discrimination based on grip shape kinetics. Four different grip shapes emerged and several participants made grip adjustments (change in grip shape or grip height) or rotated the pen during writing. Nonetheless, intra-participant variation in grip kinetics was generally much smaller than inter-participant force variations. Using the entire grip shape images as a 32-dimensional input feature vector, a K-nearest neighbor classifier achieved an error rate of [Formula: see text]% in discriminating among participants. These results indicate that writers had unique grip shape kinetics that were repeatable over time but distinct from those of other participants. The topographic analysis of grip kinetics may inform the development of personalized interventions or customizable grips in clinical and industrial applications, respectively.
... Synthetic biometric is defined as "inverse problem of biometric" [70] and is intended to create artificial phenomenon that does not exist in physical reality, but resembles it. The extensive research on synthetic biometric has been conducted at the Biometric Technologies Laboratory, University of Calgary, and results has been recently reported in the World Scientific book "Image Pattern Recognition: Synthesis and Analysis in Biometrics" [69]. ...
Domestic and industrial robots, intelligent software agents, and virtual world avatars are quickly becoming a part of our
society. Just like it is necessary to be able to accurately authenticate identity of human beings, it is becoming essential
to be able to determine identities of the non-biological entities. This paper presents current state of the art in virtual
reality security, focusing specifically on emerging methodologies for avatar authentication. It also makes a strong link between
avatar recognition and current biometric research. Finally, future directions and potential applications for this high impact
research field are discussed.
... Synthetic biometric is defined as "inverse problem of biometric" [70] and is intended to create artificial phenomenon that does not exist in physical reality, but resembles it. The extensive research on synthetic biometric has been conducted at the Biometric Technologies Laboratory, University of Calgary, and results has been recently reported in the World Scientific book "Image Pattern Recognition: Synthesis and Analysis in Biometrics" [69]. ...
Domestic and industrial robots, intelligent software agents, virtual world avatars and other artificial entities are quickly becoming a part of our everyday life. Just like it is necessary to accurately authenticate identity of human beings, it is becoming essential to be able to determine identities of non-biological agents. In this paper, we present the current state of the art in virtual reality security, focusing specifically on emerging methodologies for avatar authentication. We also outline future directions and potential applications for this high impact research field.
... The problems when using DNA in other applications such as authentication systems is that there is no automated process of analyzing the DNA and comparing them. A lot of time and resources are required for sequencing and processing, even though research indicates that this can be done real time with future technology [36]. Due to this, many say that it can not be considered a biometric technology. ...
IntroductionFundamental Design Concepts of the PassDecision-Making Support Assistant DesignHyperspectral Analysis and Synthesis of Facial Skin TexturePrototype Decision-Making Support Assistant DesignThe Training System T-PASSDiscussion and Open ProblemsConclusion
AcknowledgmentsReferences
At some point, in the not-too-distant future, we will stop using money. Indeed, the old ―Life Takes Visa‖ TV commercials, in which the easy flow of commerce in various settings comes to a grinding halt when a patron tries to pay with cash or check rather than swipe a card, is a harbinger of such a transformation. Criminal enterprises depend upon the relative anonymity of cash because it severs the link between the crime and its profits, and the disappearance of a cash economy will have implications for crime. The nature of economic transactions has changed through the years. The ―hard currency‖ of coins and bars became abstracted into paper representations: dollar bills, bearer bonds, and personal checks. Further abstraction into credit and debit cards has permitted the wedding of commerce with electronic communications: a series of numbers (whether on checks or on plastic cards) represents actual wealth held elsewhere, or potential wealth. Money transformed into numbers conveyed across the electronic network changes the nature of security as well. At the present time, two models of security exist—a third is emerging. The dominant security models are token-based (―what you have‖) and knowledge-based (―what you know‖) (Woodward, Orlans, and Higgins, 2003). Tokens include the form of identification requested for paying by check (and in some cases by credit card), electronic passkeys, and the like. Personal Identification Numbers (PINs) and passwords comprise knowledge-based security. When the abstract money of a debit or credit card is presented as payment, an additional abstraction (a PIN and/or a code printed on the reverse side of the embossed card) is required to validate the numbers visible on the card. A thief who obtains the primary numbers needs a second set of numbers or letters (presumably known only to the rightful owner) to use the primary string. When doubt arises, numbers integral to complementary systems – the last four digits of a Social Security Number (SSN), for instance – serve to backstop the system-created safeguards (see note 1) The rise of identity theft necessitates a foolproof way to verify that the often-unseen individual presenting a number as payment is the rightful owner of that number. That search has taken a quantum leap from the four-digit PIN and the three-digit, printed security number on the back of credit cards. The newest form of identity verification is one thought to be almost invulnerable to the vagaries of human memory and considerably more resistant to most ordinary forms of theft. It replaces ―what you have‖ and ―what you know‖ systems with ―who you are‖: biometrics. Biometrics Biometrics is not yet a mature technology, but it is rapidly developing, expanding with the proliferation of digital media. Some banks already offer thumbprint verification for check-cashing, and biometric identification is being encoded into U.S. passports.
Various techniques have been proposed in different literature to analyze biometric samples collected from individuals. However, not a lot of attention has been paid to the inverse problem, which consists of synthesizing artificial biometric samples that can be used for testing existing biometric systems or protecting them against forgeries. In this paper, we present a framework for mouse dynamics biometrics synthesis. Mouse dynamics biometric is a behavioral biometric technology, which allows user recognition based on the actions received from the mouse input device while interacting with a graphical user interface. The proposed inverse biometric model learns from random raw samples collected from real users and then creates synthetic mouse actions for fake users. The generated mouse actions have unique behavioral properties separate from the real mouse actions. This is shown through various comparisons of behavioral metrics as well as a Kolmogorov–Smirnov test. We also show through a two-fold cross-validation test that by submitting sample synthetic data to an existing mouse biometrics analysis model we achieve comparable performance results as when the model is applied to real mouse data.
Even though iris-based systems have proven to be very promising in a world where security is crucial, surprisingly enough, this means of authentication has not been given a very warm welcome from the users. In order to appropriately confront this issue, critical success factors of the deployment of networked-based systems for iris authentication - namely technical, human, and implementation aspects, as well as necessary policies and standards - need to be carefully considered. One of the major success factors is the adoption issue concerning this relatively new technology. The decision to adopt iris-based authentication is influenced by many factors, including user characteristics, social factors, and technology characteristics. Addressing these key factors is extremely valuable for the successful implementation of iris-based technology.
