[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2004023384A2 - Systeme de verification d'identite mobile au volume et procede d'utilisation d'une analyse biometrique multiniveau - Google Patents

Systeme de verification d'identite mobile au volume et procede d'utilisation d'une analyse biometrique multiniveau Download PDF

Info

Publication number
WO2004023384A2
WO2004023384A2 PCT/US2003/027675 US0327675W WO2004023384A2 WO 2004023384 A2 WO2004023384 A2 WO 2004023384A2 US 0327675 W US0327675 W US 0327675W WO 2004023384 A2 WO2004023384 A2 WO 2004023384A2
Authority
WO
WIPO (PCT)
Prior art keywords
biometric data
primary
biometric
match
data
Prior art date
Application number
PCT/US2003/027675
Other languages
English (en)
Other versions
WO2004023384A3 (fr
Inventor
Robert C. Houvener
Original Assignee
Houvener Robert C
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US10/236,513 external-priority patent/US6950536B2/en
Priority claimed from US10/236,785 external-priority patent/US6757408B2/en
Application filed by Houvener Robert C filed Critical Houvener Robert C
Priority to AU2003268434A priority Critical patent/AU2003268434A1/en
Publication of WO2004023384A2 publication Critical patent/WO2004023384A2/fr
Publication of WO2004023384A3 publication Critical patent/WO2004023384A3/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/20—Individual registration on entry or exit involving the use of a pass
    • G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
    • G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
    • G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically

Definitions

  • the present invention relates to the field of security identification systems, and relates in particular to systems and methods for verifying the identity of persons in high volume screening applications.
  • biometric analysis systems require some human interpretation of the data to be certain of the identity in a high percentage of cases, and this interpretation may vary.
  • the process of obtaining reliable and consistent biometric information from a large number of persons, to be identified remains difficult and expensive due to biometric data capturing concerns, particularly with non-contact biometric data capturing.
  • Certain conventional non-contact biometric data capturing systems use video cameras to capture the faces of people in a subject area, or employ non-contact sensors to capture characteristics of parts of a person's body.
  • Such systems remain inconsistent and insufficiently reliable, at least in part due to variations in how the subject is presented to the video camera or sensor. For facial recognition, poor or changing lighting and poor pose angles present significant difficulties.
  • Difficulties are also presented by having a moving subject with a fixed camera view area, particularly if the subject's face occupies a small portion of a large and highly varying view area.
  • Other non-contact biometric techniques include iris scanning, which requires that each subject walk up to a capture device, align themselves correctly and have their iris scanned and verified.
  • Contact based biometric systems such as finger print readers, are generally considered to be less safe from a health standpoint due to having a large number of persons touch the same device over a long period of time.
  • Contact based biometric verifications also take longer to complete than non-contact based, by the very nature of the interaction between the sensor and the person being verified. For example, U.S. Patent No.
  • U.S. Patent No. 6,018,739 discloses a distributed biometric personal identification system that uses fingerprint and photographic data to identify individuals. The system is disclosed to capture biometric data at workstations and to send it to a centralized server via a wide area telecommunications network for automated processing.
  • U.S. Patent No. 6,317,544 discloses a distributed mobile biometric identification system with a centralized server and mobile workstations that uses fingerprint and photographic data to identify individuals. The system is disclosed to capture biometric data at workstations and to send it to a centralized server via a wireless network for automated processing.
  • the invention provides a security identification system and method for providing information regarding subjects to be identified, verified, or both.
  • the system includes a primary biometric data input unit for receiving primary biometric data regarding a subject, a primary biometric analysis unit, a secondary biometric data input unit, a secondary biometric analysis unit, and a security clearance output unit.
  • the primary biometric analysis unit is for analyzing the primary biometric data and comparing it against known biometric data in a database.
  • the primary biometric analysis unit is also for providing primary match data that is indicative of whether a match exists with respect to the primary biometric data and whether the primary match data meets or exceeds a preselected primary biometric data correlation threshold.
  • the secondary biometric data input unit is for receiving secondary biometric data regarding the subject when the primary match data is below the preselected minimum primary biometric data threshold.
  • the secondary biometric analysis unit is for analyzing the secondary biometric data and comparing it against known biometric data in the database.
  • the secondary biometric analysis unit is also for providing secondary match data that is indicative of whether a match exists with respect to the secondary biometric data, whether the secondary match data is above the preselected secondary biometric data correlation threshold and, in a more limited aspect, whether the primary biometric match data collected can be used to increase the performance of the primary biometric match process.
  • the security clearance output unit is coupled to the primary biometric data analysis unit and to the secondary biometric data analysis unit for providing an indication of whether the subject is cleared.
  • a method for one or both of: (a) verifying the identity of a person and (b) determining whether the person is a high-risk individual is provided.
  • Primary biometric data regarding a subject are received, analyzed, and compared against known biometric data in a database.
  • Primary match data is provided which is indicative of whether a match exists with respect to said primary biometric data and whether the primary match data meets or exceeds a preselected primary biometric data correlation threshold.
  • Secondary biometric data regarding the subject is received when said primary match data is below said preselected primary biometric data threshold.
  • the secondary biometric data is analyzed and compared against known biometric data in the database.
  • Secondary match data is provided which is indicative of whether a match exists with respect to said secondary biometric data and whether the secondary match data is above a preselected secondary biometric data correlation threshold. An indication is provided as to whether the subject is cleared responsive to said primary biometric data and said secondary biometric data.
  • Figure 1 shows an illustrative view of a screener using a system in accordance with an embodiment of the invention to screen a subject
  • Figure 2 shows an illustrative enlarged view of the screener of Figure 1 wearing a data collection unit in accordance with the system shown in Figure 1 ;
  • Figure 3 shows an illustrative view of a screen display as seen by a screener in accordance with an embodiment of the invention
  • Figure 4 shows an illustrative flowchart of the operation of a system in accordance with an embodiment of the invention
  • Figure 5 shows an illustrative diagrammatic view of a system in accordance with an embodiment of the invention
  • Figure 6 shows an illustrative view of a packet of information that is communicated from a screener to a central facility in accordance with an embodiment of the invention
  • Figure 7 shows an illustrative view of a screen display as seen by an expert analyst in accordance with an embodiment of the invention
  • Figures 8 A - 8C show illustrative diagrammatic top, side and end views respectively of a contact biometric system in accordance with an embodiment of the invention.
  • FIGS. 9A and 9B show illustrative flowcharts of the operation of a system in accordance with an embodiment of the invention.
  • the present invention provides for systems and methods for optimally gathering biometric data and documentation data regarding individuals whose identity is to be verified in high volume screening applications.
  • the method involves the use of face to face human interaction to set up and execute scripted scenarios for operators (screeners) to follow, ensures that optimal quality data is captured in a highly consistent manner.
