Image processing method and device, computer-readable storage medium and electronic device

• US 10,771,689 B2
• Filed: 04/24/2019
• Issued: 09/08/2020
• Est. Priority Date: 04/28/2018
• Status: Active Grant

• Current Assignee: Guangdong OPPO Mobile Telecommunications Corporation Limited
• Original Assignee: Guangdong OPPO Mobile Telecommunications Corporation Limited
• Inventors: Guo, Ziqing, Zhou, Haitao, Au, Kamwing, Hui, Fangfang, Tan, Xiao
• Primary Examiner(s): Hsu, Amy R
• Application Number:
  US16/393,778
• Publication Number:
  US 20190335098A1
• Time in Patent Office: 503 Days
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

An image processing method and device, a computer-readable storage medium and an electronic device are provided. The method includes that: a target infrared image and a target depth image are acquired, and face detection is performed according to the target infrared image to determine a target face region, here, the target depth image is used to represent depth information corresponding to the target infrared image; a target face attribute parameter corresponding to the target face region is acquired, and face matching processing is performed on the target face region according to the target face attribute parameter; responsive to that face matching succeeds, liveness detection processing is performed on the target face region according to the target depth image to obtain a liveness detection result; and a face verification result is obtained according to the liveness detection result.

Claims

1. A method for image processing, the method being applied to an electronic device comprising a first processor, the method comprising:

acquiring, by the first processor, a target infrared image and a target depth image, and performing face detection according to the target infrared image to determine a target face region, wherein the target depth image is used to represent depth information corresponding to the target infrared image;

acquiring, by the first processor, a target face attribute parameter corresponding to the target face region, and performing face matching processing on the target face region according to the target face attribute parameter;

responsive to that face matching succeeds, performing, by the first processor, liveness detection processing on the target face region according to the target depth image to obtain a liveness detection result; and

obtaining, by the first processor, a face verification result according to the liveness detection result;

wherein the electronic device further comprises a second processor and a camera module; and

acquiring the target infrared image and the target depth image comprises;

responsive to that a face verification instruction has been detected by the second processor, controlling, by the second processor, the camera module to acquire an infrared image and a depth image and receiving the infrared image and the depth image from the camera module, wherein a time interval between a first moment at winch the infrared image is acquired and a second moment at which the depth image is acquired is less than a first threshold; and

acquiring, by the first processor, the target infrared image according to the infrared image, and acquiring the target depth image according to the depth image.

2. The method of claim 1, wherein the target face attribute parameter comprises at least one of:

a face deflection angle, a face brightness parameter, a parameter about facial features, a skin type parameter, or a geometric feature parameter.

3. The method of claim 1, wherein acquiring the target infrared image according to the infrared image and acquiring the target depth image according to the depth image comprises:

calculating, by the second processor, an infrared parallax image according to the infrared image and calculating a depth parallax image according to the depth image;

sending, by the second processor, the infrared parallax image and the depth parallax image to the first processor; and

performing, by the first processor, correction according to the infrared parallax image to obtain the target infrared image and performing correction according to the depth parallax image to obtain the target depth image.

4. The method of claim 1, wherein performing face detection according to the target infrared image to determine the target face region comprises:

detecting, by the first processor, a face region in the target infrared image; and

when two or more face regions exist in the target infrared image, determining, by the first processor, a face region with a largest region area as the target face region.

5. The method of claim 1, wherein performing liveness detection processing on the target face region according to the target depth image comprises:

extracting, by the first processor, a target face depth region corresponding to the target face region from the target depth image, and acquiring a target liveness attribute parameter according to the target face depth region; and

performing, by the first processor, liveness detection processing according to the target liveness attribute parameter.

6. The method of claim 1, wherein the target liveness attribute parameter comprises at least one of:

face depth information, a skin type feature, a texture direction, a texture density, or a texture width.

7. The method of claim 1, wherein performing liveness detection processing on the target face region according to the target depth image comprises:

extracting, by the first processor, the target face depth region corresponding to the target face region from the target depth image, and acquiring a first target liveness attribute parameter according to the target face depth region;

acquiring, by the first processor, a speckle image, the speckle image being an image which is acquired by a laser camera and which is formed by irradiation of an object with a laser speckle and the target depth image being calculated according to the speckle image;

extracting, by the first processor, a target face speckle region corresponding to the, target face region from the speckle image, and acquiring a second target liveness attribute parameter according to the target face speckle region; and

performing, by the first processor, liveness detection processing according to the first target liveness attribute parameter and the second target liveness attribute parameter.

