WO2022027432A1

WO2022027432A1 - Photography method, photographic apparatus, and terminal device

Info

Publication number: WO2022027432A1
Application number: PCT/CN2020/107396
Authority: WO
Inventors: 邓宝华; 袁田
Original assignee: 深圳市锐明技术股份有限公司
Priority date: 2020-08-06
Filing date: 2020-08-06
Publication date: 2022-02-10
Also published as: CN112055961B; CN112055961A

Abstract

Provided is a photography method, comprising: after a facial image is acquired, determining a human eye weight region and a first facial weight region in the facial image according to feature point information in the facial image; determining a first weight of the human eye weight region and a second weight of the first facial weight region according to the size of the human eye weight region and the size of the first facial weight region; determining an exposure parameter according to the first weight, the second weight, first brightness information of the human eye weight region and second brightness information of the first facial weight region; and photographing a target user according to the exposure parameter. By means of the method, the photographic quality of human eye details during the photographing of a face can be improved.

Description

Shooting method, shooting device and terminal equipment

technical field

The present application belongs to the field of photographing technologies, and in particular, relates to a photographing method, a photographing apparatus, a terminal device, and a computer-readable storage medium.

Background technique

In application scenarios such as in-vehicle security, cameras are often deployed to capture human behavior. For example, a camera can be installed in the cab of the vehicle to capture the driver's driving state to determine whether the driver is in a fatigued driving state. Therefore, it is necessary to capture detailed information of human eyes when shooting.

technical problem

However, at present, when photographing a human face, due to many interfering factors such as other facial features and the environment, the photographic quality of the human eye details in the photographed face image is often poor.

technical solutions

The embodiments of the present application provide a photographing method, a photographing apparatus, a terminal device, and a computer-readable storage medium, which can improve the photographing quality of human eye details when photographing a human face.

In a first aspect, an embodiment of the present application provides a shooting method, including:

After acquiring the face image, determine the eye weight area and the first face weight area in the face image according to the feature point information in the face image;

According to the size of the human eye weight area and the size of the first face weight area, determine the first weight of the human eye weight area and the second weight of the first face weight area;

determining an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area;

According to the exposure parameters, the target user is photographed.

In a second aspect, an embodiment of the present application provides a photographing device, including:

a first determination module, configured to determine a human eye weight area and a first face weight area in the face image according to the feature point information in the face image after acquiring the face image;

A second determination module, configured to determine the first weight of the eye weight region and the first weight of the first face weight region according to the size of the eye weight region and the size of the first face weight region two weights;

a third determining module, configured to determine an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area;

The photographing module is used for photographing the target user according to the exposure parameter.

In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, a display, and a computer program stored in the memory and running on the processor, characterized in that the processor executes the computer During the program, the shooting method as described above in the first aspect is implemented.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the shooting method described in the first aspect is implemented.

In a fifth aspect, an embodiment of the present application provides a computer program product that, when the computer program product runs on a terminal device, enables the terminal device to execute the above-mentioned shooting method in the above-mentioned first aspect.

beneficial effect

In this embodiment of the present application, after the face image is acquired, the eye weight area and the first face weight area may be determined in the face image according to the feature point information in the face image. In this case, The face image may be partitioned according to the feature point information. Then, according to the size of the eye weight area and the size of the first face weight area, determine the first weight of the eye weight area and the second weight of the first face weight area, and then according to The first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area, determine exposure parameters such that the first weight and The second weight can better reflect the importance of the corresponding weight area in the face image, so that the importance of the different weight areas of the face and the brightness of the different weight areas can be fully considered to determine the exposure parameters, so as to avoid the exposure parameters caused by the presence of human eyes. The proportion of the human face is small, so that the exposure parameters during shooting are mainly determined according to other features in the face image, so that the shooting quality of the details of the human eye is poor, so that according to the exposure parameters, the When the target user is shooting, it can improve the shooting quality of human eye details.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic flowchart of a photographing method provided by an embodiment of the present application;

2 is a schematic diagram of an exemplary division manner of each weight region in a face image provided by an embodiment of the present application;

FIG. 3 is a schematic flowchart of step S102 provided by an embodiment of the present application;

FIG. 4 is an exemplary schematic diagram of determining the edge of the human eye weight region provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a photographing device according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

Embodiments of the present invention

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to illustrate the above-mentioned technical solutions of the present application, the following specific embodiments are used for description.

Example 1

The shooting methods provided by the embodiments of the present application are described below.

FIG. 1 shows a flowchart of a photographing method provided by an embodiment of the present application, and the photographing method may be applied to a terminal device.

The shooting methods provided in the embodiments of the present application can be applied to in-vehicle devices, servers, desktop computers, mobile phones, tablet computers, wearable devices, augmented reality (AR)/virtual reality (VR) devices, notebook computers, On terminal devices such as an ultra-mobile personal computer (UMPC), a netbook, and a personal digital assistant (PDA), the embodiments of the present application do not limit the specific type of the terminal device.

At present, in some application scenarios, it is necessary to capture the details of the human eye through the camera, so as to more accurately judge the current state of the person being photographed. For example, the driver's face image can be captured by a camera installed on the car, and whether the driver is in a fatigued driving state can be determined through the details of the human eye and other facial information in the face image. However, during the shooting process, because the human eye area is small and the skin reflectivity of different faces is different, the exposure brightness will be continuously adjusted according to factors such as skin reflectivity, etc., so that the shooting of human eye details cannot be guaranteed. quality; in addition, wearing glasses, masks, etc. will also interfere with the shooting of human eye details; and, in scenes such as backlighting, the human face is often dark, so the human eye details cannot be effectively identified.