  • the collection method is driven by the voice of the screener as part of the normal conversation with the person being screened.
  • the screener is queued by an interactive teleprompter on a miniature screen display.
  • the system invokes a live identification expert with access to auxiliary data to assist the field-based screener via live text, audio and video.
  • the method provides significant improvement in biometric performance and improves screening efficiency.
  • the system also provides interactive training of screening personnel in an embodiment based on their on-going performance.
  • a screener 8 may wear a specialized data collection and display device 10 that includes an earphone 12, a camera 14, a micro display 16, and a microphone 18.
  • the camera 14 is a miniature high resolution color or grayscale camera.
  • the micro display 16 is a miniature high resolution color r grayscale display that is viewable only by the screener, such as those sold by MicroOpical Corporation of Westwood, Massachusetts. The display may project an image into space in front of the screener's face (again viewable only by the screener).
  • the device 10 is connected via a cable 20 to a small computer 22, which in turn communicates via an antenna 24 and a high speed wireless connection to a central analysis facility.
  • the computer 22 may be worn by a screener on a waist belt out of view of the person being screened 26.
  • the devices 10 may be made even smaller, with each communication device fitting on a single pair of eyeglasses so as to fully minimize the impact on the subject 26 and permit natural interaction between the screener 8 and subject 26.
  • Each device 10 is personalized at the time of use to a particular authorized screener. All communications with the central analysis facility are encrypted.
  • the device application software includes two way voice, text (from the central facility) and two way video and still image capture / display, as well as local biometric data, compression, control and communication capabilities.
  • the device 10 is completely driven by the voice of the screener for all real-time functions via keyword spotting that is tied to the main screening script as discussed in more detail below.
  • the miniature display 16 may provide a significant amount of information in the form of a screen display 30 as shown in Figure 3, including a photograph 32 of the subject 26, a photograph of the subject's identification card (ID) 34, a photograph of the subject's airline ticket 36, a streaming video image 38, and an image of an eye 39 for, e.g., iris scanning or retinal imaging.
  • the camera 14 may have sufficient resolution to locate the one or both eyes in the image of the subject's face, and increase the scale of the eye to fill the viewing image to create the image 39 for processing.
  • the display may also provide a results field 40 and a system status field 42, and the may further include text accompanying any of the various photographs or images as shown, as well as text generated from remote locations.
  • the analysis facility includes strong authentication and firewalls for incoming and outgoing communications. It contains a very high speed local area network (LAN) / storage area network (SAN) system, connecting database and analysis servers to devices 10 and to human analysts and quality control personnel.
  • the analysis servers include generalized correlation engines, biometric correlation engines, as well as other automated support for screener based devices, in addition to local analysts supporting screeners in the field. Also at these facilities are automated on-line training / screening performance metrics servers.
  • the secure facilities may be run under United States Department of Defense security standards and may be staffed with fully security cleared operators, particularly at the expert analysts workstations.
  • the analysis facility has local copies of known threat data, as well as secure connectivity to appropriate governmental agencies.
  • the system combines real time access to experts with the least traveler inconvenience or impact.
  • the system may be used, for example at airports during check-in, gate-entry-screening, boarding, or baggage claim.
  • the system may be used in a wide variety of environments where the accurate and rapid identification of individuals is required such as any secure entry or access facility.
  • the system begins (step 400) when a subject to be screened walks up to a screener at, for example, an airline ticket counter at an airport or an airline gate screening security station.
  • the screener may be required to log in and verify their own identity via the biometric analysis system. As shown in Figure 4, during operation the screener follows a script and looks directly at the subject and asks to see the subject's ticket. When the system hears the screener say the word "ticket” (step 402) it takes a picture of whatever the screener is looking at at that moment. The image 406 of the subject that is taken by the camera will be a close up picture in full view of the subject's face and/or eye from a front-on direction. The screener should be trained to not say the word "ticket” until the subject is looking at the screener.
  • the system may permit the picture to be retaken if the subject fails to look toward the screener by again stating the word "ticket” or by recognizing some other pre-arranged command, such as "look at me, please” if necessary.
  • the image 406 is recorded by the computer 22.
  • the system may also automatically request that the screener re-take a picture, for example, if the biometric processing results in an ambiguity.
  • the screener then asks for some photo-identification, and while looking at the photo-identification the screener asks whether the address on the photo-id is the current address.
  • the system hears the word "address” (step 408) and takes a photograph (step 410) of the photo-id that the screener is looking at.
  • the photograph of the identification card 412 is also recorded by the computer 22.
  • the screener looks at the ticket and reads the flight information out loud (e.g., "I see that you are on Flight 100 to Washington D.C.”).
  • the word "flight” step 414) it takes another picture (step 416), this time of the ticket 418, which is recorded by the computer 22.
  • Each of the pictures 406, 412 and 418 are recorded in seconds, without interrupting the normal flow of passenger interaction.
  • the pictures taken by the camera 14 are shown on the display as illustrated in Figure 3 at 32, 34 and 36 respectively, and are processed for transmission to the central facility.
  • Biometric analysis may be performed by each computer 22 or preferably sent to the central facility for biometric analysis as well.
  • each screener 8 has a data collection device 10 that is attached to a computer 22 that communicates via wireless communication to a central facility (optionally via a local wireless transmitter/receiver station 50).
  • the central facility includes a firewall 52, a central transmitter/receiver station/server 54, and a number of high speed LAN / SAN data storage and analysis processors.
