Fingerprint identification device, method and electronic device

Patent metadata

Field	Value
Publication number	US-11048910-B2
Application number	US-201916416166-A
Country	US
Kind code	B2
Filing date	May 18, 2019
Priority date	Dec 13, 2018
Publication date	Jun 29, 2021
Grant date	Jun 29, 2021

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 pixel units 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, comprising:
an optical fingerprint sensor comprising a plurality of pixel units; and
at least two filter units disposed above at least two pixel units of the plurality of pixel units, wherein each filter unit corresponds to at least one pixel unit, and the at least two filter units comprise filter units in at least two colors;
wherein a fingerprint image with at least two colors of an object to be identified captured by the at least two pixel units is used to determine whether the object to be identified is a real finger;
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; and
a green filter layer is disposed above other pixel units except the at least two pixel units in the plurality of pixel units, the adjacent filter units in the filter unit group comprise a red filter unit and a blue filter unit exclusively; or
no filter layer is disposed above the other pixel units, 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.

2. The device according to claim 1 , wherein colors of the at least two filter units are different from a color of a filter layer disposed above other pixel units except the at least two pixel units in the plurality of pixel units, or no filter layer is disposed above the other pixel units.

3. The device according to claim 2 , wherein a ratio of a number of the at least two filter units to a total number of the plurality of pixel units is less than a first threshold, and a number of consecutive filter units in the at least two filter units is less than a second threshold.

4. 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 pixel units to determine whether the object to be identified is a real finger, and perform fingerprint identification according to a fingerprint image captured by other pixel units except the at least two pixel units in the plurality of pixel units.

5. The device according to claim 4 , 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.

6. A 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 pixel units of the plurality of pixel units, each filter unit corresponds to at least one pixel unit, and the at least two filter units comprise filter units in at least two colors; and
determining, according to a fingerprint image with at least two colors of the object to be identified captured by the at least two pixel units, whether the object to be identified is a real finger;
wherein the determining, according to the fingerprint image with at least two colors of the object to be identified captured by the at least two 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 pixel units to determine whether the object to be identified is the real finger.

7. The method according to claim 6 , further comprising:
capturing fingerprint images of a plurality of real fingers and fake fingers through the optical fingerprint sensor;
extracting sample values of the pixel units corresponding to the filter units in each fingerprint image, and recombining the sample values to obtain a color fingerprint image; and
inputting the color fingerprint image into the deep learning network for training to obtain a model and a parameter of the deep learning network.

8. The method according to claim 6 , further comprising:
performing fingerprint identification according to a fingerprint image captured by other pixel units except the at least two pixel units in the plurality of pixel units.

9. The method according to claim 6 , wherein colors of the at least two filter units are different from a color of a filter layer disposed above other pixel units except the at least two pixel units in the plurality of pixel units, or no filter layer is disposed above the other pixel units;
wherein a ratio of a number of the at least two filter units to a total number of the plurality of pixel units is less than a first threshold, and a number of consecutive filter units in the at least two filter units is less than a second threshold.

10. The method 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.

11. A fingerprint identification device configured to be disposed in an electronic device with a display screen, comprising:
an optical fingerprint sensor, configured to be disposed below the display screen, and a fingerprint detecting region of the optical fingerprint sensor is located within a display region of the display screen, wherein the optical fingerprint sensor comprises a pixel array having a plurality of pixel units, the plurality of pixel units comprises characteristic pixel units and ordinary pixel units, and the characteristic pixel units are distributed and arranged in the pixel array of the optical fingerprint sensor;
a plurality of filter units, disposed above the optical fingerprint sensor, wherein each filter unit corresponds to at least one characteristic pixel unit, the plurality of filter units comprises a first filter unit and a second filter unit of different colors, and the characteristic pixel units are used to receive light signals formed by an object to be identified above the display screen and passing through the first filter unit and the second filter unit, and the light signals are used to determine whether the object to be identified above the display screen is a real finger;
wherein a light transmissive material or an air gap is formed above the ordinary pixel units of the pixel array, and the ordinary pixel units are used to receive fingerprint detection signals formed by a finger above the display screen and passing through the light transmissive material or the air gap, so as to obtain a grayscale fingerprint image of the finger.

12. The device according to claim 11 , the first filter unit and the second filter unit are respectively a red filter unit that allows the passage of the red wavelength band and a blue filter unit that allows the passage of the blue wavelength band.

13. The device according to claim 11 , the plurality of filter units constitute a plurality of filter unit groups, and the plurality of filter unit groups are discretely distributed in the pixel array of the optical fingerprint sensor, and each filter unit group includes at least one first filter unit and at least one second filter unit and adjacent filter units in ea

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

  using image processing · CPC title

• G06F18/217

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