Knuckle profile identity verification system

• US 5,862,246 A
• Filed: 10/18/1996
• Issued: 01/19/1999
• Est. Priority Date: 06/20/1994
• Status: Expired due to Fees

• Current Assignee: Personal Information & Entry Access Control Incorporated
• Original Assignee: Personal Information & Entry Access Control Incorporated
• Inventors: Colbert, Charles
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Tadayon, Bijan
• Application Number:
  US08/732,688
• Time in Patent Office: 823 Days
• Field of Search: 382/115, 382/116, 382/117, 382/135, 382/136, 382/100, 382/141, 382/155, 382/181, 382/190, 382/191, 382/192, 382/193, 382/194, 382/195, 382/196, 382/197, 382/198, 382/199 , 382/201, 382/202, 382/203, 382/204, 382/205, 382/209, 382/216, 382/217, 382/218, 382/219, 382/220, 382/221, 382/224, 382/225, 382/226, 382/227, 382/228, 382/254 , 382/266, 382/270, 382/278, 382/282, 382/283, 382/286, 382/305, 382/307, 382/308, 382/312, 382/321, 382/316, 382/323, 382/296, 382/179, 340/825.34, 356/71
• US Class Current: 382/115
• CPC Class Codes: G06V 40/12 Fingerprints or palmprints
• CPC Class Codes: G07C 9/257 electronically G07C9/26 takes precedence

Abstract

A system (method and apparatus) for verifying/identifying a person based on contour of the knuckle surface of at least one hand, e.g. a digitized waveform unique to each individual. At an Enrollment Station a microcomputer is connected to a device for identifying the knuckle surface profile (e.g. a video camera or electromechanical contour sensing device). A candidate user grasps a grip handle, preferably vertically oriented, on the apparatus, positioning a fist before a viewing window and activating the device to scan or assess the fist and generate a contour of the user'"'"'s knuckle surface contour. User'"'"'s data comprises a knuckle contour, an assigned PIN, and optionally, information such as user'"'"'s name, bank ID number, Social Security Number, and access restrictions. User'"'"'s data may be stored as a profile (template) in an ID card, and/or in a master database containing data of all authorized users in a guarded system.

Claims

1. A biometric hand geometry method for preparing a unique identity characteristic of a user based on at least one fist in grip configuration by creating and storing as a template a reference profile of the undulating peaks and valleys of a knuckle surface contour unique to each user, the method comprising the steps of

a) positioning the user'"'"'s knuckles of said one fist with respect to a device which captures the undulating contour of the knuckle and interphalangeal joint surfaces,

b) scanning the surface of the knuckles, the successive scan lines running from the interphalangeal joints to a position on the knuckle,

c) extracting the knuckle surface contour as a smooth curve defined as a sequence of discrete points on the knuckle contour,

d) storing the knuckle surface contour as a template in a storage medium.

2. The method as defined in claim 1, further comprising

f) storing, along with the user'"'"'s template, unique user data the user'"'"'s assigned personal identification number, name, Social Security number, and/or account number.

3. A method according to claim 1, for verifying a user'"'"'s identity by performing the preparation steps of claim 1, and then

g) generating the user'"'"'s knuckle contours as profiles, and

h) comparing the user'"'"'s profile with the user'"'"'s previously stored template,

i) determining the degree of congruence between the user'"'"'s profile and template by calculating a numerical match score,

j) testing for the degree of congruence by comparing the match score with a predetermined threshold score, and

k) determining whether the user is to be accepted or rejected based on the results of the threshold test.

4. The method set forth in claim 3 wherein the templates of all authorized users are stored in a database, and step (g) is performed by riffling through such database, comparing the user'"'"'s profile with each stored template, and selecting the stored template with the highest match score, and step (j) is performed by comparing the selected template with the threshold score and making an accept decision if the threshold criterion is met.

5. A method according to claim 1, for verifying a user'"'"'s identity by performing the preparation steps a) through d) of claim 1 for a number of different users, and then

e1)storing the knuckle surface contours of all users as templates in a database,

g) searching the database to match the user'"'"'s profile with the user'"'"'s previously stored template,

i) determining the degree of congruence between the user'"'"'s profile and a template selected in step g) by calculating a numerical match score,

j) comparing the match score with a predetermined threshold score, and

k) determining whether the user is to be accepted or rejected based on the magnitude of the match score in relation to the threshold score.

6. A method as defined in claim 1, wherein

step (b) is performed by an electronic video camera and associated edge detector, said camera generating scan lines intersecting the images of the successive proximal interphalangeal joints and intersecting the knuckle images, said edge detector extracting the user'"'"'s knuckle and interphalangeal joint contours from the illuminated fist image and thus generating the knuckle profile.