Therefore, in scenes with high requirements for eye shooting details, such as fatigue driving recognition, the current method of shooting human faces is prone to improper exposure, thus failing to meet the shooting requirements for human eye details.

In the embodiment of the present application, the first weight of the human eye weight region and the first weight of the human eye weight region may be determined according to the size of the human eye weight region in the human face image and the size of the first face weight region in the human face image. a second weight of the face weight region, and then according to the first weight, the second weight, the first brightness information of the human eye weight region, and the second brightness information of the first face weight region, Determine the exposure parameters so that the first weight and the second weight can better reflect the importance of the corresponding weight regions in the face image, so that the importance of the different weight regions of the face and the different weight regions can be fully considered The exposure parameter is determined according to the brightness of the target user, so that when the target user is photographed according to the exposure parameter, the photographing quality of the details of the human eye can be improved.

Specifically, as shown in FIG. 1 , the shooting method may include:

Step S101 , after acquiring the face image, according to the feature point information in the face image, determine the human eye weight area and the first face weight area in the face image.

In the embodiment of the present application, the face image is an image including a human face. There are many ways to acquire the face image. Exemplarily, the face image may be captured by a camera in the terminal device implementing the embodiments of the present application; in addition, the face image may also be captured by a camera communicatively connected to the terminal device, and transmitted to in the terminal device; alternatively, the face image may also be a local image pre-stored in the terminal device or the like. The specific acquisition method of the face image is not limited herein.

The feature point information may include at least one of information on feature points of facial features in a human face, feature points on an edge of the human face, and the like, and information on feature points on objects associated with the human face. Exemplarily, the objects associated with the face may include items such as glasses, masks, etc., which are worn by the face in the face image, as well as other shielding objects for the face, etc. Correspondingly, the feature point information may be It includes information such as the coordinates of the feature points used to identify the outline of the glasses, and the coordinates of the feature points used to identify the outline of the mask.

The human eye weight area may include at least part of the human eye area, the first face weight area may include at least part of the face area, for example, the first face weight area may include at least part of the cheek area, at least part of the forehead area and at least one of at least part of the hair area and the like. Wherein, the first face weight region may not overlap with the human eye weight region.

In the embodiment of the present application, there may be various specific manners for determining the eye weight region and the first face weight region. In some embodiments, the region where the human eye is located may be determined as the human eye weight region according to the edge feature points of the human eye; or, the size of the region where the human eye is located, the relative positional relationship between the target camera and the human face may be used (For example, the camera shoots the front or side of the face, or is inclined at a certain angle relative to the front of the face, etc.), expand the area where the human eye is located, and use the expanded human eye area as the eye weight area. The manner of determining the first face weight region may be similar to that of the human eye weight region, or may be determined in other manners. Exemplarily, after the human eye weight region is determined, the first face weight region may be determined according to information such as edges of the human eye weight region and corresponding facial feature point information. In some examples, the first face weight area may be a cheek weight area. In this case, the lower edge feature point, the left edge feature point and the right edge feature point of the cheek may be obtained, and according to the human eye weight The lower edge of the region, which determines the edge of the cheek weight region.

Step S102: Determine a first weight of the human eye weight area and a second weight of the first face weight area according to the size of the eye weight area and the size of the first face weight area.

In this embodiment of the present application, the first weight may be used to reflect the importance of the human eye weight area, and the second weight may be used to reflect the importance of the first face weight area.

In this embodiment of the present application, the first weight and the second weight may be dynamically determined according to the size of the eye weight region and the size of the first face weight region, rather than being preset. Exemplarily, the ratio between the first weight and the second weight may be determined according to the ratio between the area of the eye weight area and the area of the first face weight area, so that all When the eye weight area is smaller than the first face weight area, the size of the first weight can be appropriately increased, so as to avoid subsequent determinations due to the small proportion of the first eye weight area. The exposure parameters and other shooting parameters cannot capture the details of the human eye.

In some embodiments, the determining the first weight of the eye weight region and the size of the first face weight region according to the size of the eye weight region and the size of the first face weight region Second weight, including:

determining a first weight of the eye weight region and a second weight of the first face weight region such that the product of the first weight and the first area is the product of the second weight and the second area The ratio is greater than a preset ratio, wherein the first area is the area of the human eye weight region, and the second area is the area of the first face weight region.

In this embodiment of the present application, the specific value of the preset ratio may be determined according to a specific application scenario, a preset experiment, or the like. Exemplarily, the preset ratio may be 3.

Through the embodiment of the present application, the first weight and the second weight can be better adjusted according to the area of different weighted regions in the face image, so as to avoid the problem of the human eyes occupying a small proportion in the face. As a result, the exposure parameters during shooting are mainly determined according to other features in the face image, so that the shooting quality of the details of the human eye is poor.

Step S103: Determine an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area.

Exemplarily, the first brightness information of the human eye weight region may include an average brightness value, an overall brightness value, and/or a brightness value of each pixel of the first human eye weight region, and the like. In some embodiments, the human eye weight region may also include multiple sub-regions, and the first brightness information may include brightness information of each of the sub-regions.

In some embodiments, a corresponding weighting operation may be performed on the first weight, the second weight, the average brightness value of the human eye weight region, and the average brightness value of the first face weight region to obtain An overall brightness value from which to determine exposure parameters. The exposure parameters may include exposure time, exposure gain, and the like. If the overall brightness value is small, the image brightness can be improved by increasing the exposure time and/or increasing the exposure gain; if the overall brightness value is large, reducing the exposure time and/or reducing the exposure gain etc. to reduce the image brightness.

In some embodiments, the exposure parameter is determined according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area ,include:

determining comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information;

The exposure parameter is determined according to the comprehensive brightness information.

