Image analysis – Applications – Personnel identification
Reexamination Certificate
2003-04-03
2004-11-09
Werner, Brian (Department: 2621)
Image analysis
Applications
Personnel identification
C356S071000, C250S297000, C250S297000, C250S339020
Reexamination Certificate
active
06816605
ABSTRACT:
BACKGROUND OF THE INVENTION
This application relates generally to methods and systems for performing biometric identifications. More specifically, this application relates to methods and systems for performing biometric identification of individuals using linear optical spectroscopy.
Biometric identification describes the process of using one or more physical or behavioral features to identify a person or other biological entity. There are two common modes in which biometric identification occurs: one-to-many (identification) and one-to-one (verification). One-to-many identification attempts to answer the question of, “do I know you?” The biometric measurement device collects a set of biometric data from a target individual. From this information alone it assesses whether the person was previously enrolled in the biometric system. Systems that perform the one-to-many identification task such as the FBI's Automatic Fingerprint Identification System (AFIS) are generally very expensive (several million dollars or more) and require many minutes to detect a match between an unknown sample and a large database containing hundreds of thousands or millions of entries. The one-to-one mode of biometrics answers the question of, “are you who you say you are?” This mode is used in cases where an individual makes a claim of identity using a code, magnetic card, or other means, and the device uses the biometric data to confirm the identity of the person by comparing the target biometric data with the enrolled data that corresponds with the purported identity.
There also exists at least one variant between these two modes. This variant occurs in the case where a small number of individuals are contained in the enrolled database and the biometric application requires the determination of only whether a target individual is among the enrolled set. In this case, the exact identity of the individual is not required and thus the task is somewhat different (and often easier) than the identification task described above. This variant might be useful in applications where the biometric system is used to secure an expensive, dangerous, or complex piece of machinery. In this example, only authorized people should be able to use the equipment, but it might not be of interest to determine specifically which of the authorized personnel are using it at a particular time.
Although in general the one-to-many identification task is more difficult than one-to-one, the two tasks become the same as the number of recognized or authorized users for a given biometric device decreases to just a single individual. Situations in which a biometric identification task has only a small number of entries in the authorization database are quite common. For example, biometric access to a residence, to a personal automobile, to a personal computer, to a cellular telephone, to a handgun, and other such personal devices typically require an authorization database of just a few people.
Biometric identification and verification are useful in many applications. Examples include verifying identity prior to activating machinery or gaining entry to a secure area. Another example would be identification for matching an individual to records on file for that individual, such as for matching hospital patient records when the individual's identity is unknown. Biometric identification is also useful to match police records at the time a suspect is apprehended, but true identity of the suspect is not known. Additional uses of biometric identification or verification include automotive keyless start and entry applications, secure computer and network access, automated financial transactions, authorized handgun use, and time-and-attendance applications.
Current methods for biometric identification are manifold, but some of the most common techniques include fingerprint pattern matching, facial recognition, hand geometry, iris scanning, and voice recognition. Each of these technologies addresses the need for biometric identification to some extent. However, due to cost, performance, or other issues, each of the existing methods has advantages and disadvantages relative to the other technologies.
One present biometric product on the market is known as the LiveGrip™, made by Advanced Biometrics, Inc. This product is based on the technology disclosed in U.S. Pat. No. 5,793,881, by Stiver et al. In this patent, Stiver et al. disclose an identification system that is a security device, which consists of a cylindrical or elongated transparent shell with an internal light source and a means to scan the hand of the person grasping the shell to record the internal structure or subcutaneous structure of the hand using an imaging methodology. The system uses near-infrared light to image the pattern of blood vessels and associated tissue in the hand. The LiveGrip product based on this patent is claimed to have reduced the ability for an intruder to fool the biometric system as they claim can be easily done using a latex mold with many finger print readers or hand-geometry systems. However, the imaging approach requires good quality optics and/or detector arrays that add to both system complexity and cost. Further, the system relies on imaging blood vessels, and therefore, requires that the same site be presented to the system in use as during enrollment and further requires that the repositioning of the site is accurate enough to allow the software to align the two images to confirm identity. Finally, the size of the sensor head is limited to the portion of the hand that must be imaged for accurate identification.
Others in the field have disclosed methods and systems for measuring properties of samples based on an optical nonlinearity associated with the depletion of the density of states that depends on the presence and magnitude of multiple simultaneous wavelengths of illumination light. In some cases these nonlinear optical spectroscopic sensors are mounted on linear potentiometers and are adjusted to measure the optical properties of the tissue between consecutive pairs of fingers. The resulting measurements from potentiometers are combined with the measurements from the nonlinear optical probes to act as inputs into an identification process.
Living human tissue is recognized as a dynamic system containing a multitude of components and analyte information that is particularly useful in the medical profession for diagnosing, treating and monitoring human physical conditions. To this end, effort has been directed toward developing methods for non-invasive measurement of tissue constituents using spectroscopy. The spectrographic analysis of living tissue has been focused on the identification of spectral information that defines individual analytes and relates such spectral data to the analyte's concentration. Concentrations of these analytes vary with time in an individual person. Acquiring tissue spectral data with sufficient accuracy for use in diagnosis and treatment has proven difficult. Difficulties in conducting the analysis have been found that are related to the fact that the tissue system is a complex matrix of materials with differing refractive indices and absorption properties. Further, because the constituents of interest are many times present at very low concentrations, high concentration constituents, such as water, have had a detrimental impact on identifying the low level constituent spectral information and giving an accurate reading of the desired constituent concentration. Development of these techniques has always focused on the changes in spectral output with change in concentration of a dynamic analyte of interest, such as glucose. The techniques disclosed are focused on identifying concentrations of specific analytes, the concentration of which is expected to vary with time.
Improved methods and apparatus for gathering and analyzing a near-infrared tissue spectrum for an analyte concentration are disclosed in the following U.S. Patent applications and issued patents, each of which is incorporated
Corcoran Stephen P.
Nixon Kristin A.
Rowe Robert K.
Lumidigm, Inc.
Werner Brian
LandOfFree
Methods and systems for biometric identification of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Methods and systems for biometric identification of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods and systems for biometric identification of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3313440