7. A method as defined in claim 6, wherein a combination of a CCD video camera, an incandescent lamp, and an IR filter are used to insure that high contrast is achieved between the knuckle and interphalangeal joint images and surroundings, independent of skin color.

8. A method according to claim 1, wherein step (b) is performed by an electromechanical device having a set of independently movable parallel sensor tines contained in a holder supporting said tines for contact with the fist, moving said set of tines to conform to the knuckle surface whereby the tips of the tines assume the knuckle surface contour, and sensing and recording the curve defined by the so positioned tines to extract the knuckle surface contour.

9. A method as defined in claim 1, where in

step (b) is performed by an electronic video camera and associated edge detector, said camera generating scan lines defining the knuckle surface as imaged from the back of the hand, said edge detector extracting the user'"'"'s knuckle contour from the illuminated fist image.

10. In the method of claim 1, adjusting the threshold score to meet the needs of the facility served, thus relaxing either the Type I error rate or the Type II error rate at the expense of the other.

11. The method set forth in claim 1, wherein the knuckle surface image is scanned from a head on position viewing the knuckles and their profile from the proximal joints of the fist.

12. The method of claim 1, including the additional step of

d1) decreasing the size of a profile and template by recording only the distances between the knuckle surface peaks and valleys and storing such modified contours as a template in an auxiliary database.

13. The method of claim 1, further including

d1) sharpening the peaks and valleys of the knuckle surface profile by convolving the profile using an autocorrelation algorithm, then storing the resulting autocorrelation curve information as the template in an auxiliary database for later matching to an autocorrelation curve similarly generated from a user'"'"'s profile.

14. The method of claim 1, further including

c2) extracting a contour of the proximal interphalangeal joints in addition to the knuckle surface contour,

d2) digitizing the joint contour in addition to the knuckle surface contour, and

wherein step (e) stores both the digitized knuckle surface contour and digitized joint contour as a template.

15. An apparatus for verifying the identity of a candidate user based on a knuckle surface contour of at least one fist, comprising

a face plate having a first viewing window therein of a size to accommodate the area encompassing the knuckles and proximal interphalangeal joints of a closed fist,

a grip handle for the candidate user to grasp so as to bring his closed fist into position for viewing through said window,

means mounting said grip handle for pivotable motion before said window, whereby grasping said grip handle in front of said window will locate the fist for viewing through said window,

scanning means mounted so as to view and record through said window an image of the knuckle surface of a fist, said scanning means generating a scan-type output waveform signal, successive scan lines running from the interphalangeal joints to a position on the knuckles,

signal processing means for receiving said output signal and transforming said output signal into a digitized contour of the knuckles surface, and

means for storing the digitized contour signals in memory as a template.

16. An apparatus as defined in claim 15, wherein said scanning means is an electronic camera.

17. An apparatus as defined in claim 15, wherein said scanning means includes a mechanical array of movable tines conformable to the knuckle surface contour of the fist, and a means for sensing the tine positions whereby the tips of the conformed tines describe the knuckle surface contour, and means for generating the output waveform signal corresponding to the knuckle surface contour from said sensing means.

18. An apparatus as defined in claim 15, wherein said grip handle is pivotally mounted to one side of said window and is movable into a scanning location extending across the view through said window.

19. Apparatus as defined in claim 18, further including a second viewing window located in spaced relation to said first window and said grip handle,

said mounting means for said grip handle providing for turning of said grip handle to positions in front of either of said first and second windows,

whereby users can present one fist before said first window and a second fist before said second window,

said camera viewing and scanning the images through said windows in sequence and said digitizer means transforming the two images into a combined output signal for storing as a single template.

20. An apparatus as defined in claim 15, wherein said grip handle extends vertically within the view through said window,

the scanning means being arranged to follow horizontally extending, vertically spaced scan lines over a fist formed around said grip handle.

21. An apparatus as defined in claim 15, wherein said grip handle is mounted extending across the view through said window, and

bearings supporting said grip handle for rotation about an axis extending lengthwise of said grip handle.

22. An apparatus as defined in claim 15, wherein said grip handle is non-circular in cross-section,

means supporting said grip handle for motion about an axis extending lengthwise of said grip handle, and stops limiting such motion to two positions approximately 90 degrees apart.

23. Apparatus as defined in claim 15, further including

a card reader/encoder for storing a user'"'"'s template waveform signal to be possessed by the user associated therewith.

24. Apparatus as defined in claim 15, further including

means providing a database memory for storing individually as templates the contour signals from the digitizer means, and

means for comparing the stored templates with a digitized profile to determine congruence between the profile generated from a user'"'"'s knuckles and a selected one from among the stored templates.