In the embodiment of the present application, through the predetermined first weight and the second weight, the comprehensive brightness information can fully consider the human eye weight area, and can also take into account the first face weight area, etc. other areas other than the weight area of the human eye, so that the brightness comprehensively evaluated in the comprehensive brightness information can better reflect the approximate moderate range of human eye brightness in the face image, and is used to determine the exposure parameter, so that The exposure parameters can ensure that parts such as human eyes will not be overexposed or underexposed when photographing a human face, so that details of human eyes will not be lost.

In some embodiments, the first face-weighted region is located below the eye-weighted region;

The determining of the comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information includes:

Determine the height of the human eye according to the feature point information of the human eye in the feature point information;

If the height of the human eye is greater than the second preset height, the area directly above the eye weight area and the height is the first height threshold is used as the second face weight area, and the area located in the second face weight area The area directly above the area and the height of which is the second height threshold is used as the third face weight area;

According to the first weight, determine the third weight of the second face weight area and the fourth weight corresponding to the third face weight area;

According to the first weight, the second weight, the first brightness information, the second brightness information, the third weight, the fourth weight, the third brightness of the second face weight area information and fourth luminance information of the third face weighting region to determine the comprehensive luminance information.

In this embodiment of the present application, the information on the feature points of the human eye may include the coordinates of the upper edge feature point of the human eye and the coordinates of the lower edge feature point of the human eye. The height of the human eye can be calculated according to the coordinates of the upper edge feature point of the human eye and the coordinates of the lower edge feature point of the human eye.

Generally speaking, the width of the human eye weight region and the width of the first face weight region may be relatively close. Therefore, the height of the human eye can reflect the size of the region where the human eye is located in the human eye image, and will have a greater impact on the size of the human eye weight region. Wherein, if the height of the human eye is greater than the second preset height, it can be considered that the region where the human eye is located in the human eye image is larger, contains more details of the human eye, and the corresponding weight region of the human eye is often larger. big. Therefore, the second face weight area and the third face weight area in the face image can be further determined, so that on the basis of obtaining richer human eye information, it is possible to take into account factors such as forehead, hair, cheeks, etc. Or the effect of facial factors in areas such as masks on image brightness.

Wherein, the first height threshold and the second height threshold may be determined according to actual scenarios. In some embodiments, the face image is divided into a plurality of first regions, in this case, the first height threshold and the second height threshold may be determined according to the height of the first region, for example The first height threshold may be the height of a first area, the second height threshold may be the height of a first area, etc., so as to facilitate subsequent determination of the first area belonging to the second face weight area and a first region belonging to the third face weight region. The third weight of the second face weight area and the fourth weight corresponding to the third face weight area may be determined according to the first weight, therefore, the third weight and the fourth weight may also be determined according to The first weight is dynamically adjusted to ensure the importance of the eye weight area, and at the same time, the second face weight area and the third face weight area can be taken into account.

As shown in FIG. 2 , it is an exemplary division manner of each weight region in the face image. The first face weight area is located below the human eye weight area and can be considered as the cheek weight area, and the second face weight area is located directly above the human eye weight area and can be considered as the forehead weight area area, the third face weight area is located directly above the second weight area, which can be considered as a hair weight area. At this time, the eye weight area, the first face weight area, the second face weight area, and the third face weight area may roughly include the main feature areas of the human face, and the weight area of each weight area may be determined dynamically weights to determine the importance of each weighted area respectively.

Wherein, exemplarily, the third weight may be 0.5 times the first weight, and the fourth weight may be 0.25 times the first weight, so as to ensure the importance of the human eye weight region, At the same time, the second face weight area and the third face weight area can be taken into consideration.

In some embodiments, the determining comprehensive luminance information according to the first weight, the second weight, the first luminance information and the second luminance information includes:

If the height of the human eye is not greater than the second preset height, determining a fifth weight of the second face weight region according to the first weight;

The comprehensive brightness information is determined according to the first weight, the second weight, the first brightness information, the second brightness information, the fifth weight and the third brightness information.

In the embodiment of the present application, if the height of the human eye is not greater than the second preset height, it can be considered that the area where the human eye is located in the human eye image is small and contains less details of the human eye, and the corresponding The human eye weight area also tends to be smaller. Therefore, the second face weight region in the face image and the fifth weight of the second face weight region can be further determined to reduce the influence of other face factors in the face except the human eye on the brightness of the image . Wherein, for example, the fifth weight may be 0.5 times the first weight.

In step S104, the target user is photographed according to the exposure parameter.

In the embodiment of the present application, the shooting manner of shooting the target user may be associated with the shooting manner of the face image. Exemplarily, in an application scenario, the target user may be a driver in a cab.

On the basis of the above embodiments, in some embodiments, the feature point information includes human eye feature point information and first facial feature point information;

After obtaining the face image, according to the feature point information in the face image, determine the human eye weight area and the first face weight area in the face image, including:

Step S301, after acquiring the face image, divide the face image into a plurality of first regions;

Step S302, according to the human eye feature point information, determine the first area belonging to the human eye weight area;

Step S303: Determine a first area belonging to the first face weight area according to the edge of the human eye weight area and the first facial feature point information.

In this embodiment of the present application, the first facial feature point information is associated with the first facial weight region. For example, if the first face weight area is a cheek weight area, the first facial feature point information includes cheek feature point information, for example, includes information such as coordinates of cheek edge feature points; If the partial weight area includes other areas in the face area except the eye weight area, the first facial feature point information may include face feature point information, for example, including the coordinates of the face edge feature points, etc. information. The number and size of the first regions may be determined according to the size of the face image, the size of the face region, and the like. Exemplarily, if the resolution of the face image may be 1920*1080, the number of the first regions may be K*P, wherein the resolution of each first region may be (1920/K )*(1080/P).