8. The method of claim 1, wherein obtaining the thee verification result according to the liveness detection result comprises:

responsive to that liveness detection succeeds, obtaining, by the first processor, a result indicating that face verification succeeds, and responsive to that liveness detection fails, obtaining, by the first processor, a result indicating that face verification fails; and

the method further comprises;

responsive to that li mess matching fails, obtaining, by the first processor, a result indicating that face verification fails.

9. An electronic device, comprising:

a first processor; and

a memory storing instructions that, when executed by the first processor, cause processor to;

acquire a target infrared image and a target depth image and perform face detection according to the target infrared image to determine a target face region, Wherein the target depth image is used to represent depth information corresponding to the target infrared image;

acquire a target face attribute parameter corresponding to the target face region and perform face matching processing on the target face region according to the target face attribute parameter;

responsive to that face snatching succeeds, perform liveness detection processing on the target region according to the target depth image to obtain liveness detection result; and

obtain a face verification result according to the liveness detection result;

wherein the electronic device further comprises a second processor and a camera module and

the second processor is configured to, responsive to that a face verification instruction has been detected by the second processor, control the camera module to acquire an infrared image and a depth image and receive the infrared image and the depth image from the camera module, wherein a time interval between a first moment at which the infrared image is acquired and a second moment at which the depth image is acquired is less than a first threshold; and

the first processor is further configured to acquire the target infrared image according to the infrared image and acquire the target depth image according to the depth image.

10. The electronic device of claim 9, wherein the target face attribute parameter comprises at least one of:

a face deflection angle, a face brightness parameter, a parameter about facial features, a skin type parameter, or a geometric feature parameter.

11. The electronic device of claim 9, wherein the second processor is further configured to calculate an infrared parallax image according to the infrared image and calculate a depth parallax image according to the depth image, and send the infrared parallax image and the depth parallax image to the first processor;

and

the first processor is further configured to perform correction according to the infrared parallax image to obtain the target infrared image and perform correction according to the depth parallax image to obtain the target depth image.

12. The electronic device of claim 9, wherein the first processor is further configured to detect a face region in the target infrared image and, when two or more face regions exist in the target infrared image, determine a face region with a largest region area as the target face region.

13. The electronic device of claim 9, wherein the first processor is further configured to extract a target thee depth region corresponding to the target face region from the target depth image, acquire a target liveness attribute parameter according to the target face depth region and perform liveness detection processing according to the target liveness attribute parameter.

14. The electronic device of claim 9, wherein the target liveness attribute parameter comprises at least one of:

face depth information, a skin type feature, a texture direction, a texture density, or a texture width.

15. The electronic device of claim 9, wherein the first processor is further configured to extract a target face depth region corresponding to the target face region from the target depth image and acquire a first target liveness attribute parameter according to the target face depth region;

acquire a speckle image, the speckle image being an image which is acquired by a laser camera and which is formed by irradiation of an object with a laser speckle and the target depth image being calculated according to the speckle image;

extract a target face speckle region corresponding to the target face region from the speckle image and acquire a second target liveness attribute parameter according to the target face speckle region; and

perform liveness detection processing according to the first target liveness attribute parameter and the second target liveness attribute parameter.

16. The electronic device of claim 9, wherein the first processor is further configured to, responsive to that liveness detection succeeds, obtain a result indicating that face verification succeeds;

responsive to that liveness detection fails, obtain a result indicating that face verification fails, and

responsive to that face matching fails, obtain a result indicating that face verification fails.

17. The electronic device of claim 9, wherein the first processor comprises a central. processing unit (CPU) core and the second processor comprises a microcontroller unit (MCU);

or the first processor comprises a central processing unit (CPU) core and the second processor comprises a Digital Signal Processor (DSP) module in the CPU.

18. A non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by one or more processors, cause the one or more processors to:

acquire a target infrared image and a target depth image and perform face detection according to the target infrared image to determine a target face region, wherein the target depth image is used to represent depth information corresponding to the target infrared image;

acquire a target face attribute parameter corresponding to the target face region and perform face matching processing on the target face region according to the target face attribute parameter;

responsive to that face matching succeeds, perform liveness detection processing on the target face region according to the target depth image to obtain a liveness detection result; and

obtain a face verification result according to the liveness detection result;

wherein the operation of acquiring the target infrared image and the target depth image comprises;

responsive to that a face verification instruction has been detected by the second processor, controlling a camera module to acquire an infrared image and a depth image and receiving the infrared image and the depth image from the camera module, wherein a time interval between a first moment at which the infrared image is acquired and a second moment at which the depth image is acquired is less than a first threshold; and

acquiring the target infrared image according to the infrared image, and acquiring the target depth image according to the depth image.