Method and apparatus for confirming the identity of an individual presenting an identification card

• US 5,509,083 A
• Filed: 06/15/1994
• Issued: 04/16/1996
• Est. Priority Date: 06/15/1994
• Status: Expired due to Term

• Current Assignee: Grady C. Shumate Sr, Nooral S. Abtahi
• Original Assignee: Nooral S. Abtahi
• Inventors: Abtahi, Nooral S., Shumate, Grady C. Sr., Yang, Hedong, Heyward, Waddie
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Johns, Andrew W.
• Application Number:
  US08/259,879
• Time in Patent Office: 671 Days
• Field of Search: 382/2, 382/4, 382/5, 382/30, 382/124, 382/125, 382/126, 382/127, 382/209, 340/825.3, 340/825.31, 340/825.33, 340/825.34, 356/71, 235/380, 235/382, 235/382.5, 283/74, 283/75, 283/78, 283/82
• US Class Current: 382/124
• CPC Class Codes: G06K 7/10831 Arrangement of optical elements, e.g. lenses, mirrors, prisms optical elements per se G02B
• CPC Class Codes: G06Q 20/341 Active cards, i.e. cards including their own processing means, e.g. including an IC or chip
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06V 40/13 Sensors therefor
• CPC Class Codes: G07C 9/257 electronically G07C9/26 takes precedence
• CPC Class Codes: G07F 7/1008 Active credit-cards provided with means to personalise their use, e.g. with PIN-introduction/comparison system

Abstract

A system for confirming the identity of an individual presenting an identification card includes a card reader, an associated central processing unit, a preselected feature template library associated with the central processing unit, a scanner for scanning preselected portions of an epidermis, such as a fingerprint, RAM storage means operatively associated with the central processing unit and the scanner, a communication interface such as a modem communicating with a remote site, and an output display indicating the identifier correlation. This invention provides an improved method of verifying that a card holder is the card owner by matching the image of the card holder'"'"'s fingerprint to the unique code which has been assigned to the card owner and encoded on the card'"'"'s magnetic strip, which requires only a relatively small amount of data to perform identification, making it possible to use low cost, low density encoding methods including bar code and magnetic strip. Fingerprint verification apparatus is also disclosed.

Claims

1. A method for adding individuals to a system which confirms the identity of an individual presenting an identification card comprising:

providing a central processing unit;

providing a preselected feature template library in communication with said central processing unit;

scanning preselected portions of an epidermis to provide a scanned image, and sending said scanned image to said central processing unit;

wherein said scanning step comprises;

providing a finger cradle;

operatively associating an imaging system with said finger cradle;

operatively associating a charged couple device camera with said imaging system;

operatively associating a frame grabber with said charged couple device camera;

operatively associating a stepper motor with said charged couple device camera;

operatively associating a control interface with said stepper motor and said central processing unit; and

operatively associating a position detector with said control interface;

dividing said scanned image into an array of image blocks;

correlating each image block with each feature stored in said preselected feature template library;

identifying and selecting features of said epidermis by said central processing unit;

determining a reference code corresponding to features contained in said feature template library for each feature selected by said central processing unit;

encoding said reference code on an identification card; and

recording said reference code at a centralized data bank;

said central processing unit generating a signal to said stepper motor to adjust said charged couple device camera to locate a distinctive reference position on preselected portions of an epidermis, and said central processing unit generating a distinctive position code corresponding to a distance between said distinctive reference position and a center portion of said preselected portions of said epidermis;

said charged couple device camera generating an analog video image of said preselected portions of an epidermis;

said charged couple device camera generating several video images of said preselected portions of an epidermis;

averaging each of said video images with other of said video images to produce a single video image, and temporarily saving said single video image.

2. A method, according to claim 1, further comprising:

filtering said video images employing a non-linear filter thereby creating a filtered image and converting said filtered image into a binary image.

3. A method, according to claim 2, wherein:

said central processing unit is adapted to invert said binary image as an inverted binary image and to generate an inverse flag code, said inverted binary image and said inverse flag code being temporarily saved in said central processing unit.

4. A method, according to claim 3, wherein:

said feature template library contains a plurality of predetermined binarized features, each of said plurality of predetermined binarized features having a feature code.

5. A method, according to claim 4, wherein:

said binary image is divided up into a plurality of overlapping small sections, each of said small sections being correlated with each of said plurality of predetermined binarized features contained in said template library to determine a degree of similarity between features contained in said small sections and each of said plurality of predetermined binarized features in said template library, each of said plurality of predetermined binarized features being assigned a correlation value corresponding to its said degree of similarity with said features contained in said small sections and assigned a location value indicating a position of said feature within each of said small sections.