The human eye feature point information may include human eye edge feature point information, human eye center feature point information, and the like. According to the human eye feature point information, the first region belonging to the human eye weight region can be determined; of course, in some applications, it can also be based on the human eye feature point information and information such as face edge feature point information, etc., to determine the first region belonging to the human eye weight region.

In some embodiments, the human eye feature point information includes information of human eye center feature points and human eye edge feature points;

Determining the first region belonging to the human eye weight region according to the human eye feature point information includes:

Determine the height of the human eye according to the feature point information of the human eye;

Determine the distance threshold according to the relative positional relationship between the target camera and the human face and the height of the human eye, wherein the target camera is a camera that captures the face image;

Judging whether the central feature point of the human eye is located on the edge line of any first region;

If the central feature point of the human eye is located on the edge line of any first region, then according to the distance threshold and the first distance between each preset edge feature point and the central feature point of the human eye, determine the central feature point of the human eye. The edge of the human eye weight region, wherein the preset edge feature point includes at least one human eye edge feature point.

In the embodiment of the present application, the relative positional relationship between the target camera and the human face may affect the presentation effect of the human face part in the corresponding human face image. For example, if the target camera is installed on the left side of the subject such as the driver, if the face image obtained by the target camera shooting the subject has not been mirrored, the face in the face image is often will be close to the right side of the face image, and the face features in the right side of the face image are also more clear; and if the target camera captures the subject, the face image obtained has already been captured. Through mirror processing, the face in the face image tends to be close to the left side of the face image. On the other hand, if the target camera is installed on the right side of the person to be photographed, such as the driver, the situation is reversed.

Exemplarily, if the target camera is installed on the left side of the person being photographed, when determining the first area belonging to the weighted area of the human eye, the person can be determined by judging the location of the edge feature points of the human eye. An eye weight region, so that most of the left eye features or even all left eye features of the photographed subject can be obtained in the human eye weight region.

In addition, the height of the human eye may also roughly reflect the size of the area occupied by the human eye in the human face image and the number of details of the human eye contained therein. For example, if the height of the human eye is small, it can be considered that the area where the human eye is located in the human eye image is small, contains less details of the human eye, and the corresponding weight area of the human eye is often small, then By setting the distance threshold, the human eye weight region includes as many human eye features as possible. Therefore, the distance threshold can be determined according to the relative positional relationship between the target camera and the human face and the height of the human eye.

There may be one or more than two distance thresholds, and different distance thresholds may be used to compare with the first distances obtained in different directions. Exemplarily, the distance threshold may include an upper distance threshold, a lower distance threshold, a left distance threshold and a right distance threshold. The human eye edge feature points may include at least one of a human eye upper edge feature point, a human eye lower edge feature point, a human eye left edge feature point, and a human eye right edge feature point.

The preset edge feature points are used to determine the edge of the human eye weight region. Wherein, for example, if the upper edge and the lower edge of the human eye weight region are determined according to the upper edge and the lower edge of the human eye, the preset edge feature points may include the upper edge feature point of the human eye and the lower edge of the human eye. edge feature points; in addition, if the left edge and the right edge of the eye weight region are determined according to the cheek edge of the human face, the preset edge feature points may include the left edge feature point of the cheek and the right edge feature point of the cheek.

In the embodiment of the present application, each of the first distances is a distance between the corresponding preset edge feature point and the center feature point of the human eye. In some examples, a remainder of dividing the first distance by the height of the first region may be obtained, and the remainder may be compared with a corresponding distance threshold to determine the edge of the eye-weighted region, wherein , the human eye weight region may be composed of a first region, and therefore, the edge of the human eye weight region may coincide with the edge of a specific first region.

Exemplarily, an exemplary implementation manner of determining the edge of the human eye weight region is described below with a specific example.

In a specific example, if the height of the human eye is greater than a certain height threshold (for example, greater than the height of a first area) and the target camera is shooting a face, the distance threshold may be determined to be 0. That is to say, as shown in Figure 4(a), if the center feature point of the human eye is located on the edge line of any first region, then if the preset edge feature point includes the right edge feature point of the cheek and the cheek The left edge feature point, and the right edge feature point of the cheek and the left edge feature point of the cheek are respectively on the edge line of a certain first area, then the two edge lines can be used as the left edge and right edge of the human eye weight area ; The manner of determining the upper edge and the lower edge of the human eye weight region may be similar, and will not be described in detail here.

However, as shown in Figure 4(b), if there is a certain preset edge feature point (such as the right edge feature point of the cheek or the left edge feature point of the cheek) in a certain first area, it is determined that the first area is relatively A certain outer edge of the central feature point of the human eye is an edge of the human eye weight region. The manner of determining the upper edge and the lower edge of the human eye weight region may be similar, and will not be described in detail here.

In some embodiments, the photographing method further includes:

If the central feature point of the human eye is not located on the edge line of any first region, the first region where the central feature point of the human eye is located is determined as the core region, and it is determined whether there is an external edge feature point, wherein the The outer edge feature points are preset edge feature points located outside the core area;

If there is at least one external edge feature point, for each external edge feature point, obtain a second distance between the external edge feature point and the target edge, where the target edge is directed from the external edge feature point The first region edge closest to the outer edge feature point in the core region;

If the second distance is greater than the corresponding distance threshold, determine the edge of the human eye weight region according to the first region and the core region where the external edge feature points are located;

If the second distance is not greater than the corresponding distance threshold, the edge of the human eye weight region is determined according to the target edge and the core region.

