Image analysis – Applications – Personnel identification
Reexamination Certificate
1997-03-25
2001-01-09
Johns, Andrew W. (Department: 2721)
Image analysis
Applications
Personnel identification
C382S125000
Reexamination Certificate
active
06173068
ABSTRACT:
BACKGROUND OF THE INVENTION
This invention relates generally to the field of image recognition and processing and specifically to methods and systems for identifying, diagnosing, and treating people based on thermal minutiae within a person's body, primarily the face.
Improved methods for automated access control and surveillance are vital to ensure the continued security of nuclear weapon storage facilities, as well as other sensitive or valuable items. Potential threats range from terrorist bombings, insider thefts, and industrial espionage to sabotage by environmental activists. There is concern for increased vigilance in the protection of critical strategic assets.
Current technology being used for access control is not sufficient reliable, secure, fast rugged or cost effective for routine unattended operations at high-security locations. The challenge is to develop systems to secure facilities and personnel from internal and external threats in a cost effective and timely manner. Replacing human guards with automated systems can provide a significant cost savings.
The requirement to positively identify each individual seeking access to a facility or to information or services is widespread. Manpower-intensive guard brigades are deployed at public functions to protect celebrities, and at locations where valuable or important items are stored. Guards are used to screen entrants based upon recognizing either the person or some credential he carries. Identification credentials such as photo ID badges and driver's licenses are widely used for manual identification when cashing checks or using credit cards. Manual checking of such identification cards may not recognize cases where the card is forgery or where the person using it is not the rightful owner of the card. To assist in solving that problem, more sophisticated identifying characteristics may be used on the card, and features may be added to make the card more difficult to counterfeit. The use of biometric characteristics such as fingerprints, signatures, visual descriptions, or photographs is becoming more common. Such information can either be readable manually or encoded for reading by an automated system.
When the identification system is fully automated, without a human attendant, biometric sensors at the access location can compare the characteristics of a person at the location with the stored characteristics of the person he is claiming to be. When initially issuing permission for a person to access a biometrically-controlled system or location, his biometric characteristics are recorded in the system memory, and also recorded on an identification card, for later comparison by the system controller with his live characteristics.
BRIEF DESCRIPTION OF THE PRIOR ART
Current biometric identification systems include use of inkless fingerprint systems (called “live scan” units), retinal scanners, hand geometry measuring devices, voice recognition, handwriting recognition, and facial recognition systems which use either visual or infrared cameras. Use of fingerprints is generally considered the most secure method for positive identification. However, when used in an unattended mode, fingerprints can be lifted from one location or surface and positioned at another location. Therefore unattended use of fingerprints for identification at locations requiring very high security is not acceptable. A more common limitation to widespread use of fingerprints for identification is the requirement for placing one or more clean fingers on a glass plate for imaging by the fingerprint recognition system. This requires that the hands be free and relatively clean, and that the glass plates be maintained intact and clean. The plates are vulnerable to vandalism. When used for access control at a busy location, there is a time delay associated with unloading the hands and positioning the fingers properly. Also, users must cooperate with the system. In certain scenarios of use, cooperation of the subject may be difficult to obtain. Furthermore, many persons have a reluctance to being fingerprinted for an identity card, since they associate the process with criminal activities.
Fingerprints traditionally have been the sole means of positive identification admissible as evidence in criminal trials in the U.S. Fingerprinting of criminals, military personnel, persons seeking security clearances, and persons applying for sensitive jobs has been performed for many years. The FBI established and maintained a card file in which each person's fingerprints were printed by rolling the fingers first on an inked pad and then on the card. Much of the original FBI fingerprint file of rolled prints has now been digitized and made available on-line for computer access. The process of digitizing the historical files, and the continuing task of maintaining current fingerprint files, has cost hundreds of millions of dollars during the past ten years alone. Aside from the labor costs of performing the digitization and managing the search tasks through the database, significant R&D has been performed to develop specialized software for comparing unknown fingerprints against the database within a reasonable period of time, and specialized hardware has been developed to provide rapid response.
Inkless techniques are now generally used to produce a “tenprint” card which substitutes for the former rolled print card. Common inkless techniques utilize polarized light to illuminate the fingers, and light sensors to image the light reflected and refracted from the ridges. The resulting image can be more consistent and higher quality than the rolled prints, since inconsistencies in the amount of ink applied and in the pressure used to transfer the print to paper are not a factor.
Automated fingerprint matching techniques have been developed which rapidly classify an unknown print and then search through the portion of the database associated with that class looking for a match. Unknown prints may be from a “tenprint” card, or may be latent prints which have been lifted from a crime scene. A latent print may include a sizable area of one or more fingers, such as on a water glass, or it may include only a portion of one or more fingers, such as on a telephone keypad. Latent prints may be found on top of other latent prints, such as when several people have used the same telephone.
Matching techniques often extract minutiae points from the prints, and then compare the sets of minutiae rather than compare entire prints. Various classifications of minutiae types have been proposed by different companies and authorities. An example is given from the Costello U.S. Pat. No. 4,947,443. Six types of “characteristic features” are presented in this patent, each one relating to a type of minutiae. This fingerprint matching technique references the type, orientation, and location of each characteristic and each and every other characteristic. Using this approach, on the order of 80 to 150 minutia points are identified in each fingerprint. Other fingerprint minutiae extraction and matching patents produce essentially the same number of minutiae, with difference in what features of set of minutiae are considered in attempted matching and in how the matching is performed. In U.S. courts, evidentiary rules have traditionally required that 16 or more minutia points be found to correspond between two prints in order for them to be considered to be from the same person. The determination of likely matching prints is generally assisted or performed entirely by a computer system; however, the final decree of a match is made by a fingerprint expert, who reviews the computer system results.
Matches between different prints taken from the same finger are never perfect, since the fingers are deformable, three-dimensional, connected and jointed structures which leave two-dimensional prints on surfaces they encounter through pressure. The exact angles between the fingers and the surfaces, the amount and direction of pressure, and the effect of movement between the fingers and the
Johns Andrew W.
Laubscher & Laubscher
Mikos, Ltd.
LandOfFree
Method and apparatus for recognizing and classifying... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for recognizing and classifying..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for recognizing and classifying... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2489446