Fingerprint identification device, method and electronic device

Patent metadata

Field	Value
Publication number	US-11475706-B2
Application number	US-202117326987-A
Country	US
Kind code	B2
Filing date	May 21, 2021
Priority date	Dec 13, 2018
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

Provided are a fingerprint identification device, a fingerprint identification method and an electronic device, which could improve security of fingerprint identification. The fingerprint identification device includes an optical fingerprint sensor including a plurality of pixel units; at least two filter units disposed above at least two of the plurality of pixel units, where each filter unit corresponds to one pixel unit, and the at least two filter units comprise filter units in at least two colors.

First claim

What is claimed is:

1. A fingerprint identification device, arranged under a display screen to implement under-display optical fingerprint detection for capturing a fingerprint pattern of a finger on the display screen, the fingerprint identification device comprising:
an optical fingerprint sensor comprising a plurality of pixel units,
at least two filter units disposed above at least two characteristic pixel units of the plurality of pixel units, wherein each filter unit corresponds to one characteristic pixel unit, the at least two filter units comprise filter units in at least two colors, a color fingerprint image of an object to be identified captured by the at least two characteristic pixel units is used to determine whether the object to be identified is a real finger, and a gray scale fingerprint image captured by other pixel units except the at least two characteristic pixel units in the plurality of pixel units is used to perform fingerprint identification;
wherein a ratio of a number of the at least two filter units to a total number of the plurality of pixel units in the optical fingerprint sensor is less than 5%.

2. The device according to claim 1 , wherein a number of consecutive filter units in the at least two filter units is less than 8.

3. The device according to claim 1 , wherein no filter layer is disposed above other pixel units except the at least two characteristic pixel units in the plurality of pixel units.

4. The device according to claim 3 , wherein the at least two filter units constitute at least one filter unit group, each filter unit group comprises at least two filter units, and adjacent filter units in the filter unit group comprise filter units in at least two colors.

5. The device according to claim 4 , the adjacent filter units in the filter unit group comprise at least two of a red filter unit, a green filter unit and a blue filter unit.

6. The device according to claim 1 , wherein the color of a filter layer disposed above other pixel units except the at least two characteristic pixel units in the plurality of pixel units is green.

7. The device according to claim 6 , wherein the at least two filter units constitute at least one filter unit group, each filter unit group comprises at least two filter units, and adjacent filter units in the filter unit group comprise filter units in at least two colors.

8. The device according to claim 7 , wherein the adjacent filter units in the filter unit group comprise a red filter unit and a blue filter unit exclusively.

9. The device according to claim 7 , wherein the adjacent filter units in the filter unit group comprise a red filter unit, a blue filter unit and a green filter unit exclusively.

10. The device according to claim 1 , the at least two filter units constitute a plurality of filter unit groups which are discretely distributed above a pixel array constituted by the plurality of pixel units.

11. The device according to claim 1 , wherein the fingerprint identification device further comprises:
a processor, configured to process, through a deep learning network, a fingerprint image of an object to be identified captured by the at least two characteristic pixel units to determine whether the object to be identified is a real finger.

12. The device according to claim 11 , wherein the processor is further configured to:
perform fingerprint identification according to a fingerprint image captured by other pixel units except the at least two characteristic pixel units in the plurality of pixel units.

13. The device according to claim 11 , wherein the processor is further configured to:
extract, from fingerprint images of a plurality of real fingers and fake fingerprints captured by the optical fingerprint sensor, sample values of the pixel units corresponding to the filter units in each fingerprint image, and recombine the sample values to obtain a color fingerprint image; and
input the color fingerprint image into the deep learning network for training to obtain a model and a parameter of the deep learning network.

14. A fingerprint identification method, applied to a fingerprint identification device arranged under a display screen to implement under-display optical fingerprint detection for capturing a fingerprint pattern of a finger on the display screen, the fingerprint identification method comprising:
capturing a fingerprint image of an object to be identified through a plurality of pixel units of an optical fingerprint sensor, wherein at least two filter units are disposed above at least two characteristic pixel units of the plurality of pixel units, each filter unit corresponds to one characteristic pixel unit, the at least two filter units comprise filter units in at least two colors, and a ratio of a number of the at least two filter units to a total number of the plurality of pixel units in the optical fingerprint sensor is less than 5%; and
determining, according to a color fingerprint image of the object to be identified captured by the at least two characteristic pixel units, whether the object to be identified is a real finger;
performing fingerprint identification according to a gray scale fingerprint image captured by other pixel units except the at least two characteristic pixel units in the plurality of pixel units.

15. The method according to claim 14 , wherein the determining, according to the fingerprint image of the object to be identified captured by the at least two characteristic pixel units, whether the object to be identified is the real finger comprises:
processing, through a deep learning network, the fingerprint image of the object to be identified captured by the at least two characteristic pixel units to determine whether the object to be identified is the real finger.

16. The method according to claim 14 , wherein a number of consecutive filter units in the at least two filter units is less than 8.

17. The method according to claim 14 , wherein no filter layer is disposed above other pixel units except the at least two characteristic pixel units in the plurality of pixel units.

18. The method according to claim 14 , wherein the color of a filter layer disposed above other pixel units except the at least two characteristic pixel units in the plurality of pixel units is green.

19. An electronic device, comprising:
a display screen; and
a fingerprint identification device arranged under the display screen to implement under-display optical fingerprint detection for capturing a fingerprint pattern of a finger on the display screen;
wherein the fingerprint identification device comprises:
an optical fingerprint sensor comprising a plurality of pixel units;
at least two filter units disposed above at least two characteristic pixel units of the plurality of pixel units, wherein each filter unit corresponds to one characteristic pixel unit, the at least two filter units comprise filter units in at least two colors, a color fingerprint image of an object to be identified captured by the at least two characteristic pixel units is used to determine whether the object to be identified is a real finger, and a gray scale fingerprint image captured by other pixel units except the at least two characteristic pixel units in the plurality of pixel units is used to perform fingerprint identification;
wherein a ratio of a number of the at least two filter units to a total number of the plurality of pixel units in the optical fingerprint sensor is less than 5%.

Assignees

• Shenzhen Goodix Tech Co Ltd

Inventors

• Li Shunzhan
• Cheng Xiang
• Gu Qin
• Wu Yonghui

Classifications

• G02B5/201 Primary

  in the form of arrays · CPC title

• G06V40/1312

  direct reading, e.g. contactless acquisition · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V40/1388 Primary

  using image processing · CPC title

• G06F18/217

  Validation; Performance evaluation; Active pattern learning techniques · CPC title