Wherein, due to the relative positional relationship between the target camera and the human face, the rendering effect of the human face part in the corresponding human face image may be affected. For example, if the target camera is installed on the left side of the subject such as the driver, if the face image obtained by the target camera shooting the subject has not been mirrored, the face in the face image is often will be close to the right side of the face image, and the face features in the right side of the face image are also more and often clearer; and if the target camera captures the face obtained by the subject The image has been mirrored, so the face in the face image tends to be close to the left side of the face image. On the other hand, if the target camera is installed on the right side of the person to be photographed, such as the driver, the situation is reversed. Therefore, the distance threshold is determined according to the relative positional relationship between the target camera and the face and the height of the human eye, wherein the target camera is the camera that captures the face image, and the distance threshold can be determined according to the relative positional relationship and the human eye height. Eye height, adjust the distance thresholds in different directions, so that more abundant human eye information in a specific direction can be preserved in the human eye weight area.

An exemplary implementation manner of determining the edge of the human eye weight region is described below with a specific example.

In a specific example, if the height of the human eye is less than a certain height threshold (for example, less than the height of a first area) and the target camera shoots and mirrors the human face from the right side, the human eye is obtained. image, it can be determined that the right distance threshold in the distance thresholds is smaller, and the left distance threshold is larger, so that the information of the right face in the face image can be better obtained.

As shown in Figure 4(c), if the second distance corresponding to the feature point on the left edge of the cheek in the face image is smaller than the left distance threshold, the target edge located on the right side of the feature point on the left edge of the cheek is used as the The left edge of the weight area of the human eye, and the second distance corresponding to the feature point on the right edge of the cheek in the face image is greater than the right distance threshold, then the edge of the first region located on the right side of the feature point on the right edge of the cheek is used as the The right edge of the eye weight area. The manner of determining the upper edge and the lower edge of the human eye weight region may be similar, and will not be described in detail here.

In this embodiment of the present application, the distance threshold is determined according to the relative positional relationship between the target camera and the face and the height of the human eye, wherein the target camera is a camera that captures the face image, and the relative position can be used to determine the distance threshold. The face presentation mode in the face image corresponding to the relationship pre-judgment, so as to adjust the distance threshold according to the face presentation mode, so as to better determine the eye weight area, so as to obtain the following results. The brightness information of the human eye part that is more in line with the actual situation; in addition, the approximate region where the human eye is located in the human face image can be preliminarily evaluated according to the human eye height, so as to determine the human eye weight region.

Determine the first brightness value of the human eye weight region according to the regional brightness value of the first region included in the human eye weight region;

determining the second luminance value of the first face weighting area according to the area luminance value of the first area included in the first face weighting area;

The exposure parameter is determined according to the first weight, the second weight, the first brightness value and the second brightness value.

In the embodiment of the present application, exemplarily, the regional brightness value of the first region may include the mean brightness of each pixel in the first region, the median brightness of the pixel, the weighted value of the brightness of the pixel, etc. at least one of etc.

In some examples, the specific calculation methods of the regional luminance values corresponding to each of the first regions in the human eye weight regions may be different. For example, for any first region located at the edge of the human eye weight region, the weight of each pixel point in the first region can be determined according to the positions of the human eye edge feature points included in the first region, and then The weighted value of the brightness of the pixel points in the first area is calculated, so that the regional brightness value of the first area can better reflect the brightness of the part of the human eye included in the first area. Of course, the specific calculation method of the regional brightness value corresponding to each first region in the human eye weight region can also be the same, for example, the regional brightness value can be the corresponding pixel of each pixel in the first region. Average point brightness.

In the embodiment of the present application, by dividing the face image into a plurality of first regions, it is convenient to divide the eye weight region and the first face weight according to each first region and its edge. In addition, according to the regional pixel value of the corresponding first area, the first brightness value of the corresponding human eye weight area can be determined, and the first brightness value of the first face weight area can be determined. Two brightness values, and then determine the exposure parameters in combination with the dynamically determined first weight and second weight, so that the importance of the different weighted areas of the face and the brightness of the different weighted areas can be fully considered to determine the exposure parameters, avoiding the need for human eyes. The proportion of the human face is small, so that the exposure parameters during shooting are mainly determined according to other features in the face image, which makes the shooting quality of human eye details poor, so that according to the exposure parameters, When shooting the target user, the shooting quality of the details of the human eye can be improved.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Example 2

An embodiment of the present application provides a photographing apparatus, and the above photographing apparatus may be integrated into a terminal device.

FIG. 5 shows a structural block diagram of a photographing apparatus provided by an embodiment of the present application. For convenience of description, only parts related to the embodiment of the present application are shown.

5, the photographing device 5 includes:

The first determination module 501 is configured to determine the eye weight area and the first face weight area in the face image according to the feature point information in the face image after acquiring the face image;

A second determination module 502, configured to determine a first weight of the human eye weight region and a size of the first face weight region according to the size of the eye weight region and the size of the first face weight region the second weight;

The third determination module 503 is configured to determine exposure parameters according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area ;

The photographing module 504 is configured to photograph the target user according to the exposure parameter.

Optionally, the feature point information includes human eye feature point information and first facial feature point information;

The first determining module 501 includes:

a dividing unit, configured to divide the facial image into a plurality of first regions after acquiring the facial image;

a first determining unit, configured to determine a first region belonging to the human eye weight region according to the human eye feature point information;

A second determining unit, configured to determine a first area belonging to the first face weight area according to the edge of the human eye weight area and the first facial feature point information.

