Fingerprint verification device

• US 20040131237A1
• Filed: 01/07/2003
• Published: 07/08/2004
• Est. Priority Date: 01/07/2003
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Avago Technologies ECBU IP Singapore Pte Limited (Broadcom, Inc.)
• Inventors: Machida, Akihiro
• Granted Patent: US 7,116,805 B2
• Time in Patent Office: Days
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1335 Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection

Abstract

A fingerprint verification device includes a fingerprint sensor including an imaging surface. The fingerprint sensor is configured to capture images of a user'"'"'s finger when the finger is swiped against the imaging surface. A memory stores fingerprint data. A controller compares minutiae in the captured images with the stored fingerprint data to verify the user'"'"'s identity. The controller is configured to determine whether the finger is a real human finger based on the spacing of minutiae in the captured images.

Claims

1. A fingerprint verification device comprising:

a fingerprint sensor including an imaging surface, the fingerprint sensor configured to capture images of a user'"'"'s finger when the finger is swiped against the imaging surface;

a memory for storing fingerprint data; and

a controller for comparing minutiae in the captured images with the stored fingerprint data to verify the user'"'"'s identity, the controller configured to determine whether the finger is a real human finger based on the spacing of minutiae in the captured images.

2. The fingerprint verification device of claim 1, wherein the fingerprint sensor is configured to capture a first set of images of the finger when the finger is swiped in a first direction on the imaging surface, and capture a second set of images of the finger when the finger is swiped in a second direction on the imaging surface.

3. The fingerprint verification device of claim 2, wherein the fingerprint sensor is configured to generate a first stitched image based on the first set of images, and a second stitched image based on the second set of images, and wherein the controller is configured to compare minutiae in the first and the second stitched images with the stored fingerprint data to verify the user'"'"'s identity.

4. The fingerprint verification device of claim 3, wherein the controller is configured to compare the spacing between minutiae in the first stitched image with the spacing between minutiae in the second stitched image.

5. The fingerprint verification device of claim 4, wherein the controller is configured to determine whether the finger is a real human finger based on the comparison of the spacing between minutiae in the first and the second stitched images, and the stored fingerprint data.

6. The fingerprint verification device of claim 3, wherein the controller is configured to calculate a delta value representing a difference between the spacing of minutiae in the first stitched image and the spacing of minutiae in the second stitched image.

7. The fingerprint verification device of claim 6, wherein the controller is configured to compare the delta value to the stored fingerprint data to determine whether the finger is a real human finger.

8. The fingerprint verification device of claim 7, wherein the controller is configured to calculate a first value representing the spacing between a first minutia and a second minutia in the first stitched image, calculate a second value representing the spacing between the first minutia and the second minutia in the second stitched image, and wherein the delta value represents the difference between the first value and the second value.

9. The fingerprint verification device of claim 1, wherein the fingerprint sensor is an optical swipe sensor.

10. A method of recognizing a fingerprint, the method comprising:

providing a fingerprint sensor;

capturing a first set of images of a finger when the finger is swiped in a first direction on the fingerprint sensor;

stitching the first set of images together to form a first stitched image;

capturing a second set of images of the finger when the finger is swiped in a second direction on the fingerprint sensor;

stitching the second set of images together to form a second stitched image;

comparing minutiae in the first and the second stitched images to stored fingerprint data; and

determining whether the finger is recognizable based on the comparison.

11. The method of claim 10, and further comprising:

comparing the distance between features in the first stitched image with the distance between features in the second stitched image.

12. The method of claim 11, and further comprising:

determining whether the finger is a real human finger based on the comparison of the distance between features, and the stored fingerprint data.

13. The method of claim 10, and further comprising:

calculating a delta value representing a difference between the distance between features in the first stitched image and the distance between features in the second stitched image.

14. The method of claim 13, and further comprising:

comparing the delta value to the stored fingerprint data to determine whether the finger is a real human finger.

15. The method of claim 14, and further comprising:

calculating a first value representing the distance between a first minutia and a second minutia in the first stitched image;

calculating a second value representing the distance between the first minutia and the second minutia in the second stitched image; and

wherein the delta value represents the difference between the first value and the second value.

16. The method of claim 10, and further comprising:

generating movement information with the fingerprint sensor, the movement information indicative of movement of the finger on the fingerprint sensor; and

wherein the first and the second stitched images are formed based on the movement information.

17. An electronic device comprising:

an optical swipe sensor including an imaging surface, the optical swipe sensor configured to capture a first set of images of a user'"'"'s finger when the finger is swiped in a first direction on the imaging surface, and capture a second set of images of the finger when the finger is swiped in a second direction on the imaging surface, wherein the second direction is substantially opposite to the first direction;

a memory for storing fingerprint data; and

a processor for extracting minutiae from the first and the second set of images, the processor configured to compare the extracted minutiae with the stored fingerprint data to verify the user'"'"'s identity, the processor configured to distinguish between a real human finger and a fake finger based on the spacing of features appearing in the captured images.

18. The electronic device of claim 17, wherein the optical swipe sensor is configured to generate a first stitched image based on the first set of images, and a second stitched image based on the second set of images.

19. The electronic device of claim 18, wherein the processor is configured to compare the spacing between minutiae in the first stitched image with the spacing between minutiae in the second stitched image.

20. The electronic device of claim 19, wherein the processor is configured to distinguish between a real human finger and a fake finger based on the comparison of the spacing between minutiae in the first and the second stitched images, and the stored fingerprint data.