WO2018054054A1

WO2018054054A1 - Face recognition method, apparatus, mobile terminal and computer storage medium

Info

Publication number: WO2018054054A1
Application number: PCT/CN2017/082055
Authority: WO
Inventors: 胡文迪; 李飞; 李晶
Original assignee: 中兴通讯股份有限公司
Priority date: 2016-09-23
Filing date: 2017-04-26
Publication date: 2018-03-29
Also published as: CN107872613A

Abstract

Disclosed in the embodiments of the present invention are a face recognition method, apparatus, mobile terminal and computer storage medium, the method comprising: adjusting exposure of an auxiliary camera image until a face area in the auxiliary camera image is recognized; and recognizing a face area in a main camera image using parameter information related to the face area in the auxiliary camera image.

Description

Method, device, mobile terminal and computer storage medium for face recognition

Cross-reference to related applications

The present application is based on a Chinese patent application filed on Apr. 23, 2016, the entire disclosure of which is hereby incorporated by reference.

Technical field

The present invention relates to the field of photographing technology, and in particular, to a method and device for recognizing a face, a mobile terminal, and a computer storage medium.

Background technique

The face recognition algorithm has a wide range of applications in photographing and videography. The face recognition algorithm can adjust the exposure strategy of the face position in real time according to the position of the face in the image, and focus according to the position of the face in the picture, thereby obtaining the person. Face-oriented, more natural photos and movies. However, for some special scenes, such as photos taken in a backlit scene, the exposure strategy of the backlight will darken the overexposed portion so that the face in the photo is dark, resulting in the face recognition algorithm not recognizing the special scene. The face of the face, in turn, can not be exposed and focus optimized for the face.

Summary of the invention

Embodiments of the present invention are desirable to provide a method and apparatus for face recognition, a mobile terminal, and a computer storage medium capable of accurately recognizing a face region in a main camera image in any shooting scene.

The embodiment of the invention provides a method for face recognition, which is applied to a mobile terminal including a main camera and a secondary camera;

Adjusting an exposure amount of the auxiliary camera image until a face region in the auxiliary camera image is recognized;

A face region in the main camera image is identified using parameter information associated with a face region in the secondary camera image.

In an embodiment, the adjusting the exposure amount of the auxiliary camera image until the recognition of the face region in the auxiliary camera image comprises:

If the auxiliary camera image is in the backlight scene, increasing the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized by using a face recognition algorithm;

If the secondary camera image is in a strong light scene, the exposure amount of the secondary camera image is reduced until the face region in the secondary camera image is recognized by the face recognition algorithm.

In an embodiment, the parameter information includes: a face coordinate position in the secondary camera image or an exposure amount when the face region is recognized in the secondary camera image.

In an embodiment, when the parameter information is a face coordinate position in the secondary camera image, the parameter information related to the face region in the secondary camera image is used to identify the image in the main camera image. Face area, including:

Mapping a face coordinate position in the auxiliary camera image to the main camera image by using a perspective correction algorithm to obtain a face coordinate position in the main camera image;

The exposure amount at the face coordinate position in the main camera image is adjusted until the face region in the main camera image is recognized using a face recognition algorithm.

In an embodiment, when the parameter information is an exposure amount when a face region is recognized in the auxiliary camera image, the parameter information is identified by using parameter information related to a face region in the auxiliary camera image. The face area in the main camera image, including:

Adjusting an exposure amount of the main camera image within a preset value range by using an exposure amount when the face region is recognized in the auxiliary camera image as a reference value until the main recognition is performed by using a face recognition algorithm The face area in the camera image.

In an embodiment, the method further includes:

And measuring the main camera image according to the face region in the main camera image, obtaining an exposure amount required by the main camera image, and adjusting the main camera image according to the exposure amount.

The embodiment of the invention further provides a device for recognizing a face, comprising:

a secondary recognition module configured to adjust an exposure amount of the secondary camera image until a face region in the secondary camera image is recognized;

The main image recognition module is configured to recognize a face region in the main camera image by using parameter information related to a face region in the auxiliary camera image.

In an embodiment, the auxiliary recognition module is configured to:

If the auxiliary camera image is in a strong light scene, the exposure amount of the secondary camera image is reduced until the face region in the secondary camera image is recognized by the face recognition algorithm.