Optionally, the human eye feature point information includes the information of the human eye center feature point and the human eye edge feature point;

The first determining unit includes:

a first determination subunit, configured to determine the height of the human eye according to the information of the human eye feature point;

a second determination subunit, configured to determine a distance threshold according to the relative positional relationship between the target camera and the face and the height of the human eye, wherein the target camera is a camera that captures the face image;

A judging subunit for judging whether the central feature point of the human eye is located on the edge line of any first region;

The third determination subunit is configured to, if the central feature point of the human eye is located on the edge line of any first region, determine the difference between the central feature point of the human eye and the central feature point of the human eye according to the distance threshold and each preset edge feature point. and determine the edge of the human eye weight region, wherein the preset edge feature points include at least one human eye edge feature point.

Optionally, the photographing device 5 further includes:

The fourth determination module is used to determine that the first region where the central feature point of the human eye is located is the core region if the central feature point of the human eye is not located on the edge line of any first region, and determine whether there is an external edge feature points, wherein the external edge feature points are preset edge feature points located outside the core area;

The obtaining module is configured to, if there is at least one external edge feature point, for each external edge feature point, obtain the second distance between the external edge feature point and the target edge, wherein the target edge is from the When the outer edge feature point points to the core region, the first region edge closest to the outer edge feature point;

a fifth determination module, configured to determine the edge of the human eye weight region according to the first region and the core region where the external edge feature points are located if the second distance is greater than the corresponding distance threshold;

A sixth determination module, configured to determine the edge of the human eye weight region according to the target edge and the core region if the second distance is not greater than the corresponding distance threshold.

Optionally, the third determining module 503 includes:

a seventh determination module, configured to determine the first brightness value of the human eye weight region according to the regional brightness value of the first region included in the human eye weight region;

an eighth determination module, configured to determine a second brightness value of the first face weight region according to the regional brightness value of the first region included in the first face weight region;

A ninth determination module, configured to determine the exposure parameter according to the first weight, the second weight, the first brightness value and the second brightness value.

Optionally, the third determining module 503 includes:

a third determining unit, configured to determine comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information;

The fourth determining unit is configured to determine the exposure parameter according to the comprehensive brightness information.

Optionally, the first face weight area is located below the human eye weight area;

The third determining unit includes:

a fourth determination subunit, configured to determine the height of the human eye according to the human eye feature point information in the feature point information;

a fifth determination subunit, configured to use the area directly above the eye weight area and the height of which is the first height threshold as the second face weight area if the height of the human eye is greater than the second preset height, and Taking the area directly above the second face weight area and having a height of the second height threshold as the third face weight area;

a sixth determination subunit, configured to determine the third weight of the second face weight area and the fourth weight corresponding to the third face weight area according to the first weight;

A seventh determination subunit, configured to determine according to the first weight, the second weight, the first brightness information, the second brightness information, the third weight, the fourth weight, the first The third luminance information of the bi-face weighting area and the fourth luminance information of the third face weighting area determine the comprehensive luminance information.

Optionally, the seventh determination subunit is used for:

Optionally, the second determining module 502 is specifically configured to:

It should be noted that the information exchange, execution process and other contents between the above-mentioned devices/units are based on the same concept as the method embodiments of the present application. For specific functions and technical effects, please refer to the method embodiments section. It is not repeated here.

Example 3

FIG. 6 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As shown in FIG. 6 , the terminal device 6 in this embodiment includes: at least one processor 60 (only one is shown in FIG. 6 ), a memory 61 , and is stored in the above-mentioned memory 61 and can run on the above-mentioned at least one processor 60 The computer program 62, when the processor 60 executes the computer program 62, implements the steps in any of the foregoing shooting method embodiments.

The above-mentioned terminal device 6 may be a vehicle-mounted device, a server, a mobile phone, a wearable device, an augmented reality (AR)/virtual reality (virtual reality, VR) device, a desktop computer, a notebook, a desktop computer, a handheld computer and other computing devices. equipment. The terminal device may include, but is not limited to, a processor 60 and a memory 61 . Those skilled in the art can understand that FIG. 6 is only an example of the terminal device 6, and does not constitute a limitation on the terminal device 6, and may include more or less components than the one shown, or combine some components, or different components , for example, may also include input devices, output devices, network access devices, and so on. Wherein, the above-mentioned input devices may include keyboards, touchpads, fingerprint collection sensors (for collecting user's fingerprint information and fingerprint direction information), microphones, cameras, etc., and output devices may include displays, speakers, and the like.

The above-mentioned processor 60 may be a central processing unit (Central Processing Unit, CPU), and the processor 60 may also be other general-purpose processors, digital signal processors (Digital Signal Processors) Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The above-mentioned memory 61 may be an internal storage unit of the above-mentioned terminal device 6 in some embodiments, such as a hard disk or a memory of the terminal device 6 . The above-mentioned memory 61 may also be an external storage device of the above-mentioned terminal device 6 in other embodiments, such as a plug-in hard disk equipped on the above-mentioned terminal device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) , SD) card, flash memory card (Flash Card), etc. Further, the above-mentioned memory 61 may also include both the internal storage unit of the above-mentioned terminal device 6 and an external storage device. The above-mentioned memory 61 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, for example, program codes of the above-mentioned computer programs. The above-mentioned memory 61 can also be used to temporarily store data that has been output or is to be output.

In addition, although not shown, the above-mentioned terminal device 6 may also include a network connection module, such as a Bluetooth module, a Wi-Fi module, a cellular network module, etc., which will not be repeated here.