  • the central facility may also include an interactive and automated on-line screener training/performance metric system 58 that monitors the performance of each screener.
  • the analysis processors 56 are also coupled to a bank of analysts work stations 60 for providing real time expert analysis support for the screeners via two way communication.
  • the analysts stationed at the work stations 60 provide backup analysis in the event that the biometrics analysis is not fully satisfactory, and provide question and answer support/training for the screeners.
  • the system may also include access to information from a Federal information link 62 such as to the Federal Bureau of Investigations.
  • the real-time analysis system at the central facility runs the picture 406 of the subject's face, or a mathematical representation of the face that has been extracted from the picture at either the screener or central site, against the known database of high-risk individuals. If there is no match (step 420) then a message is sent to the screener's device, and the screener receives an indication in field 40 of Figure 3 that the subject is cleared and free to go.
  • Typical biometric analysis systems employ a variety of test characteristics that together provide a numerical number, e.g., a match of x out of y characteristics.
  • a match is typically defined as a range (m - y) such that numbers in the range (m ⁇ x ⁇ y) indicate a match.
  • a match is strong if the number x is close to y, and weak if the number x is close to the threshold m.
  • the system determines whether or not the match is strong or weak (step 422). If the match is strong (step 422), then the system prompts the screener to not let the subject pass and to contact security immediately (step 424) for further questioning or retention. In certain embodiments, the system may itself contact security immediately to assist the screener. If there is a match at step 420, but the match is weak (step 422), then the system automatically involves one or more experts (step 426) that are stationed at work stations 60 to assist in the analysis. The experts review the images and data in real time, and contact with screener with instructions to either clear the individual or to contact security.
  • the system then ends (step 428) and begins anew with the next subject to be screened. Even if the expert analysts are involved, the screening process should require only seconds to fully execute.
  • the system may also automatically involve one or more experts if the individual with whom a match appears to exist is a known high risk individual regardless of whether the match is strong or weak.
  • an index may be collected from the subject as via a barcode. This allows the system to check the current person against their previously enrolled identity.
  • the system is not required to utilize any single biometric characteristic such as facial recognition, and may be modified to capture and review other biometric information such as voice prints and iris scanning.
  • biometric information such as facial recognition
  • the benefits of both biometric analyses and the use of expert analysts in real time significantly improves results for minimal costs.
  • the packet of information that is sent to the central facility for any particular subject includes the biometric information as well as copies of the pictures taken of the subject's face 406, photo-id 412 and photograph of the ticket 418.
  • each expert analyst station may include the above as well as any pertinent classified information 70 that is available only to the expert analysts.
  • the present invention provides high quality data capture and screening by leveraging the interaction between screening personnel and people being screened.
  • Biometric data collection devices that are worn by the screener rely on the proximity and voice interaction between the screener and subject to obtain very reliable biometric data.
  • the collection devices also communicate with a central control system for full analysis and reporting of the biometric data.
  • the visual prompting of the screener in synchronization with the collection system, yields a systematic, uniform, natural, efficient and optimal data collection process. This increases the likelihood of detecting a known high-risk individual, and minimizes the number of false positive identifications.
  • the system also reduces the required level of skill of the screeners that are in contact with the persons to be identified. Duplicate screeners, in fact, may even be employed at different stations in an airport, such as check-in, gate-entry, boarding and baggage claim. Further, the system may provide a safeguard that ensures that each passenger boarded a plane, that their luggage is on the plane, and that the luggage is later claimed by the correct person.
  • biometric data acquisition techniques other than facial recognition may also be employed.
  • the easiest system for the subject to interact with is a non-contact biometric system such as facial recognition, where the subject needs only to be within a field of view of the facial recognition camera to have his or her face acquired and analyzed.
  • Another non-contact method is voice verification, where the subject only needs to be within the range of the microphone being used to capture the voice.
  • a drawback, however, of these non-contact biometric data acquisition techniques is that the quality and consistency of the capture may be highly variable. This variability in the captured data, in turn, causes the matching algorithms to have poor performance.
  • Another non-contact biometric technique is iris recognition, which has much less variability in the matching process, but capturing a high quality image is quite difficult due to the small size of the iris.
  • contact based biometrics such as finger imaging
  • contact based biometrics have much less of a problem capturing the appropriate part of the subject even at the proper resolution, but suffer from problems associated with having a large number of people touch the same sensor over an extended period of time, in addition to frying to quickly acquire finger image(s) that are properly aligned.
  • an identity verification system may employ a first biometric acquisition and analysis, followed by a secondary biometric acquisition and analysis in certain cases as discussed in more detail below.
  • the secondary biometric information may also be input to the system, and this feedback may permit the primary biometric analysis system to initially learn (enroll) or better learn a subject's identity over time and therefore become more efficient.
  • a system of the invention may employ a contact biometric data acquisition system such as the fingerprint capture sensor device shown in Figures 8A - 8C fingerprint capture device 80 includes a pair of fingerprint sensors 82 and 84 mounted on oppositely facing surfaces such that the device may be squeezed by a subject when a subject's thumb and forefinger are placed on the sensors 82 and 84.
  • the device also includes a light source 86 and sensor contacts 86 that indicate that the subject is squeezing the device and thereby firmly pressing the thumb and forefinger against the respective sensors.
  • the sensors are also coupled to a sensor output wire 90 for coupling to a communication system such as that shown in Figures 1 - 7.