In an embodiment, when the parameter information is a face coordinate position in the secondary camera image, the primary recognition module is configured to:

In an embodiment, when the parameter information is an exposure amount when a face region is recognized in the auxiliary camera image, the main camera recognition module is configured to:

Taking the exposure amount when the face region is recognized in the auxiliary camera image as a reference value, in advance The exposure amount of the main camera image is adjusted within the set value range until the face region in the main camera image is recognized by the face recognition algorithm.

In an embodiment, the apparatus further includes:

a photometry module configured to meter the main camera image according to a face region in the main camera image, obtain an exposure amount required by the main camera image, and compare the exposure amount to the main camera The image is adjusted.

The embodiment of the invention further provides a mobile terminal, which comprises the device for face recognition according to the embodiment of the invention.

The embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the method for face recognition according to the embodiment of the present invention.

The method, device, mobile terminal and computer storage medium for face recognition according to embodiments of the present invention solve the problem that a face recognition algorithm cannot be used to recognize a face region in a main camera image in a backlight scene or a glare scene. In the embodiment of the invention, different exposure strategies are used in the main camera and the auxiliary camera, and the auxiliary camera is used to adjust the exposure amount to help the main camera find the face region in the image. Embodiments of the present invention can improve the range and recognition rate of a face in a main camera image under different exposure conditions.

DRAWINGS

1 is a flowchart of a method for face recognition according to a first embodiment of the present invention;

2 is a flowchart of a method for face recognition according to a second embodiment of the present invention;

3 is a flowchart of a method for face recognition according to a third embodiment of the present invention;

4 is a schematic structural diagram of a device for a face recognition according to a fourth embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a device for a face recognition according to a fifth embodiment of the present invention; FIG.

FIG. 6 is a schematic diagram showing the structure of a device for face recognition according to a sixth embodiment of the present invention.

detailed description

The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments.

A first embodiment of the present invention is a method for face recognition, which is used in a mobile terminal including a main camera and a secondary camera; as shown in FIG. 1, the following specific steps are included:

Step S101: Adjust the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized.

Specifically, step S101 includes:

Step S102: Identify a face region in the main camera image by using parameter information related to the face region in the auxiliary camera image.

Specifically, step S102 includes:

When the parameter information is a face coordinate position in the auxiliary camera image, a face coordinate position in the auxiliary camera image is mapped into the main camera image by using a perspective correction algorithm to obtain the main camera. a face coordinate position in the image, adjusting an exposure amount at a face coordinate position in the main camera image until a face region in the main camera image is recognized by a face recognition algorithm; or

When the parameter information is an exposure amount when the face region is recognized in the auxiliary camera image, the exposure amount when the face region is recognized in the auxiliary camera image is used as a reference value, and is preset The exposure amount of the main camera image is adjusted within the value range until the face region in the main camera image is recognized using a face recognition algorithm.

A second embodiment of the present invention is a method for face recognition for use in a mobile terminal including a main camera and a secondary camera; as shown in FIG. 2, the following specific steps are included:

Step S201: The backlight detection algorithm and the strong light detection algorithm are used to determine whether the secondary camera image is in a backlight scene or a strong light scene. When the determination result is that the secondary camera image is in a backlight scene or a strong light scene, step S202 is performed.

Step S202: Adjust the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized.

Specifically, step S202 includes:

If the auxiliary camera image is in the backlight scene, the exposure amount of the auxiliary camera image is gradually increased until the coordinate position of the human face in the auxiliary camera image can be recognized by using the face recognition algorithm;

If the auxiliary camera image is in a strong light scene, the exposure amount of the secondary camera image is gradually reduced until the coordinate position of the face in the secondary camera image can be recognized by the face recognition algorithm.

As an implementation manner, since it is only necessary to obtain the coordinate position of the face in the auxiliary camera, and it is not necessary to accurately know the optimal exposure amount of the auxiliary camera, the range of the exposure amount is roughly set to 25 exposure levels. For example, from the -12th exposure level to the 12th exposure level; if the auxiliary camera image is in a strong light scene, the exposure level is gradually increased from the 0 exposure level until the face recognition algorithm can be used to identify the face. The coordinate position in the camera image; if the auxiliary camera image is in a strong light scene, the exposure level is gradually reduced from the 0 exposure level until the coordinate position of the face in the auxiliary camera image can be recognized by the face recognition algorithm .

Step S203: Map a face coordinate position in the secondary camera image to the main camera image by using a perspective correction algorithm to obtain a face coordinate position in the main camera image.

Step S204: adjusting the exposure amount at the face coordinate position in the main camera image, To identify a face region in the main camera image using a face recognition algorithm.

Step S205: metering the main camera image according to the face region in the main camera image, obtaining an exposure amount required by the main camera image, and adjusting the main camera image according to the exposure amount. .

Specifically, step S205 includes:

Taking the brightness of the face region in the main camera image as the main focus, taking into account the brightness of other regions in the main camera image, obtaining the exposure amount required by the main camera image according to the weight metering algorithm, and according to the The exposure amount is adjusted on the main camera image, and the face recognition algorithm is used to perform face recognition on the main camera image after adjusting the exposure amount.

A third embodiment of the present invention is a method for face recognition for use in a mobile terminal including a main camera and a secondary camera; as shown in FIG. 3, the following specific steps are included:

Step S301: The backlight detection algorithm and the strong light detection algorithm are used to determine whether the secondary camera image is in a backlight scene or a strong light scene. When the determination result is that the secondary camera image is in a backlight scene or a strong light scene, step S302 is performed.

Step S302: Adjust the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized.

Specifically, step S302 includes:

The auxiliary camera adjusts an exposure amount of the auxiliary camera image by cyclically traversing a preset exposure table until a face region in the auxiliary camera image is recognized.

The preset exposure table includes a plurality of levels of exposure parameters, which are roughly set to 25 exposure levels compared to the range of values of the exposure amount of the second embodiment, the preset exposure table will be an exposure amount The range of values is divided into more precise exposure parameters.

Step S303: Synchronize the exposure parameters in the preset exposure table when the face region is recognized in the auxiliary camera image into the main camera image.

Step S304: using an exposure parameter in the preset exposure table, and the exposure parameter The main camera image is adjusted by a preset number of front and rear (for example, five before and after) exposure parameters in the preset exposure table until the face region in the main camera image is recognized by the face recognition algorithm.

Step S305: metering the main camera image according to the face region in the main camera image, obtaining an exposure amount required by the main camera image, and adjusting the main camera image according to the exposure amount. .

Specifically, the step S305 includes:

A fourth embodiment of the present invention, a device for recognizing a face, as shown in FIG. 4, includes the following components:

The auxiliary image recognition module 401 is configured to adjust an exposure amount of the auxiliary camera image until the face region in the auxiliary camera image is recognized;

The main image recognition module 402 is configured to recognize a face region in the main camera image by using parameter information related to a face region in the auxiliary camera image.

Specifically, the auxiliary photo recognition module 401 is configured to:

Specifically, the main photo recognition module 402 is configured to:

When the parameter information is a face coordinate position in the auxiliary camera image, the face coordinate position in the secondary camera image is mapped to the main camera image by using a perspective correction algorithm Adjusting the exposure amount at the face coordinate position in the main camera image until the face coordinate position in the main camera image is obtained, until the face in the main camera image is recognized by the face recognition algorithm Area; or,

A fifth embodiment of the present invention, a device for recognizing a face, as shown in FIG. 5, includes:

The determining module 501 is configured to determine whether the secondary camera image is in a backlight scene or a strong light scene by using a backlight detection algorithm and a strong light detection algorithm. When the determination result is that the secondary camera image is in a backlight scene or a strong light scene, the auxiliary camera is triggered. Identification module 502;

The auxiliary image recognition module 502 is configured to adjust an exposure amount of the auxiliary camera image until a face region in the auxiliary camera image is recognized;

The information synchronization module 503 is configured to map the face coordinate position in the secondary camera image to the main camera image by using a perspective correction algorithm to obtain a face coordinate position in the main camera image.

The main image recognition module 504 is configured to adjust an exposure amount at a face coordinate position in the main camera image until a face region in the main camera image is recognized by a face recognition algorithm.

Specifically, the auxiliary image recognition module 502 is configured to:

If the auxiliary camera image is in the backlight scene, increasing the exposure amount of the auxiliary camera image until the coordinate position of the human face in the auxiliary camera image can be recognized by using the face recognition algorithm;

If the auxiliary camera image is in a highlight scene, the exposure amount of the secondary camera image is reduced until the coordinate position of the face in the secondary camera image can be recognized by the face recognition algorithm.

As an implementation manner, since only the coordinate position of the face in the auxiliary camera is obtained, and the optimal exposure amount of the auxiliary camera is not required to be accurately understood, the range of the exposure amount is roughly set to 25 exposure levels; If the auxiliary camera image is in a strong light scene, the exposure level is gradually increased from the 0 exposure level until the coordinate position of the face in the auxiliary camera image can be recognized by the face recognition algorithm; if the auxiliary camera image In the glare scene, the exposure level is gradually reduced from the 0 exposure level until the coordinate position of the face in the auxiliary camera image can be recognized by the face recognition algorithm.

As an embodiment, the device further includes: a photometry module 505 configured to perform photometry on the main camera image according to a face region in the main camera image to obtain an exposure required by the main camera image And adjusting the main camera image according to the exposure amount.

Specifically, the photometry module 505 is configured to:

A sixth embodiment of the present invention, a device for recognizing a face, as shown in FIG. 6, includes:

The determining module 601 is configured to determine whether the secondary camera image is in a backlight scene or a strong light scene by using a backlight detection algorithm and a strong light detection algorithm. When the determination result is that the secondary camera image is in a backlight scene or a strong light scene, the auxiliary camera is triggered. Identification module 602.

The auxiliary recognition module 602 is configured to adjust an exposure amount of the secondary camera image until a face region in the secondary camera image is recognized.

The information synchronization module 603 is configured to synchronize the exposure parameters in the preset exposure table when the face region is recognized in the secondary camera image into the main camera image.

The main image recognition module 604 is configured to adjust the exposure parameter in the preset exposure table, and the exposure parameter adjusts the preset number of exposure parameters in the preset exposure table The main camera image until the face region in the main camera image is recognized using a face recognition algorithm.

Specifically, the auxiliary photo recognition module 602 is configured to:

The exposure amount of the secondary camera image is adjusted by looping through the preset exposure table until the face region in the secondary camera image is recognized.

The preset exposure table includes a plurality of levels of exposure parameters, which are roughly set to 25 exposure levels compared to the value range of the exposure amount with the fifth embodiment, the preset exposure table will be an exposure amount The range of values is divided into more precise exposure parameters.

As an embodiment, the device further includes: a photometry module 605 configured to perform photometry on the main camera image according to a face region in the main camera image to obtain an exposure required by the main camera image And adjusting the main camera image according to the exposure amount.

Specifically, the photometry module 605 is configured to:

Taking the brightness of the face region in the main camera image as the main focus, taking into account the brightness of other regions in the main camera image, obtaining the exposure amount required by the main camera image according to the weight metering algorithm, and according to the The exposure amount is adjusted to the main camera image, and the face recognition algorithm is used to perform face recognition on the main camera image after adjusting the exposure amount.

A seventh embodiment of the present invention provides a mobile terminal, which includes the device for face recognition according to any one of the fourth to sixth embodiments of the present invention.

In the several embodiments provided by the present invention, it should be understood that the disclosed method and apparatus, It can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be another division manner, for example, multiple modules or components may be combined, or Can be integrated into another system, or some features can be ignored or not executed. In addition, the communication connections between the various components shown or discussed may be indirect coupling or communication connections through some interfaces, devices or modules, and may be electrical, mechanical or otherwise.

The modules described above as separate components may or may not be physically separated. The components displayed as modules may or may not be physical modules, that is, may be located in one place or distributed to multiple network modules; Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may be separately used as one module, or two or more modules may be integrated into one module; The module can be implemented in the form of hardware or in the form of hardware plus software function modules.

It will be understood by those skilled in the art that all or part of the steps of implementing the foregoing method embodiments may be performed by hardware related to program instructions. The foregoing program may be stored in a computer readable storage medium, and when executed, the program includes The foregoing steps of the method embodiment; and the foregoing storage medium includes: a removable storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and the like, which can store program codes.

Alternatively, the above-described integrated module of the embodiment of the present invention may be stored in a computer readable storage medium if it is implemented in the form of a software function module and sold or used as a stand-alone product. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a storage medium, including a plurality of instructions. Enabling a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods of the various embodiments of the present invention All or part. The foregoing storage medium includes various media that can store program codes, such as a mobile storage device, a ROM, a magnetic disk, or an optical disk.

The memory switching method and apparatus described in the embodiments of the present invention are only exemplified by the foregoing embodiments, but are not limited thereto, and those skilled in the art should understand that the technical solutions described in the foregoing embodiments may still be modified. Equivalent replacement of some or all of the technical features may be made without departing from the scope of the technical solutions of the embodiments of the present invention.

The above is only the preferred embodiment of the present invention and is not intended to limit the scope of the present invention.

Industrial applicability

The technical solution of the embodiment of the invention solves the problem that the face recognition algorithm cannot be used to recognize the face region in the main camera image in the backlight scene or the glare scene. In the embodiment of the invention, different exposure strategies are used in the main camera and the auxiliary camera, and the auxiliary camera is used to adjust the exposure amount to help the main camera find the face region in the image. Embodiments of the present invention can improve the range and recognition rate of a face in a main camera image under different exposure conditions.

Claims

A method for face recognition is applied to a mobile terminal including a main camera and a secondary camera;

Adjusting an exposure amount of the auxiliary camera image until a face region in the auxiliary camera image is recognized;

A face region in the main camera image is identified using parameter information associated with a face region in the secondary camera image.
The method of claim 1, wherein the adjusting the exposure amount of the secondary camera image until the recognition of the face region in the secondary camera image comprises:

If the auxiliary camera image is in the backlight scene, increasing the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized by using a face recognition algorithm;

If the secondary camera image is in a strong light scene, the exposure amount of the secondary camera image is reduced until the face region in the secondary camera image is recognized by the face recognition algorithm.
The method of claim 1 wherein

The parameter information includes: a face coordinate position in the secondary camera image or an exposure amount when the face region is recognized in the secondary camera image.
The method according to claim 3, wherein when said parameter information is a face coordinate position in said secondary camera image, said identifying is performed using parameter information related to a face region in said secondary camera image The face area in the main camera image, including:

Mapping a face coordinate position in the auxiliary camera image to the main camera image by using a perspective correction algorithm to obtain a face coordinate position in the main camera image;

The exposure amount at the face coordinate position in the main camera image is adjusted until the face region in the main camera image is recognized using a face recognition algorithm.
The method according to claim 3, wherein said utilization and said auxiliary camera image are when said parameter information is an exposure amount when a face region is recognized in said secondary camera image The parameter information related to the face region in the middle identifies the face region in the main camera image, including:

Adjusting an exposure amount of the main camera image within a preset value range by using an exposure amount when the face region is recognized in the auxiliary camera image as a reference value until the main recognition is performed by using a face recognition algorithm The face area in the camera image.
The method of claim 1 wherein the method further comprises:

And measuring the main camera image according to the face region in the main camera image, obtaining an exposure amount required by the main camera image, and adjusting the main camera image according to the exposure amount.
A device for face recognition, comprising:

a secondary recognition module configured to adjust an exposure amount of the secondary camera image until a face region in the secondary camera image is recognized;

The main image recognition module is configured to recognize a face region in the main camera image by using parameter information related to a face region in the auxiliary camera image.
The apparatus according to claim 7, wherein the auxiliary recognition module is configured to:

If the auxiliary camera image is in the backlight scene, increasing the exposure amount of the secondary camera image until the face region in the secondary camera image is recognized by using a face recognition algorithm;

If the secondary camera image is in a strong light scene, the exposure amount of the secondary camera image is reduced until the face region in the secondary camera image is recognized by the face recognition algorithm.
The apparatus according to claim 7, wherein

The parameter information includes: a face coordinate position in the secondary camera image or an exposure amount when the face region is recognized in the secondary camera image.
The apparatus according to claim 9, wherein when the parameter information is a face coordinate position in the secondary camera image, the primary recognition module is configured to:

Mapping a face coordinate position in the auxiliary camera image to the main camera image by using a perspective correction algorithm to obtain a face coordinate position in the main camera image;

The exposure amount at the face coordinate position in the main camera image is adjusted until the face region in the main camera image is recognized using a face recognition algorithm.
The apparatus according to claim 9, wherein when the parameter information is an exposure amount when a face area is recognized in the auxiliary camera image, the main picture recognition module is configured to:

Adjusting an exposure amount of the main camera image within a preset value range by using an exposure amount when the face region is recognized in the auxiliary camera image as a reference value until the main recognition is performed by using a face recognition algorithm The face area in the camera image.
The apparatus of claim 7 wherein said apparatus further comprises:

a photometry module configured to meter the main camera image according to a face region in the main camera image, obtain an exposure amount required by the main camera image, and compare the exposure amount to the main camera The image is adjusted.
A mobile terminal comprising the device for face recognition according to any one of claims 7 to 12.
A computer storage medium storing computer executable instructions for performing the method of face recognition according to any one of claims 1 to 6.