In the embodiment of the present application, when the processor 60 executes the computer program 62 to implement the steps in any of the above-mentioned shooting method embodiments, after acquiring the face image, according to the feature point information in the face image, The eye weight region and the first face weight region are determined in the face image, and at this time, the face image can be partitioned according to the feature point information. Then, according to the size of the eye weight area and the size of the first face weight area, determine the first weight of the eye weight area and the second weight of the first face weight area, and then according to The first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area, determine exposure parameters such that the first weight and The second weight can better reflect the importance of the corresponding weight area in the face image, so that the importance of the different weight areas of the face and the brightness of the different weight areas can be fully considered to determine the exposure parameters, to avoid The proportion of the human face is small, so that the exposure parameters during shooting are mainly determined according to other features in the face image, so that the shooting quality of the details of the human eye is poor, so that according to the exposure parameters, the When the target user is shooting, it can improve the shooting quality of human eye details.

Embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

The embodiments of the present application provide a computer program product, when the computer program product runs on a terminal device, so that the terminal device can implement the steps in the foregoing method embodiments when executed.

If the above-mentioned integrated units are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the methods of the above-mentioned embodiments, which can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program is in When executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code may be in the form of source code, object code form, executable file or some intermediate form. The above-mentioned computer-readable medium may include at least: any entity or device capable of carrying the computer program code to the photographing device/terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory ( RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. For example, U disk, mobile hard disk, disk or CD, etc. In some jurisdictions, under legislation and patent practice, computer readable media may not be electrical carrier signals and telecommunications signals.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed apparatus/device and method may be implemented in other manners. For example, the apparatus/equipment embodiments described above are only illustrative. For example, the division of the above modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components. May be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

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

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the above-mentioned embodiments, those of ordinary skill in the art should understand that the above-mentioned embodiments can still be used for The recorded technical solutions are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in this document. within the scope of protection of the application.

Claims

A method of shooting, comprising:

After acquiring the face image, determine the eye weight area and the first face weight area in the face image according to the feature point information in the face image;

According to the size of the human eye weight area and the size of the first face weight area, determine the first weight of the human eye weight area and the second weight of the first face weight area;

determining an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area;

According to the exposure parameters, the target user is photographed.
The shooting method according to claim 1, wherein the feature point information comprises human eye feature point information and first facial feature point information;

After obtaining the face image, according to the feature point information in the face image, determine the human eye weight area and the first face weight area in the face image, including:

After acquiring the face image, dividing the face image into a plurality of first regions;

According to the human eye feature point information, determine the first region belonging to the human eye weight region;

A first area belonging to the first face weight area is determined according to the edge of the human eye weight area and the first facial feature point information.
The photographing method according to claim 2, wherein the information on the feature points of the human eye includes the information of the center feature point of the human eye and the feature point of the edge of the human eye;

Determining the first region belonging to the human eye weight region according to the human eye feature point information includes:

Determine the height of the human eye according to the feature point information of the human eye;

Determine the distance threshold according to the relative positional relationship between the target camera and the human face and the height of the human eye, wherein the target camera is a camera that captures the face image;

Judging whether the central feature point of the human eye is located on the edge line of any first region;

If the central feature point of the human eye is located on the edge line of any first region, then according to the distance threshold and the first distance between each preset edge feature point and the central feature point of the human eye, determine the central feature point of the human eye. The edge of the human eye weight region, wherein the preset edge feature point includes at least one human eye edge feature point.
The photographing method of claim 3, further comprising:

If the central feature point of the human eye is not located on the edge line of any first region, the first region where the central feature point of the human eye is located is determined as the core region, and it is determined whether there is an external edge feature point, wherein the The outer edge feature points are preset edge feature points located outside the core area;

If there is at least one external edge feature point, for each external edge feature point, obtain a second distance between the external edge feature point and the target edge, where the target edge is directed from the external edge feature point The first region edge closest to the outer edge feature point in the core region;

If the second distance is greater than the corresponding distance threshold, determine the edge of the human eye weight region according to the first region and the core region where the external edge feature points are located;

If the second distance is not greater than the corresponding distance threshold, the edge of the human eye weight region is determined according to the target edge and the core region.
The shooting method according to claim 2, wherein the first weight, the second weight, the first brightness information of the human eye weight area, and the first face weight area The second brightness information determines exposure parameters, including:

Determine the first brightness value of the human eye weight region according to the regional brightness value of the first region included in the human eye weight region;

determining the second luminance value of the first face weighting area according to the area luminance value of the first area included in the first face weighting area;

The exposure parameter is determined according to the first weight, the second weight, the first brightness value and the second brightness value.
The photographing method according to claim 1, characterized in that, according to the first weight, the second weight, the first brightness information of the human eye weight area, and the first face weight area The second brightness information determines exposure parameters, including:

determining comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information;

The exposure parameter is determined according to the comprehensive brightness information.
The photographing method according to claim 6, wherein the first face weight area is located below the human eye weight area;

The determining of the comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information includes:

Determine the height of the human eye according to the feature point information of the human eye in the feature point information;

If the height of the human eye is greater than the second preset height, the area directly above the eye weight area and the height is the first height threshold is used as the second face weight area, and the area located in the second face weight area The area directly above the area and the height of which is the second height threshold is used as the third face weight area;

According to the first weight, determine the third weight of the second face weight area and the fourth weight corresponding to the third face weight area;

According to the first weight, the second weight, the first brightness information, the second brightness information, the third weight, the fourth weight, the third brightness of the second face weight area information and fourth luminance information of the third face weighting region to determine the comprehensive luminance information.
The shooting method according to claim 7, wherein the determining the comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information comprises:

If the height of the human eye is not greater than the second preset height, determining a fifth weight of the second face weight region according to the first weight;