  • the sensors record the image that is acquired from the finger, and the light 86 alerts the subject to the status of the capture process.
  • the sensors may employ capacitive, optical or other finger image capture technologies.
  • the sensors 82 and 84 are relatively inexpensive and easy to replace. This is preferred not only for hygienic reasons, but also to thwart efforts by subjects to damage or alter the sensors.
  • the device 80 allows for the capture of more than one finger at a time, automatically aligns the fingers with the sensors 82, 84, and further ensures that the correct amount of pressure is applied by the subject.
  • the device permits the sensors to be squeezed (e.g., rotated about a pin 92) against a spring to a stop position, e.g., when the sensor contacts 86 abut one another.
  • the subject is then notified via audio or light that the capture is complete and releases the device.
  • This method permits the collection of correctly positioned finger images and hence leads to better recognition results.
  • Other contact biometric data acquisition sensors may involve sending light through a person's skin to uniquely identify individuals, such as by using the LIGHTPRLNT sensor product sold by Lumidigm, Inc. of Albuquerque, NM.
  • a method is accordance with a further embodiment of the invention involves the process of primary biometric data acquisition (steps 900 - 924) similar to the data acquisition process described above with reference to steps 400 - 424 of Figure 4. If the analysis of the biometric data provides a strong match (step 922) then the program directs that the operator is to notify local security (step 924). If, however, the match is not strong (step 922) then the program directs the operator to acquire secondary biometric data as shown in step 930 in Figure 9B.
  • the secondary biometric data acquisition technique may involve non- contact biometric data such as by using the finger print capture sensor device 80 shown in Figure 8. In other embodiments, the secondary biometric data acquisition technique may involve contact biometric data acquisition.
  • the program determines whether the match is a strong match (step 934) similar to the procedure discussed above with respect to the primary biometric data analysis. If the match is not strong, the system may then proceed to invoking the expert analysts at the central facility (step 936) as discussed above with respect to step 426 in Figure 4. If the secondary biometric analysis provides a strong match, then the system adds the primary set of biometric data to the databases in the central facility (step 938) for future use in watchlist or verification purposes. By adding another set of primary biometric data to the central facility, the system provides helpful feedback with respect to the primary biometric data.
  • This feedback permits the system to initially learn or to better recognize individuals already in the system by using the primary biometric data, and therefore permits the system to learn as it operates and such learning is independent of the remote computers on each screener or operator or other capture methods.
  • the system may permit the primary biometric system to learn via neural network feedback. Such feedback may be performed automatically and may further be conducted based on information from the expert analysts - either with or without using the secondary biometric system. Over time, this may considerably improve the performance of the primary biometric system thereby significantly increasing throughput in the overall verification system.
  • the present invention not only optimizes the quality of the captured data presented to biometric algorithms, but it also allows the operator to select the easiest to use biometric that may be used in a given situation, including the use of fixed or mobile sensors for primary and secondary biometrics. This may allow non-contact biometric acquisition technique to be used in a first pass and a contact or alternate non-contact biometric acquisition technique to be used in a second pass if the first pass biometric does not achieve the desired results due to problems with the collection of the data for the first pass biometric.
  • the first pass biometric works 90% of the time and takes 5 seconds
  • a second pass biometric takes 15 seconds and works for 95% of the 10% that did not work in the first pass
  • overall the two passes of biometrics will work for 99.5% of the subjects being verified.
  • the average time to complete the biometric data acquisition will be significantly less time than the time required if the secondary biometric acquisition technique was employed all of the time (as the first pass technique).
  • the subject can be rapidly and securely enrolled for the first time in the primary biometric system, dramatically reducing the cost and hassle of initial enrollment. This reduced time produces much shorter queues of subjects being verified, provides better overall customer experience, and much lower costs for screening activities.
  • the system permits interactive training of screening personnel based on their on-going performance.
  • Quality assurance may also be improved by using an identity verification system of an embodiment of the invention.
  • quality assurance personnel may record the complete interaction between a subject and a screener via the wearable computer and upload the interaction to the central facility. The quality assurance personnel may then play back the interaction and evaluate performance.
  • the system may provide the capability to immediately react to issues noted by a quality assurance personnel, by allowing the quality assurance personnel to assign an interactive multi-media training module to the field personnel (or screener). The field personnel are then prompted to participate in a training session at the next convenient time, such as when they log into their wearable computer at the start of their next shift.
  • This centralized quality assurance and training capability permits large organizations to assure that their field personnel are providing high quality customer service in a method that is considerably more efficient and effective than sending quality assurance personnel to the field for auditing and training purposes.
  • the quality assurance personnel may collect the field data on a periodic or directed basis and the customer or subject interactions may be recorded via the wearable computer.
  • Such a quality assurance routine may be conducted over an extended period of time for the convenience of the quality assurance personnel and the screeners. For example, the interaction may be automatically uploaded to the central facility at scheduled times, then viewed by a quality assurance person at any later time.
  • the quality assurance person may select and transmit to the screener a training module (e.g., to improve the quality of pictures being taken by the screener). The screener may then be prompted to run the training module when he or she next signs onto the system. Any initial training may also be similarly conducted without requiring the screener to travel to the central facility.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