6. A method, according to claim 5, wherein:

said inverted binary image is divided into a plurality of overlapping small sections, each of said small sections being correlated with each of said plurality of predetermined binarized features in said template library to determine a degree of similarity between features contained in each of said small sections and each of said plurality of predetermined binarized features in said template library, each of said plurality of predetermined binarized features being assigned a correlation value corresponding to its said degree of similarity with said features contained in said small sections and assigned a location value indicating the position of said feature within each of said small sections, and an inverse flag code indicating an inverted binary image as a source of each of said small sections.

7. A method, according to claim 6, wherein:

said central processing unit compares each of said plurality of predetermined binarized features'"'"' correlation value with a threshold value, each of said plurality of predetermined binarized feature having a correlation value above said threshold value being stored in the central processing unit.

8. A method, according to claim 7, wherein:

said central processing unit is adapted to select a plurality of predetermined binarized features based on a predetermined criteria and thereby form a candidate epidermis record.

9. A method, according to claim 8, wherein:

said central processing unit is adapted to select a plurality of predetermined binarized features based on the highest threshold value and thereby form a candidate epidermis record.

10. A method, according to claim 8, wherein:

said central processing unit is adapted to randomly select a plurality of predetermined binarized features and thereby form a candidate epidermis record.

11. A method, according to claim 8, wherein:

said central processing unit is adapted to compare said candidate epidermis record with other epidermis records.

12. A method, according to claim 11, wherein:

said central processing unit is adapted to select a distinctive candidate epidermis record.

13. A method, according to claim 12, wherein:

said distinctive candidate epidermis record contains said feature code of each of said plurality of predetermined binarized features, a location code corresponding to a location of said feature within said binary image, said inverse flag code and said location code.

14. A method, according to claim 13, wherein:

said central processing unit is adapted to forward said distinctive candidate epidermis record to an encoder for encoding of said distinctive epidermis record onto said identification card.

15. A method, according to claim 14, wherein:

a card reader engages said identification card and receives said distinctive epidermis record and transmits said distinctive epidermis record to said central processing unit.

16. A method for confirming the identity of an individual cardholder presenting an identification card, comprising:

providing a predetermined feature template library containing a plurality of feature templates and corresponding feature codes;

providing an identification card containing information regarding a preselected portion of the cardholder'"'"'s epidermis and codes corresponding to feature codes in said feature template library;

scanning a preselected portion of said cardholder'"'"'s epidermis and temporarily storing the results of the scan as temporary results;

reading said information from said identification card;

comparing said temporary results with the information read from said card, and generating a comparison;

determining a correlation between the information scanned and the information contained on said card; and

displaying results of said correlation, thereby indicating whether to accept the identity of said cardholder;

generating a signal to a stepper motor to adjust a charge coupled device camera to locate a distinctive reference position on preselected portions of an epidermis, and generating a distinctive position code corresponding to a distance between said distinctive reference position and a center portion of said preselected portion of an epidermis;

said charge coupled device camera generating an analog video image of said preselected portions of an epidermis; and

said charge coupled device camera generating several video images of said preselected portions of an epidermis; and

averaging each of said video images with other of said video images to produce a single video image, and temporarily saving said single video image.

17. A method according to claim 16, further comprising:

filtering said video image employing a non-linear filter thereby creating a filtered image and converting said filtered image into a binary image.

18. A method according to claim 17, further comprising:

inverting said binary image as an inverted binary image and temporarily saving said inverted binary image in the central processing unit.

19. A method according to claim 18, wherein:

said feature template library contains a plurality of predetermined binarized features, each of said plurality of predetermined binarized feature having a one of a plurality of feature codes, further comprising dividing said binary image into a plurality of overlapping small sections, correlating each of said small sections with a feature template corresponding to a feature code contained in said feature template library to determine a degree of similarity between features contained in each of said small sections and features specified by said feature codes contained in said feature template library, assigning a correlation value to each of said plurality of predetermined binarized features corresponding to its said degree of similarity with said features contained in each of said small sections, and assigning a location value indicating a position of said feature within each of said small sections.

20. A method according to claim 19, wherein:

said inverted binary image is divided into a plurality of overlapping small sections, each of said small sections being correlated with a feature template corresponding to feature code in said feature template library to determine a degree of similarity between features contained in each of said small sections and features specified by said feature codes in said feature template library, each predetermined binarized feature being assigned a correlation value corresponding to its said degree of similarity with said features contained in each of said small sections and assigned a location value indicating the position of said features within each of said small sections.