The comprehensive brightness information is determined according to the first weight, the second weight, the first brightness information, the second brightness information, the fifth weight and the third brightness information.
The photographing method according to any one of claims 1 to 8, wherein, determining the size of the human eye weight region according to the size of the human eye weight region and the size of the first face weight region The first weight and the second weight of the first face weight region, including:

determining a first weight of the eye weight region and a second weight of the first face weight region such that the product of the first weight and the first area is the product of the second weight and the second area The ratio is greater than a preset ratio, wherein the first area is the area of the human eye weight region, and the second area is the area of the first face weight region.
A photographing device, comprising:

a first determination module, configured to determine a human eye weight area and a first face weight area in the face image according to the feature point information in the face image after acquiring the face image;

A second determination module, configured to determine the first weight of the eye weight region and the first weight of the first face weight region according to the size of the eye weight region and the size of the first face weight region two weights;

a third determining module, configured to determine an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area;

The photographing module is used for photographing the target user according to the exposure parameter.
A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the following steps when executing the computer program:

After acquiring the face image, determine the eye weight area and the first face weight area in the face image according to the feature point information in the face image;

According to the size of the human eye weight area and the size of the first face weight area, determine the first weight of the human eye weight area and the second weight of the first face weight area;

determining an exposure parameter according to the first weight, the second weight, the first brightness information of the human eye weight area, and the second brightness information of the first face weight area;

According to the exposure parameters, the target user is photographed.
The terminal device according to claim 11, wherein the feature point information comprises human eye feature point information and first facial feature point information;

When the processor executes the computer program, after acquiring the face image, according to the feature point information in the face image, determine the eye weight region and the first face in the face image Weighted area, including:

After acquiring the face image, dividing the face image into a plurality of first regions;

According to the human eye feature point information, determine the first region belonging to the human eye weight region;

A first area belonging to the first face weight area is determined according to the edge of the human eye weight area and the first facial feature point information.
The terminal device according to claim 12, wherein the feature point information of the human eye includes the information of the feature point of the center of the human eye and the feature point of the edge of the human eye;

When the processor executes the computer program, the determining, according to the human eye feature point information, the first region belonging to the human eye weight region includes:

Determine the height of the human eye according to the feature point information of the human eye;

Determine the distance threshold according to the relative positional relationship between the target camera and the human face and the height of the human eye, wherein the target camera is a camera that captures the face image;

Judging whether the central feature point of the human eye is located on the edge line of any first region;

If the central feature point of the human eye is located on the edge line of any first region, then according to the distance threshold and the first distance between each preset edge feature point and the central feature point of the human eye, determine the central feature point of the human eye. The edge of the human eye weight region, wherein the preset edge feature point includes at least one human eye edge feature point.
The terminal device according to claim 13, wherein when the processor executes the computer program, it further comprises:

If the central feature point of the human eye is not located on the edge line of any first region, the first region where the central feature point of the human eye is located is determined as the core region, and it is determined whether there is an external edge feature point, wherein the The outer edge feature points are preset edge feature points located outside the core area;

If there is at least one external edge feature point, for each external edge feature point, obtain a second distance between the external edge feature point and the target edge, where the target edge is directed from the external edge feature point The first region edge closest to the outer edge feature point in the core region;

If the second distance is greater than the corresponding distance threshold, determine the edge of the human eye weight region according to the first region and the core region where the external edge feature points are located;

If the second distance is not greater than the corresponding distance threshold, the edge of the human eye weight region is determined according to the target edge and the core region.
The terminal device according to claim 12, wherein when the processor executes the computer program, the first brightness according to the first weight, the second weight, and the human eye weight region information and the second brightness information of the first face weight area to determine exposure parameters, including:

Determine the first brightness information of the human eye weight region according to the regional brightness information of the first region included in the human eye weight region;

determining the second brightness information of the first face weighting region according to the regional brightness information of the first region included in the first face weighting region;

The exposure parameter is determined according to the first weight, the second weight, the first brightness information and the second brightness information.
The terminal device according to claim 11, wherein when the processor executes the computer program, the first brightness according to the first weight, the second weight, and the human eye weight region information and the second brightness information of the first face weight area to determine exposure parameters, including:

determining comprehensive brightness information according to the first weight, the second weight, the first brightness information and the second brightness information;

The exposure parameter is determined according to the comprehensive brightness information.
The terminal device according to claim 16, wherein when the processor executes the computer program, the first weight, the second weight, the first brightness information and the first Two brightness information, determine the comprehensive brightness information, including:

Determine the height of the human eye according to the feature point information of the human eye in the feature point information;

If the height of the human eye is greater than the second preset height, the area directly above the eye weight area and the height is the first height threshold is used as the second face weight area, and the area located in the second face weight area The area directly above the area and the height of which is the second height threshold is used as the third face weight area;

According to the first weight, determine the third weight of the second face weight area and the fourth weight corresponding to the third face weight area;

According to the first weight, the second weight, the first brightness information, the second brightness information, the third weight, the fourth weight, the third brightness of the second face weight area information and fourth luminance information of the third face weighting region to determine the comprehensive luminance information.
The terminal device according to claim 17, wherein when the processor executes the computer program, the first weight, the second weight, the first brightness information and the first Two brightness information, determine the comprehensive brightness information, including:

If the height of the human eye is not greater than the second preset height, determining the fifth weight of the second face weight region according to the first weight;

The integrated brightness information is determined according to the first weight, the second weight, the first brightness information, the second brightness information, the fifth weight and the third brightness information.
The terminal device according to any one of claims 11 to 18, wherein, when the processor executes the computer program, the size of the human eye weight region and the first face weight region , determine the first weight of the eye weight area and the second weight of the first face weight area, including:

determining a first weight of the eye weight region and a second weight of the first face weight region such that the product of the first weight and the first area and the product of the second weight and the second area The ratio is greater than a preset ratio, wherein the first area is the area of the human eye weight region, and the second area is the area of the first face weight region.
A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the shooting method according to any one of claims 1 to 9 is implemented.