Join
today

Boliven PRO is more than just patent search

  • Build and save lists using the powerful Lists feature
  • Analyze and download your search results
  • Share patent search results with your clients

Patents »

US7564993: Personal authentication method and device

Share

Filing Information

Inventor(s) Kenji Kondo · Kenya Uomori ·
Assignee(s) Panasonic Corporation ·
Attorney/Agent(s) Harness, Dickey & Pierce, P.L.C. ·
Primary Examiner Matthew C Bella ·
Assistant Examiner Hadi Akhavannik ·
Application Number US11429570
Filing date 05/05/2006
Issue date 07/21/2009
Prior Publication Data
Predicted expiration date 09/03/2022
Patent term adjustment 188
U.S. Classifications 382/117  ·
International Classifications G06K900  ·
Kind CodeB2
Related U.S. Application DataCROSS-REFERENCE TO RELATED APPLICATIONS
This application is a continuation of U.S. patent application Ser. No. 10/084,107 filed on Feb. 27, 2002 which claims the benefit of Japanese Patent Application No. 2001-053602 filed Feb. 28, 2001. The disclosure(s) of the above application(s) are incorporated herein by reference.
Foreign Priority JP2001053602 - 02/28/2001 ·
13 Claims, 19 Drawings


Abstract

During registration, an iris image taken is frequency-analyzed using a plurality of frequencies f1 to fn to generate features for the respective frequencies f1 to fn. During authentication, frequencies f2 to fn are selected from the frequencies f1 to fn for use in frequency analysis for authentication. An iris image of a person to be authenticated taken is frequency-analyzed using the selected frequencies f2 to fn to generate features for the respective frequencies f2 to fn. The generated features are compared with the features generated for the same frequencies during the registration to perform personal authentication.

Independent Claims | See all claims (13)

  1. 1. A personal authentication method using iris image, wherein during registration, acquired iris image is frequency-analyzed using a plurality of band-pass filters having different passbands from each other to generate a feature for each passband and register the feature, and wherein the method comprises the steps of: acquiring an iris image of a person to be authenticated using a first apparatus different in resolution performance from a second apparatus used during registration; selecting at least one passband from the passbands of the plurality of band-pass filters; performing frequency analysis for the acquired iris image of the person to be authenticated using at least one band-pass filter having the selected passband to generate a feature for the selected passband; and comparing the generated feature with the feature generated for the same passband during the registration to perform personal authentication, wherein the selection of the passband during the authentication is performed based on a resolution of the acquired iris image during the authentication.
  2. 6. A personal authentication method using iris image, wherein during registration, acquired iris image is frequency-analyzed using a plurality of band-pass filters having different passbands from each other to generate a feature for each passband and register the feature, and wherein the method comprises the steps of: acquiring an iris image of a person to be authenticated using a first apparatus different in resolution performance from a second apparatus used during registration; selecting at least one passband from the passbands of the plurality of band-pass filters; performing frequency analysis for the acquired iris image of the person to be authenticated using at least one band-pass filter having the selected passband to generate a feature for the selected passband; and comparing the generated feature with the feature generated for the same passband during the registration to perform personal authentication, wherein during registration, a plurality of combinations each including two or more features selected from the generated features are generated and authentication precision for each combination is calculated, and wherein the selection of the passband during the authentication is performed based on the calculated authentication precision, wherein the authentication precision is calculated using a distribution of authentication scores between identical persons and a distribution of authentication scores between different persons.
  3. 7. A personal authentication method using iris image, wherein during registration, acquired iris image is frequency-analyzed using a plurality of band-pass filters having different passbands from each other to generate a feature for each passband and register the feature, and wherein the method comprises the steps of: acquiring an iris image of a person to be authenticated using a first apparatus different in resolution performance from a second apparatus used during registration; selecting at least one passband from the passbands of the plurality of band-pass filters; performing frequency analysis for the acquired iris image of the person to be authenticated using at least one band-pass filter having the selected passband to generate a feature for the selected passband; and comparing the generated feature with the feature generated for the same passband during the registration to perform personal authentication, wherein an authentication precision during the authentication is estimated from the selected passband.
  4. 12. A personal authentication device using iris image, wherein during registration, acquired iris image is frequency-analyzed using a plurality of band-pass filters having different passbands from each other to generate a feature for each passband and register the feature, and wherein the device comprises: a first apparatus for acquiring an iris image of a person to be authenticated, the first apparatus being different in resolution performance from a second apparatus used during registration; means for selecting at least one passband from the passbands of the plurality of band-pass filters; means for performing frequency analysis for the acquired iris image by the first apparatus using at least one band-pass filter having the selected passband to generate a feature for the selected passband; and means for comparing the generated feature with the feature generated for the same passband during the registration to perform personal authentication, wherein the selecting means performs the selection of passband based on a resolution of the acquired iris image by the first apparatus.
  5. 13. A personal authentication device using iris image, wherein during registration, acquired iris image is frequency-analyzed using a plurality of band-pass filters having different passbands from each other to generate a feature for each passband and register the feature, and wherein the device comprises: a first apparatus for acquiring an iris image of a person to be authenticated, the first apparatus being different in resolution performance from a second apparatus used during registration; means for selecting at least one passband from the passbands of the plurality of band-pass filters; means for performing frequency analysis for the acquired iris image by the first apparatus using at least one band-pass filter having the selected passband to generate a feature for the selected passband; and means for comparing the generated feature with the feature generated for the same passband during the registration to perform personal authentication, wherein during the registration, a plurality of combinations each including two or more features selected from the generated features are generated and authentication precision for each combination is calculated, and wherein the selecting means performs the selection of passband based on the calculated authentication precision, wherein the authentication precision is calculated using a distribution of authentication scores between identical persons and a distribution of authentication scores between different persons.