L'invention concerne un système d'identification sécurisé permettant d'apporter une information concernant des sujets à identifier, vérifier, ou les deux, comprenant une unité d'entrée de données biométriques primaires permettant de recevoir des données biométriques primaires concernant un sujet et une unité d'analyse biométrique primaire permettant d'analyser les données biométriques primaires et de les comparer par rapport aux données biométriques connues dans la bas de données. L'unité d'analyse biométrique primaire permet également d'apporter des données de coïncidence primaires indiquant si une correspondance existe par rapport aux données biométriques primaires et si lesdites données dépassent un seuil de corrélation présélectionné. L'unité d'entrée de données biométriques secondaires sert à recevoir des données biométriques secondaires concernant le sujet lorsque les données de correspondance primaires sont en deçà du seuil présélectionné de données biométriques primaires. L'unité d'analyse biométrique secondaire sert à analyser les données biométriques secondaires et à les comparer avec les données biométriques connues contenues dans la base de données. L'unité d'analyse biométrique secondaire sert également à apporter des données de correspondance secondaires indiquant si une correspondance existe par rapport aux données biométriques secondaires et si les données de correspondance secondaires dépassent un seuil de corrélation maximal de données biométriques secondaires. Selon une variante plus limitée, on prévoit un mécanisme de rétroaction automatique venant entre les données biométriques secondaires et primaires afin d'améliorer en continu les performances des données biométriques primaires, y compris l'entrée initiale dans le système biométrique primaire. L'unité de sortie d'effacement sécurisé est couplée à l'unité d'analyse de données biométriques primaires et à l'unité d'analyse de données biométriques secondaires afin de fournir une indication concernant l'effacement ou non du sujet.
PCT/US2003/027675 2002-09-06 2003-09-02 Systeme de verification d'identite mobile au volume et procede d'utilisation d'une analyse biometrique multiniveau WO2004023384A2 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2003268434A AU2003268434A1 (en) 2002-09-06 2003-09-02 High volume mobile identity verification system and method using tiered biometric analysis