References Cited

U.S. Patent Documents

Document NumberAssigneesInventorsIssue/Pub Date
US3993976 The United States of America as represented by the Secretary of the Air Force Ginsburg Nov 1976
US5291560 Iri Scan Incorporated Daugman Mar 1994
US5294560 Seiko Epson Corporation Ono et al. Mar 1994
US6122042 Wunderman et al. Sep 2000
US6317544* Raytheon Company Diehl et al. Nov 2001
US6628809 Lumidigm, Inc. Rowe et al. Sep 2003
US20020181749 Matsumoto et al. Dec 2002

Foreign Patent Documents

Document NumberAssigneesInventorsIssue/Pub Date
DE19929671SIEMENS AGJan 2001
EP0973122Media Technology CorporationJan 2000
JP63136177OMRON TATEISI ELECTRONICS COJun 1988
JP04326481CANON INCNov 1992
JP8504979May 1996
WO199409446Apr 1994
WO200062239IRITECH INC.Oct 2000
* cited by examiner

Other Publications

Wildes, R.P., “Iris recognition: an emerging biometric technology,” Proceedings of the IEEE, vol. 85, No. 9, pp. 1348-1363, Sep. 1997.*
Zhou, Guojun / Hansen, John H. L. / Kaiser, James F. (1998): “A new nonlinear feature for stress classification”, In NORSIG-1998, 89-92.*
Bovik, A.C.; Clark, M.; Geisler, W.S., “Multichannel texture analysis using localized spatial filters,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, No. 1, pp. 55-73, Jan. 1990.*
Koichi Nijima; “Wavelet Image Analysis”; Kagaku Gijutu Publishing Co., Ltd.; pp. 289-306; and partial English translation.
Cooke, M. et al.; “Missing Data Techniques for Robust Speech Recognition”; 1997 IEEE International Conference on Acoustics, Speech and Signal Processing (Cat. No. 97CB36052) IEEE Comput. Soc. Press; Los Alamitos, CA, USA; vol. 2, 1997; pp. 863-866; vol. 2; XP002305684.
Bourlard, H. et al.; “A New ASR Approach Based on Independent Processing and Recombination of partial Frequency Bands”; Proceedings ICSLP 96; Fourth International Conference on Spoken Language Processing (Cat. No. 96TH8206); IEEE New York, NY, USA; vol. 1, 1996; pp. 426-429; vol. 1; XP002305685.
Boles, W. W.; “A Wavelet Transform Based Technique for the Recognition of the Human Iris”; International Symposium on Signal Processing and its Application; Proceedings, XX, XX; vol. 2, Aug. 25, 1996; pp. 601-604; XP010241084.
“Two-Dimensional spectral analysis of cortical receptive field profiles”; (written by John Daugman. Article written in Vision Research, vol. 20, pp. 847-856).
Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters (written by John Daugman. Article written in Journal of the Optical Society of America, vol. 2(7), pp. 1160-1169).
* cited by examiner

Referenced By

Document NumberAssigneeInventorsIssue/Pub Date
US8291492 Google Inc. Michael David McNally et al. Oct 2012
US8645396 --

Patent Family

The current document is not in a family.