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US10/236,513 US6950536B2 (en) 2002-01-25 2002-09-06 High volume mobile identity verification system and method using tiered biometric analysis
US10/236,513 2002-09-06
US10/236,785 US6757408B2 (en) 2002-01-25 2002-09-06 Quality assurance and training system for high volume mobile identity verification system and method
US10/236,785 2002-09-06

Publications (2)

Publication Number Publication Date
WO2004023384A2 true WO2004023384A2 (fr) 2004-03-18
WO2004023384A3 WO2004023384A3 (fr) 2004-06-03

Family

ID=31980978

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2003/027675 WO2004023384A2 (fr) 2002-09-06 2003-09-02 Systeme de verification d'identite mobile au volume et procede d'utilisation d'une analyse biometrique multiniveau

Country Status (2)

Country Link
AU (1) AU2003268434A1 (fr)
WO (1) WO2004023384A2 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2446837A (en) * 2006-10-18 2008-08-27 Unilink Software Handheld fingerprint analysis unit
US20080211627A1 (en) * 2007-03-02 2008-09-04 Fujitsu Limited Biometric authentication method and biometric authentication apparatus
WO2015011219A1 (fr) * 2013-07-26 2015-01-29 Morpho Procédé et système d'identification biométrique à traitement accéléré
CN113992823A (zh) * 2021-09-27 2022-01-28 国网浙江省电力有限公司金华供电公司 一种基于多信息源的一二次设备故障智能诊断方法
CN115774102A (zh) * 2021-09-08 2023-03-10 复旦大学 确定新冠疫苗介导的保护免疫力应答状态的方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5513272A (en) * 1994-12-05 1996-04-30 Wizards, Llc System for verifying use of a credit/identification card including recording of physical attributes of unauthorized users
US5705993A (en) * 1995-07-14 1998-01-06 Alesu; Paul Authentication system and method
US5761329A (en) * 1995-12-15 1998-06-02 Chen; Tsuhan Method and apparatus employing audio and video data from an individual for authentication purposes
US6317544B1 (en) * 1997-09-25 2001-11-13 Raytheon Company Distributed mobile biometric identification system with a centralized server and mobile workstations

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5513272A (en) * 1994-12-05 1996-04-30 Wizards, Llc System for verifying use of a credit/identification card including recording of physical attributes of unauthorized users
US5705993A (en) * 1995-07-14 1998-01-06 Alesu; Paul Authentication system and method
US5761329A (en) * 1995-12-15 1998-06-02 Chen; Tsuhan Method and apparatus employing audio and video data from an individual for authentication purposes
US6317544B1 (en) * 1997-09-25 2001-11-13 Raytheon Company Distributed mobile biometric identification system with a centralized server and mobile workstations

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HONG ET AL.: 'Integrating faces and fingerprints for personal identification' IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE vol. 20, no. 12, December 1998, pages 1295 - 1307, XP002972708 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2446837A (en) * 2006-10-18 2008-08-27 Unilink Software Handheld fingerprint analysis unit
US20080211627A1 (en) * 2007-03-02 2008-09-04 Fujitsu Limited Biometric authentication method and biometric authentication apparatus
EP2339498A1 (fr) * 2007-03-02 2011-06-29 Fujitsu Limited Procédé d'authentification biométrique et appareil d'authentification biométrique
US8797140B2 (en) * 2007-03-02 2014-08-05 Fujitsu Limited Biometric authentication method and biometric authentication apparatus
WO2015011219A1 (fr) * 2013-07-26 2015-01-29 Morpho Procédé et système d'identification biométrique à traitement accéléré
FR3009106A1 (fr) * 2013-07-26 2015-01-30 Morpho Procede et systeme d'identification biometrique a traitement accelere
US10146920B2 (en) 2013-07-26 2018-12-04 Morpho Method and system for biometric identification with accelerated treatment
CN115774102A (zh) * 2021-09-08 2023-03-10 复旦大学 确定新冠疫苗介导的保护免疫力应答状态的方法
CN113992823A (zh) * 2021-09-27 2022-01-28 国网浙江省电力有限公司金华供电公司 一种基于多信息源的一二次设备故障智能诊断方法
CN113992823B (zh) * 2021-09-27 2023-12-08 国网浙江省电力有限公司金华供电公司 一种基于多信息源的一二次设备故障智能诊断方法

Also Published As

Publication number Publication date
WO2004023384A3 (fr) 2004-06-03
AU2003268434A1 (en) 2004-03-29

Similar Documents

Publication Publication Date Title
US6950536B2 (en) High volume mobile identity verification system and method using tiered biometric analysis
US6757408B2 (en) Quality assurance and training system for high volume mobile identity verification system and method
JP3254645B2 (ja) バイオメトリック画像の合格度を確保するシステムおよび方法
Labati et al. Biometric recognition in automated border control: a survey
US10176377B2 (en) Iris liveness detection for mobile devices
JP4387643B2 (ja) 個人認識機能付き処理装置
CN104834849B (zh) 基于声纹识别和人脸识别的双因素身份认证方法及系统
US8311294B2 (en) Image classification and information retrieval over wireless digital networks and the internet
US20060280340A1 (en) Conjunctival scans for personal identification
WO2004019154A2 (fr) Systeme de verification d'identite
US8036431B1 (en) Portable apparatus for identification verification
US20150154462A1 (en) Biometric notification system
KR20100058809A (ko) 적외선 영상을 이용한 위조 얼굴 검출 방법 및 그 장치
US20070071290A1 (en) Image Classification And Information Retrieval Over Wireless Digital Networks And The Internet
US20140016836A1 (en) Face recognition system and method
CA2812045A1 (fr) Appareil, systeme et procede d'inscription, d'admission et de test d'un candidat
US20150227791A1 (en) Biometric authentication using the eye
US20050219360A1 (en) Method and apparatus for biometric access control with fully integrated digital video storage and retrieval
CN117012352B (zh) 一种基于人脸识别的医患无感同行方法
KR102215522B1 (ko) 사용자 인증 시스템 및 방법
KR100998617B1 (ko) 중앙 통제 방식의 ｃｂｔ 시스템 및 그 방법
US20040052403A1 (en) High volume mobile identity verification system and method
CN110765851A (zh) 一种注册方法及装置、设备
WO2004023384A2 (fr) Systeme de verification d'identite mobile au volume et procede d'utilisation d'une analyse biometrique multiniveau
CN112383571B (zh) 基于人脸识别大数据的登录管理系统

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
122 Ep: pct application non-entry in european phase
NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP