WO2021023059A1

WO2021023059A1 - Photographing method and mobile terminal

Info

Publication number: WO2021023059A1
Application number: PCT/CN2020/105144
Authority: WO
Inventors: 戴同武; 勾军委
Original assignee: 华为技术有限公司
Priority date: 2019-08-07
Filing date: 2020-07-28
Publication date: 2021-02-11
Also published as: CN112351185A

Abstract

The present application is applicable to the technical field of terminals, and in particular, relates to an artificial intelligence (AI)-based photographing method and mobile terminal. The photographing method comprises: obtaining a first image corresponding to a first display region; identifying the target characteristic of a photography subject in the first image and the scene characteristic of a scene where the photography subject is located; obtaining, according to the target characteristic of the photography subject and the scene characteristic thereof, a posture image to be recommended, and displaying said posture image in a second display region to prompt the photography subject to adjust the posture according to the posture image displayed in the second display region; and photographing the photography subject to obtain a photographed image. The posture image is obtained according to the target characteristic of the photography subject and the scene characteristic thereof, which improves the accuracy and the effectiveness of posture image obtaining. Displaying the posture image in the second display region can make it convenient for the photography subject to adjust the posture or make it convenient for a photographer to guide the photography subject to adjust the posture, which improves the image capture effect.

Description

Photographing method and mobile terminal

This application claims the priority of a Chinese patent application filed with the State Intellectual Property Office on August 07, 2019, the application number is 201910727319.7, and the application name is "Photographing Method and Mobile Terminal", the entire content of which is incorporated into this application by reference.

Technical field

This application belongs to the field of terminal technology, and in particular relates to a photographing method and a mobile terminal based on artificial intelligence (AI) technology.

Background technique

With the continuous development of camera technology and the widespread popularity of mobile terminals, the camera function of mobile terminals is widely used. More and more users use mobile phones, tablet computers and other mobile terminals to take pictures, which greatly improves the convenience and convenience of taking pictures. Sex.

Existing mobile terminals can recognize the characteristics of the photographed object and/or the scene where the photographed object is located through intelligent recognition technology, so that the camera in the mobile terminal can be automatically adjusted according to the characteristics of the photographed object and/or the scene where the photographed object is located. The parameters of light and shadow, exposure, etc. can be used to obtain images with better imaging effects.

However, the existing mobile terminal that adjusts camera parameters based on the features recognized by the intelligent recognition technology can only beautify the subject and/or the shooting scene, but cannot change the shooting position and/or posture of the subject. In this way, when the user lacks photography skills, it is often difficult to obtain images that satisfy the subject, which affects the shooting effect.

Summary of the invention

The embodiments of the present application provide a photographing method and a mobile terminal, which can recommend a photographing position and/or photographing posture during the photographing process, thereby improving the photographing effect of an image.

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

Acquiring a first image corresponding to the first display area;

Identifying the target feature of the shooting object in the first image and the scene feature of the scene where the shooting object is located;

Obtain the posture image to be recommended according to the target feature of the subject and the scene feature of the scene in which the subject is located, and display the posture image in the second display area to prompt the subject according to the second Adjust the posture image displayed in the display area;

Taking a picture of the subject to obtain a photographed image.

It should be noted that the first image may be the first frame preview image previewed by the first display area, or the Nth frame preview image after the first frame, or the first frame image collected by the camera, or For the Nth frame image after the first frame, N is an integer greater than 1; the features of the subject include but are not limited to the facial features and physical features of the subject; the posture image to be recommended can be from the local or from Network access.

It should be understood that the recognizing the target feature of the shooting object in the first image and the scene feature of the scene where the shooting object is located may be using AI recognition technology and target detection technology to recognize the target of the shooting object in the first image Characteristics and scene characteristics of the scene where the subject is located.

In a possible implementation of the first aspect, the acquiring the posture image to be recommended according to the target feature of the shooting object and the scene feature of the scene in which the shooting object is located includes:

Acquiring at least one sample image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

A preset number of target sample images are selected from the sample images, and the selected target sample images are determined as the pose images to be recommended.

It should be understood that when the target sample image is selected from the sample images, the target sample image can also be selected in combination with the individual characteristics of the photographed object, where the personalized characteristic may be the preference of the photographic action set by the photographic object in advance. Features, which can also be photo features such as preferred photo actions based on the analysis of the subject’s behavior data. The selection of target sample images by combining the individual features of the subject can help improve the subject’s satisfaction with the posture image. , And help improve the user experience.

Optionally, the selecting a preset number of target sample images from the sample images includes:

Obtain the recommended value of each sample image, and select the first N sample images with high recommended value as the target sample image, where N is an integer greater than or equal to 1.

It should be understood that the recommended value of the sample image may be determined according to the number of historical recommendations of the sample image within a preset time, or may be determined according to the number of historical selections of the sample image by the user within the preset time, or according to the user’s The determination of personalized settings, for example, based on the preference tags set by the user, to recommend the posture image according to the recommended value, helps to improve the recommendation accuracy and recommendation efficiency of the posture image.

It should be noted that after a preset number of target sample images are selected, the target sample images can be sequentially displayed in the second display area as the posture images to be recommended, so that the subject or the photographer can be selected from the dynamically displayed posture images The target posture image used in the current photo is selected, and the target posture image can be fixedly displayed in the second display area for the posture reference of the subject in the current photo, thereby improving the satisfaction of image shooting and improving user experience.

For example, the display order of each posture image in the second display area can be determined according to the recommended value of each posture image. For example, the posture image with the higher the recommended value is displayed in the second display area first, and the lower the recommended value is. The posture image is later displayed in the second display area.

In a possible implementation manner of the first aspect, when there is a photographed subject in the first image, the at least one is acquired according to the target feature of the photographed object and the scene characteristic of the scene in which the photographed object is located. Sample images, including:

Determine the shooting category corresponding to the first image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

At least one sample image corresponding to the shooting category is acquired.

It should be noted that the shooting category may be a category classified according to scene characteristics and target characteristics, and each of the shooting categories may be correspondingly set with multiple sample images, that is, each of the shooting categories may be set with scene characteristics. Multiple sample images that match the scene features of the shooting category and the target features match the target features of the shooting category, so that the accuracy and efficiency of the sample image determination can be greatly improved through the setting of the shooting category, which helps Improve user experience.

In a possible implementation of the first aspect, when there are multiple photographed objects in the first image, the recognizing the target feature of the photographed object in the first image includes:

Identifying the target feature of each shooting object in the first image;

Correspondingly, the acquiring at least one sample image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located includes:

Determining the group characteristics of the multiple photographing objects in the first image according to the target characteristic of each photographing object;

At least one sample image is acquired according to the group characteristics and the scene characteristics.

It should be understood that if the photographing scene is a multi-person photographing scene, the target characteristic of each target object in the first image can be identified, and the multiple photographs in the first image can be determined according to the target characteristic of each photographed object. The group characteristics of the objects, where the group characteristics may include the total number of photographed objects, the proportions of different facial features, and/or the proportions of different physical features, etc.

Optionally, the acquiring at least one sample image according to the group characteristics and the scene characteristics includes:

According to the group feature and the scene feature, at least one sample image whose matching degree with the group feature and the scene feature is greater than a first threshold is acquired from a pre-stored sample image library.

It should be noted that, in a multi-person photographing scene, multiple sample images are stored in the sample image library, and each sample image is marked with a scene feature and a group feature corresponding to the sample image. Therefore, after obtaining the group characteristics and scene characteristics corresponding to the first image, the matching degree between the group characteristics corresponding to the first image and the group characteristics corresponding to each sample image can be calculated respectively, and the corresponding group characteristics of the first image can be calculated respectively. The matching degree between the scene feature and the scene feature corresponding to each sample image can then be determined according to the matching degree corresponding to each scene feature and the matching degree corresponding to each group feature. At least one sample image with a matching degree greater than a first threshold or the first M sample images with a high matching degree can be obtained, where M is an integer greater than or equal to, which is not limited in the embodiment of the application.

It should be understood that in a multi-person photographing scene, the posture adjustment may also include the adjustment of the position of each subject, that is, when the posture adjustment is performed, the height characteristics corresponding to each subject can also be obtained through AI recognition technology and image segmentation technology. And/or body shape characteristics, and/or facial shape characteristics, and the position adjustment method between each subject can be determined according to the height characteristics, and/or body shape characteristics, and/or facial characteristics of each subject to The position adjustment method is used to adjust the position between the photographed objects, so as to prevent the occurrence of occlusion in the multi-person photographing scene, which helps to improve the image shooting effect and helps to enhance the user experience.

In a possible implementation manner of the first aspect, the photographing the subject to obtain a photographed image includes:

After it is determined that the photographed object has adjusted its posture according to the posture image displayed in the second display area, the photographed object is photographed to obtain a photographed image.

It should be noted that, in order to ensure the image shooting effect, improve the satisfaction of image shooting, and improve user experience, the embodiment of the present application may adjust the shooting posture of the subject according to the posture image displayed in the second display area before shooting Subject takes pictures.

Optionally, the step of taking a picture of the photographing object to obtain a photographed image after determining that the photographing object performs posture adjustment according to the posture image displayed in the second display area includes:

Acquiring a second image corresponding to the first display area;

When the degree of matching between the second image and the posture image displayed in the second display area is greater than a second threshold, it is determined that the posture adjustment of the shooting object is completed, and the shooting object is photographed to obtain a photographed image.

It should be understood that in the process of adjusting the posture of the subject, the second image corresponding to the first display area can be acquired in real time. For example, the second image currently previewed in the first display area can be acquired, or the second image collected by the camera that will be in the first display area can be acquired. A second image displayed in a display area, and the second image can be compared with the posture image displayed in the second display area to determine whether the subject has adjusted the camera posture. If it is determined that the subject has adjusted the camera posture, Then you can take a picture of the subject; if it is determined that the subject has not adjusted the posture, the difference between the subject’s posture and the posture in the posture image can be identified based on the image comparison, and the subject can be prompted based on the difference Further adjustment of the shooting posture can be performed, for example, by means of voice prompts, text prompts, or action prompts to prompt the subject to further adjust the shooting posture, so as to further confirm and correct the shooting posture, improve the image shooting effect, and enhance the user experience.

In a possible implementation of the first aspect, after displaying the posture image in the second display area, the method further includes:

Acquire the prompt voice and/or prompt text corresponding to the posture image, and prompt the photographic subject to adjust the posture through the prompt voice and/or the prompt text.

It should be noted that after the posture image is acquired, the human body posture can be recognized and detected on the preset objects in the posture image through AI recognition technology and target detection technology, and the posture image can be generated based on the recognition and detection results. The corresponding prompt voice and/or prompt text, where the generated prompt voice and/or prompt text is mainly used to describe the specific posture of the preset object in the posture image, etc., therefore, when performing in the second display area When the gesture image is displayed, the prompt voice corresponding to the gesture image can also be played or the prompt text corresponding to the gesture image is displayed in the second display area or the first display area to assist in the prompt by combining the prompt voice and/or prompt text The posture adjustment of the subject is carried out to improve the speed and efficiency of posture adjustment.

In a possible implementation of the first aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a first display screen and a second display screen, and the display area of the first display screen is the first display area The display area of the second display screen is the second display area. When taking a picture, the first display area faces the photographer, and the second display area faces the photographic object.

In the embodiment of the present application, the posture image is displayed in the second display area facing the subject, so that the subject can directly view the posture image during the photographing process, so that the subject can directly adjust the posture according to the viewed posture image. Improve the efficiency of attitude adjustment.

It should be noted that when the mobile terminal includes a first display screen and a second display screen, the posture image can also be displayed in the first display area viewable by the photographer and the second display area viewable by the shooting object at the same time. It is convenient for the subject to directly adjust the posture based on the posture image, and it is also convenient for the photographer to assist in guiding the subject to adjust the posture according to the posture image displayed in the first display area, or to facilitate the photographer to understand the posture of the subject in real time Adjust the effect, thereby improving the efficiency of posture adjustment, improving the image shooting effect, and enhancing the user experience.

In another possible implementation of the first aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, the display area of the display screen is a first display area, and the second display area It is a partial display area of the first display area. When taking a picture, the first display area and the second display area face the photographer or the photographed object.

In a possible implementation of the first aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, and the first display area and the second display area are located in different display areas of the display screen When taking a picture, the first display area and the second display area face the photographer or the photographed object.

It should be noted that during the shooting process, the content displayed in the first display area and the second display area can also be exchanged. For example, the posture image displayed in the second display area can be switched to the first display area. Display, and can switch the first image displayed in the first display area to the second display area, so as to facilitate the photographer/or the subject to clearly view the first image or posture image.

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

An image acquisition module for acquiring a first image corresponding to the first display area;

The feature recognition module is configured to recognize the target feature of the shooting object in the first image and the scene feature of the scene where the shooting object is located;

The posture image recommendation module is used to obtain the posture image to be recommended according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located, and display the posture image in the second display area to prompt the The shooting object performs posture adjustment according to the posture image displayed in the second display area;

The photographing module is used to take a photograph of the photographed object to obtain a photographed image.

In a possible implementation of the second aspect, the posture image recommendation module includes:

A sample image acquisition unit, configured to acquire at least one sample image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

The posture image determining unit is configured to select a preset number of target sample images from the sample images, and determine the selected target sample image as the posture image to be recommended.

Optionally, the posture image determining unit is further configured to obtain the recommended value of each sample image, and select the first N sample images with high recommended value as the target sample image, and N is an integer greater than or equal to 1.

In a possible implementation of the second aspect, when there is a photographed subject in the first image, the sample image acquisition unit includes:

A shooting category determining subunit, configured to determine the shooting category corresponding to the first image according to the target feature of the shooting object and the scene feature of the scene in which the shooting object is located;

The sample image acquisition first subunit is configured to acquire at least one sample image corresponding to the shooting category.

In another possible implementation manner of the second aspect, when there are multiple shooting objects in the first image, the feature recognition module is further configured to identify the target of each shooting object in the first image feature;

Correspondingly, the sample image acquisition unit further includes:

A group feature determining subunit, configured to determine the group feature of the multiple shooting objects in the first image according to the target feature of each shooting object;

The second subunit for acquiring sample images is configured to acquire at least one sample image according to the group characteristics and the scene characteristics.

Optionally, the sample image acquiring second subunit is specifically configured to acquire the degree of matching with the group feature and the scene feature from a pre-stored sample image library according to the group feature and the scene feature At least one sample image greater than the first threshold.

In a possible implementation manner of the second aspect, the photographing module includes:

The posture adjustment determining unit is configured to take a picture of the subject to obtain a photographed image after it is determined that the subject is adjusted according to the posture image displayed in the second display area.

Optionally, the posture adjustment determining unit includes:

An image acquisition subunit for acquiring a second image corresponding to the first display area;

The photographing subunit is used to determine that the posture adjustment of the photographing object is completed when the degree of matching between the second image and the posture image displayed in the second display area is greater than a second threshold, and to take a picture of the photographing object to obtain Take pictures.

Optionally, the photographing device further includes:

The prompt module is used to obtain the prompt voice and/or prompt text corresponding to the posture image, and prompt the photographic subject to adjust the posture through the prompt voice and/or the prompt text.

In a possible implementation of the second aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a first display screen and a second display screen, and the display area of the first display screen is the first display Area, the display area of the second display screen is the second display area. When taking a picture, the first display area faces the photographer, and the second display area faces the photographic object.

In another possible implementation of the second aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, the display area of the display screen is a first display area, and the second display area It is a partial display area of the first display area. When taking a picture, the first display area and the second display area face the photographer or the photographed object.

In a possible implementation of the second aspect, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, and the first display area and the second display area are located in different display areas of the display screen When taking a picture, the first display area and the second display area face the photographer or the photographed object.

In the third aspect, an embodiment of the present application provides a terminal device including a display screen, a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor executes the computer The program enables the mobile terminal to implement the photographing method according to any one of the above-mentioned first aspects.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the implementation is as described in any of the above-mentioned first aspects. The photographing method described.

In a fifth aspect, embodiments of the present application provide a computer program product, which when the computer program product runs on a terminal device, causes the terminal device to execute the photographing method described in any one of the above-mentioned first aspects.

Compared with the prior art, the embodiments of this application have the following beneficial effects:

In the embodiment of the present application, the first image corresponding to the first display area is acquired; the target feature of the shooting object in the first image and the scene feature of the scene where the shooting object is located are recognized; according to the target feature of the shooting object and the scene where the shooting object is located According to the scene characteristics, the posture image to be recommended is acquired, and the posture image is displayed in the second display area to prompt the subject to adjust the posture according to the posture image displayed in the second display area; take a picture of the subject to obtain a photographed image. The embodiment of the application obtains the posture image by combining the target feature of the shooting object and the scene feature, which can improve the accuracy and effectiveness of the posture image acquisition, and display the posture image in the second display area, thereby facilitating shooting The object directly adjusts the posture according to the displayed posture image, or it is convenient for the photographer to guide the object to perform posture adjustment according to the displayed posture image, which effectively improves the image shooting effect and enhances the user experience.

Description of the drawings

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

FIG. 1 is a schematic structural diagram of a mobile phone to which the photographing method provided by an embodiment of the present application is applicable;

2 is an example diagram of a single-screen mobile phone to which the photographing method provided in an embodiment of the present application is applicable;

FIG. 3 is an example diagram of a folding screen mobile phone to which the photographing method provided by an embodiment of the present application is applicable;

Figure 4 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of previewing a first image in a photographing method provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of displaying a posture image in a second display area in the photographing method provided by an embodiment of the present application;

FIG. 7 is a schematic diagram of displaying a posture image in a second display area in a photographing method according to another embodiment of the present application;

FIG. 8 is a schematic diagram of displaying a posture image in a second display area in a photographing method according to another embodiment of the present application;

FIG. 9 is a schematic diagram of an application scenario provided by another embodiment of the present application;

FIG. 10 is a schematic diagram of an application scenario provided by another embodiment of the present application;

FIG. 11 is a schematic diagram of a photographing method provided by an embodiment of the present application for determining station position adjustment;

FIG. 12 is a schematic diagram of a photographing method provided by an embodiment of the present application instructing station position adjustment through image instructions;

FIG. 13 is a schematic flowchart of a photographing method provided by an embodiment of the present application;

FIG. 14 is a schematic structural diagram of a photographing device provided by an embodiment of the present application;

FIG. 15 is a schematic structural diagram of a mobile terminal provided by an embodiment of the present application.

detailed description

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of this application.

It should be understood that when used in the specification and appended claims of this application, the term "comprising" indicates the existence of the described features, wholes, steps, operations, elements and/or components, but does not exclude one or more other The existence or addition of features, wholes, steps, operations, elements, components, and/or collections thereof.

It should also be understood that the term "and/or" used in the specification and appended claims of this application refers to any combination of one or more of the items listed in the associated and all possible combinations, and includes these combinations.

As used in the description of this application and the appended claims, the term "if" can be construed as "when" or "once" or "in response to determination" or "in response to detecting ". Similarly, the phrase "if determined" or "if detected [described condition or event]" can be interpreted as meaning "once determined" or "response to determination" or "once detected [described condition or event]" depending on the context ]" or "in response to detection of [condition or event described]".

In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

The reference to "one embodiment" or "some embodiments" described in the specification of this application means that one or more embodiments of this application include a specific feature, structure, or characteristic described in combination with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless it is specifically emphasized otherwise. The terms "including", "including", "having" and their variations all mean "including but not limited to" unless otherwise specifically emphasized.

The photographing method provided in the embodiments of this application can be applied to mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR)/virtual reality (VR) devices, notebook computers, and super mobile personal computers ( For mobile terminals such as ultra-mobile personal computer (UMPC), netbooks, and personal digital assistant (personal digital assistant, PDA), the embodiments of this application do not impose any restrictions on the specific types of mobile terminals.

Take the mobile terminal as an example of a mobile phone. Fig. 1 shows a block diagram of a part of the structure of a mobile phone provided by an embodiment of the present application. 1, the mobile phone includes: a memory 110, an input unit 120, a display unit 130, a sensor 140, an audio circuit 150, a processor 160, a power supply 170, a camera 180 and other components. Those skilled in the art can understand that the structure of the mobile phone shown in FIG. 1 does not constitute a limitation on the mobile phone, and may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements.

The following is a detailed introduction to each component of the mobile phone in conjunction with Figure 1:

The memory 110 can be used to store software programs and modules. The processor 160 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 110. The memory 110 may mainly include a storage program area and a storage data area. The storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data (such as audio data, phone book, etc.) created by the use of mobile phones. In addition, the memory 110 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

The input unit 120 may be used to receive inputted digital or character information, and generate key signal input related to user settings and function control of the mobile phone 100. Specifically, the input unit 120 may include a touch panel 121 and other input devices 122. The touch panel 121, also called a touch screen, can collect user touch operations on or near it (for example, the user uses any suitable objects or accessories such as fingers, stylus, etc.) on the touch panel 121 or near the touch panel 121. Operation), and drive the corresponding connection device according to the preset program. Optionally, the touch panel 121 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch position, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it To the processor 160, and can receive and execute commands from the processor 160. In addition, the touch panel 121 can be implemented in multiple types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 121, the input unit 120 may also include other input devices 122. Specifically, other input devices 122 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackball, mouse, joystick, and the like.

The display unit 130 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 130 may include a display panel 131. Optionally, the display panel 131 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 121 can cover the display panel 131. When the touch panel 121 detects a touch operation on or near it, it transmits it to the processor 160 to determine the type of the touch event, and then the processor 160 responds to the touch event. The type provides corresponding visual output on the display panel 131. Although in FIG. 1, the touch panel 121 and the display panel 131 are used as two independent components to implement the input and input functions of the mobile phone, in some embodiments, the touch panel 121 and the display panel 131 may be integrated. Realize the input and output functions of mobile phones.

In some embodiments, the display unit 130 may include 1 or N display screens, and N is a positive integer greater than 1. In some embodiments, when the display panel uses OLED, AMOLED, FLED and other materials, the above-mentioned display screen may be bent. Here, the above-mentioned display screen can be bent means that the display screen can be bent at any position along any axis to any angle, and can be maintained at that angle, for example, the display screen can be folded in half from the middle. You can also fold up and down from the middle. In the embodiments of the present application, the bent display screen may be referred to as a folding screen. Wherein, the folding screen may be one screen, or a display screen formed by patching together multiple screens, which is not limited here. The display screen can also be a flexible screen, which has the characteristics of strong flexibility and bendability, and can provide users with a new interactive mode based on bendable characteristics, which can meet more needs of users for folding screen mobile phones. For a mobile phone equipped with a folding screen, the folding screen on the mobile phone can be switched between the small screen in the folded form and the large screen in the expanded form at any time.

In some embodiments, the display unit 130 may include a primary display and a secondary display. The primary and secondary displays are parallel and run independently of each other. The primary display is set on one side of the mobile phone, and the secondary display is set on the other side of the mobile phone. side. It is understandable that under normal circumstances, the main display screen and the sub display screen are two parallel surfaces. When the main display screen and the sub display screen are in a parallel relationship, an angle between the sub display screen and the horizontal ground is generated. The angle between the main display screen of the double-sided screen mobile phone and the horizontal plane is equal or complementary. The double-sided screen mobile phone can detect the angle between the main display of the double-sided screen mobile phone and the horizontal plane by means such as a gravity sensor. Understandably, the main display screen in the double-sided screen mobile phone is the main display device and is the most frequently used screen, while the secondary display screen is only used as an auxiliary screen and its use frequency is low. However, the main display and the secondary display are not strictly distinguished. The user can set one screen as the primary display (or secondary display) under different usage scenarios, and the other screen will automatically be set as the secondary display (Or the main display).

The mobile phone 100 may also include at least one sensor 140, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 131 according to the brightness of the ambient light. The proximity sensor can close the display panel 131 and/or when the mobile phone is moved to the ear. Or backlight. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (usually three-axis), and can detect the magnitude and direction of gravity when stationary, and can be used to identify mobile phone posture applications (such as horizontal and vertical screen switching, related Games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, percussion), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which can be configured in mobile phones, we will not here Repeat.

The audio circuit 150, the speaker 151, and the microphone 152 can provide an audio interface between the user and the mobile phone. The audio circuit 150 can transmit the electric signal converted from the received audio data to the speaker 151, which is converted into a sound signal for output by the speaker 151; on the other hand, the microphone 152 converts the collected sound signal into an electric signal, and the audio circuit 150 After being received, it is converted into audio data, and then processed by the audio data output processor 160, and sent to, for example, another mobile phone, or the audio data is output to the memory 110 for further processing.

The processor 160 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. It executes by running or executing software programs and/or modules stored in the memory 110, and calling data stored in the memory 110. Various functions and processing data of the mobile phone can be used to monitor the mobile phone as a whole. Optionally, the processor 160 may include one or more processing units; preferably, the processor 160 may integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, and application programs, etc. , The modem processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 160.

The mobile phone 100 also includes a power source 170 (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the processor 170 through a power management system, so that functions such as charging, discharging, and power management are realized through the power management system.

The mobile phone 100 may also include a camera 180. Optionally, the position of the camera 180 on the mobile phone 100 may be front or rear, which is not limited in the embodiment of the present application.

The camera 180 can obtain the optical image generated by the photographed object, and can convert the optical image into an electrical signal, and then the electrical signal can be converted into a digital signal through analog-to-digital conversion, and then the digital signal can be processed by the digital signal processor DSP The processed digital signal can be sent to the processor 160 for processing, and finally converted into an image that can be seen in the display unit 130.

Optionally, the mobile phone 100 may include a single camera, a dual camera, or a triple camera, etc., which is not limited in the embodiment of the present application.

For example, the mobile phone 100 may include three cameras, of which one is a main camera, one is a wide-angle camera, and one is a telephoto camera.

Optionally, when the mobile phone 100 includes multiple cameras, the multiple cameras may be all front-mounted, or all rear-mounted, or partly front-mounted and another part rear-mounted, which is not limited in the embodiment of the present application.

In addition, although not shown, the mobile phone 100 may also include a Bluetooth module, etc., which will not be repeated here.

In order to describe the technical solution of the present application more clearly, the photographing method provided in the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings and application scenarios. As an example and not a limitation, the photographing method can be applied to the mobile phone 100 described above.

scene one

This scene can be a single-person photo-taking scene. The photo-taking method in this scene can be applied to single-sided screen phones, double-sided screen phones or folding screen phones, among which, single-sided screen phones can also be folding screen phones. The single-screen mobile phone formed after unfolding, the single-screen mobile phone, double-sided mobile phone or folding screen mobile phone includes a first display area 20 and a second display area 21.

For example, when the photographing method is applied to a single-sided screen mobile phone as shown in FIG. 2, the display screen of the single-sided screen mobile phone may include a first display area 20 for previewing a first image and a second display area 21 for displaying a posture image. , And the first display area 20 and the second display area 21 both face the photographer or both face the subject.

It should be understood that the positions and sizes of the first display area 20 and the second display area 21 shown in FIG. 2 are only for schematic explanation, and should not be construed as limiting the embodiments of the present application. In the embodiment of the present application, both the first display area 20 and the second display area 21 can be located at any position in the display screen of a single-screen mobile phone. For example, the first display area 20 and the second display area 21 can be located in a single-screen mobile phone. The different display areas in the display screen, that is, the display areas of the first display area 20 and the second display area 21 do not overlap; for another example, the first display area 20 may be the entire display area of the mobile phone display with a single screen, and the second display The area 21 may be a part of the display area of the first display area 20, that is, the display areas of the first display area 20 and the second display area 21 may overlap.

It should be understood that during the photographing process, the content displayed in the first display area 20 and the second display area 21 can also be exchanged. For example, the posture image displayed in the second display area 21 can be switched to the first display. It is displayed in the area 20, and the first image displayed in the first display area 20 can be switched to be displayed in the second display area 21, so as to facilitate the photographer/or subject to clearly view the first image or the posture image.

For example, when the photographing method is applied to a double-sided screen mobile phone, the double-sided screen mobile phone may use the display area of the main display screen as the first display area 20 and the display area of the secondary display screen as the second display area 21. When taking a photo, the first display area 20 can face the photographer to serve as the operator's operating terminal, and the second display area 21 can face the subject for viewing the posture image, so that the subject can directly follow the 2. The posture image displayed in the display area 21 undergoes posture adjustment to improve posture adjustment efficiency.

For example, when the photographing method is applied to a folding screen mobile phone as shown in Figure 3, the folding screen can adopt an integrated flexible display, or two rigid screens and a flexible screen located between the two rigid screens. The composed display screen. The folding screen may include: a first screen, a second screen, and a bendable area connecting the first screen and the second screen. When the folding screen of the mobile phone is in the folded state, the display area of the first screen may be used as the first display area 20, and the display area of the second screen may be used as the second display area 21. Wherein, the folding state can be fully folded, that is, the angle between the first screen and the second screen is 0 degrees (the actual angle may not reach 0 degrees, depending on the actual angle reported by the mobile phone sensor), or it can be partially folded , That is, the angle between the first screen and the second screen is greater than 0 degrees and less than 180 degrees. As shown in FIG. 4, in the photographing of a folding screen mobile phone, the first display area 20 may face the photographer to serve as the operator's operating terminal, and the second display area 21 may face the photographed subject for the photographic subject to perform posture images. View.

Specifically, as shown in FIG. 5 and FIG. 6, when taking a picture, the processor of the mobile phone can obtain the first image corresponding to the first display area 20, and can recognize the first image through AI recognition technology to obtain the recognition As a result, the recognition result is used to indicate whether there is a subject in the first image, and to indicate the target feature of the subject when the subject is present, and to indicate the scene feature of the scene where the subject is located when the subject is present . If there is a photographed subject in the first image, obtain the posture image to be recommended according to the identified target feature of the subject and the scene feature, and display the posture image in the second display area 21 to prompt the subject The posture adjustment is performed according to the posture image, and after the posture adjustment of the subject is prompted, the subject can be photographed to obtain the photographed image. Wherein, the target feature of the subject may include the facial feature and/or physical feature of the subject, and the scene feature may include the scene type, such as beach/beach scene, forest scene, field scene, grass scene, desert scene, mountain peak Scenes, ocean scenes, lake/pond scenes, snow scenes, blue sky scenes, etc. The embodiment of the present application obtains the posture image by combining the target feature of the shooting object and the scene feature, which can improve the accuracy and effectiveness of the posture image acquisition, and displays the posture image through the second display area 21, so that the shooting object can directly The posture adjustment is performed according to the displayed posture image or it is convenient for the photographer to guide the subject to perform posture adjustment according to the displayed posture image, which effectively improves the image shooting effect and enhances the user experience.

It should be understood that the mobile phone can set up a camera mode for acquiring posture images for shooting in advance for the user to choose. When taking a photo, if the user selects the camera mode, the first image obtained can be recognized during the shooting process, and according to The recognition result displays the posture image in the second display area 21 of the mobile phone to prompt the subject to adjust the posture according to the displayed posture image; if the user does not select the photographing mode, the normal photographing process can be directly performed.

Optionally, the mobile phone can start the camera according to the detected camera start instruction, and can preview the image collected by the camera in real time through the first display area of the mobile phone. Correspondingly, the user can start the camera in the mobile phone by inputting a camera start instruction, where the camera start instruction can be an instruction that triggers the generation of a preset button, or an instruction that triggers the generation of a preset gesture, or it can be a pre-trigger. It is assumed that the voice keyword generation instruction is not limited in the embodiment of the present application.

For example, the mobile phone can be preset to generate a camera start instruction when the "volume +" button is triggered twice, or to generate a camera start instruction when the "volume +" button and the "volume -" button are triggered simultaneously, then when the user presses +" button twice, or when the user presses the "volume +" button and the "volume -" button at the same time, the phone can generate and obtain the camera start instruction. For another example, the mobile phone can be preset to generate a camera start instruction when a preset gesture such as an "O" gesture is collected, and when the user inputs a gesture that matches the preset gesture such as an "O" gesture, the mobile phone can Generate and get the camera start instruction. For example, the mobile phone can be preset to generate a camera start instruction when a preset voice keyword such as "photograph" is detected, and then when the user input voice contains a preset voice keyword such as "photograph", the mobile phone can generate And get the camera start instruction.

Optionally, the mobile phone may obtain a first image corresponding to the first display area according to a trigger event or a preset duration, where obtaining the first image corresponding to the first display area may be obtained by obtaining a preview of the first display area The image can also be the image captured by the camera in real time, that is, the camera can send the image captured in real time to the first display area of the mobile phone for preview, and can also send the image to the processor of the mobile phone as The first image corresponding to the first display area acquired by the processor of the mobile phone is not limited in the embodiment of the present application.

It should be understood that the preset duration described in the embodiments of the present application can be understood as a duration preset in the mobile phone.

Optionally, the mobile phone may obtain the image currently previewed in the first display area or the image currently captured by the camera according to the detected specific instruction, and may determine the currently previewed image or the currently captured image as the first image.

For example, the mobile phone can acquire the image currently previewed by the first display area or the image currently collected by the camera when detecting that the user clicks on any position of the first display area.

Optionally, the mobile phone can obtain the image currently previewed in the first display area or the image currently collected by the camera when the camera startup time reaches the preset time length, and can use the currently previewed image or the currently collected image Determined to be the first image.

For example, a timer or a timer can be preset in the mobile phone, and the timer or the timer can be started after the camera is started, and the duration of the timer or the timer is the preset duration (for example, 7 seconds). When the timer expires or when the timer reaches 7 seconds, the image currently previewed in the first display area or the image currently collected by the camera is obtained.

Optionally, in this embodiment of the present application, a scene recognition model may be constructed in the mobile phone in advance, so as to recognize the scene features in the first image through the scene recognition model.

In a possible implementation, the scene recognition model may be a convolutional neural network model based on a residual network (Residual Neural Network, ResNet) architecture, and the convolutional neural network can be obtained by training based on a scene database. The specific construction process and specific training process of the scene recognition model are not limited, and the existing construction process can be used for construction, or the existing training process can be used for training.

Specifically, after the scene recognition model receives the first image, it can first perform preprocessing such as information conversion, denoising, smoothing, and transformation on the first image to enhance the important features of the image; then image segmentation technology can be used , Such as using the image instance segmentation technology (Mask Region-based Convolutional Neural Networks, Mask RCNN) to perform target detection and segmentation on the preprocessed first image to obtain the foreground and background parts of the first image; then the background can be Part of the feature extraction and selection are performed, and scene features such as the scene type corresponding to the first image are identified by analyzing the selected features.

Optionally, when the target feature of the photographed subject includes the facial feature of the photographed subject, the embodiment of the present application may also construct a facial feature recognition model in the mobile phone in advance, so as to recognize the facial feature recognition model through the facial feature recognition model. The facial features of the subject in the first image.

Specifically, the facial feature recognition model may be a multi-task convolutional neural network model (Multi-task Convolutioanl Neural Networks, MTCNN). This embodiment does not limit the specific construction process and specific training process of MTCNN, and the existing The construction process can be used for construction, or the existing training process can be used for training.

It should be noted that the facial features recognized by the facial feature recognition model may include age features, gender features, facial features, expression features, and so on.

Specifically, after the facial feature recognition model receives the first image, it can first perform preprocessing such as information conversion, denoising, smoothing, and transformation on the first image to enhance the important features of the image; then, it can sample people The face recognition technology performs face recognition on the preprocessed first image to obtain the face block diagram and the key point coordinates of the facial features in the first image; then the face block diagram can be placed in the face block diagram according to the coordinates of the key points of the facial features Align the faces of, and perform feature extraction and analysis on the aligned faces to identify the facial features in the first image. Among them, aligning the face in the face block diagram according to the coordinates of the key points of the facial features of the face may be performing operations such as rotating, scaling, and extracting the face in the face block diagram according to the coordinates of the key points of the facial features of the face. The face is adjusted to a predetermined size and shape.

Optionally, when the target feature of the photographed object includes the physical characteristic of the photographed object, the embodiment of the present application may also construct a body recognition model in the mobile phone in advance, so as to recognize the photograph in the first image through the body recognition model The physical characteristics of the object.

Specifically, the shape recognition model may be a dense human pose evaluation model DensePose Region-based Convolutional Neural Networks, DensePose RCNN). The embodiment of this application does not limit the specific construction process and specific training process of DensePose RCNN, and the existing construction can be adopted. The process is constructed, or the existing training process can be used for training.

Specifically, after the shape recognition model receives the first image, it can first perform preprocessing such as information conversion, denoising, smoothing, and transformation on the first image to enhance the important features of the image; Convolutional Neural Networks (Region-based Convolutional Neural Networks, RCNN) or Faster Region-based Convolutional Neural Networks (Faster RCNN) or YOLO algorithm (You only look once, YOLO) can perform target detection on the first image, The subject in the first image is detected; then the human body posture feature can be extracted for the subject, and the physical feature of the subject in the first image can be identified according to the extracted human posture feature. Among them, the recognized physical characteristics may include height characteristics, body shape characteristics, and the like.

Optionally, the embodiment of the present application may also construct a pose recommendation model in the mobile phone in advance, and the pose recommendation model may obtain the pose image to be recommended according to scene features and target features (ie, facial features and/or body features) to By comprehensively considering scene features and target features (ie, facial features and/or physical features) to obtain accurate and effective posture images to assist and guide the subject to shoot, improve image shooting effects and enhance user experience.

In a possible implementation, the pose recommendation model may first obtain at least one sample image according to the target feature of the subject and the scene feature of the scene in which the subject is located, and select a preset number of target samples from the sample images Image, and the selected target sample image is determined as the posture image to be recommended.

Specifically, the pose recommendation model may first obtain the recommended value of each sample image, then select the top N sample images with high recommended values as the target sample images, and determine the selected N target sample images as the ones to be recommended The pose image, where N is an integer greater than or equal to 1, to recommend the pose image through the recommended value, which helps to improve the recommendation accuracy and recommendation efficiency of the pose image.

In a possible implementation, the pose recommendation model may first determine the shooting category corresponding to the first image according to the scene features and the target features (face features and/or the physical features); then, the shooting category can be obtained. Each sample image corresponding to the category, and a preset number of target sample images can be selected from these sample images, and each selected target sample image can be determined as the posture image to be recommended. The setting of the shooting category can greatly improve The accuracy and efficiency of sample image determination improves user experience.

It should be noted that in this pose recommendation model, multiple preset shooting categories can be set according to scene characteristics and target characteristics (ie, facial features and/or physical characteristics). For example, the grassy girlfriend category can be set according to scene characteristics and physical characteristics. And the high grass boyfriend category, for example, you can set the beach aesthetic category and the beach funny category according to the scene characteristics, facial features, and physical characteristics, and so on. Each preset shooting category can be configured with multiple sample images with better shooting effects and good postures, and the multiple sample images in each preset shooting category have scene characteristics that match the scene characteristics of the shooting category , And a sample image whose target feature matches the target feature of the shooting category. Therefore, after the posture recommendation model receives the scene feature and the facial feature and/or the physical feature, it can determine the shooting corresponding to the first image by matching the scene feature and the facial feature and/or the physical feature Category, that is, determining which preset shooting category is the shooting category corresponding to the first image.

It should be understood that the preset shooting categories and shooting categories are both based on the scene characteristics and target features (ie facial features and/or physical features) jointly determined categories, that is, the preset shooting categories and shooting categories are based on the scene features and target features (Ie, facial features and/or physical features) are classified into categories, so if any feature is different, the determined shooting category may also be different. Specifically, when the shooting category is jointly determined by scene features and facial features, for two first images with the same scene features but different facial features, the determined two shooting categories may be different, so the recommended pose The images may also be different. For example, when subject A and subject B are both taking pictures on the grass, the shooting category determined according to subject A and the grass scene can be the grass girl category, and the shooting is determined according to subject B and the grass scene The category can be a boyfriend category with tall grass. Therefore, for the subject A, a pose image will be obtained from the category of a small girlfriend on the grass for recommendation, and for the subject B, a pose image will be obtained from the category of boyfriend with a tall grass for recommendation. For another example, when the subject C is taking pictures on the grass and the beach respectively, the shooting category determined according to the subject C and the grass scene can be the grass little girlfriend category, and the shooting category is determined according to the subject C and the beach scene It can be a beach aesthetic category. Therefore, when the subject C is taking a photo on the grass, the pose image will be obtained from the grass little girlfriend category for recommendation, and for the subject C when taking a photo on the beach, the pose image will be obtained from the beach aesthetic category. recommend.

It should be understood that when the shooting category is jointly determined by scene features and physical features or when the shooting category is jointly determined by scene features and facial features and physical features, if the scene features are different or if the facial features are not the same or if the physical features are not the same At the same time, the determined shooting category may also be different, and the recommended posture image may also be different. The specific content is similar to the above description, and will not be repeated here.

That is to say, in the embodiment of the present application, when the same subject is photographed in different scenes, the determined shooting category may be different, and the recommended posture images may also be different. Similarly, when different subjects are in the same When taking pictures in the scene, the determined shooting categories may also be different, and the recommended posture images may also be different.

Here, the pose recommendation model can be classified through classifier design or classification decision, where the classifier design is to obtain a recognition rule through training, and perform classification through the recognition rule. Classification decision is to classify the recognized objects in the feature space.

For example, the scene feature and the first feature vector corresponding to the facial feature and/or the physical feature can be constructed first, and the scene features and facial features and/or physical features corresponding to each preset shooting category can be constructed respectively. Then, the matching degree between the first feature vector and each second feature vector is calculated respectively, and the shooting category to which the first image belongs is determined according to the matching degree.

Optionally, after the posture recommendation model determines the shooting category to which the first image belongs, it can acquire sample images corresponding to the shooting category, and select a preset number of target sample images from the sample images as the target sample images to be recommended Posture image.

In a possible implementation manner, the pose recommendation model can determine the pose image according to the recommended value of each sample image, so as to improve the recommendation accuracy and recommendation efficiency of the pose image.

Optionally, the recommended value corresponding to each sample image can be determined according to the number of historical recommendations of each sample image within a preset time. For example, it can be determined according to the number of historical recommendations of each sample image in the past week. The more recommended number of sample images, the higher the corresponding recommendation value; the smaller the number of historical recommendations, the lower the corresponding recommendation value.

Optionally, the recommended value corresponding to each sample image can also be determined according to the number of historical selections of each sample image by the mobile phone user within a preset time. For example, it can be determined based on the mobile phone user’s selection of each sample image in the past month. The number of historical selections is determined. The sample image with more historical selections has a higher recommended value; and the sample image with fewer historical selections has a lower recommended value.

Optionally, the recommended value corresponding to each sample image can also be determined according to the personalized settings of the mobile phone user. For example, when the mobile phone user uses a photographing gesture in a sample image in the previous photographing process, When the camera pose is favorited or the favorite tag is set for the camera pose, the recommended value corresponding to the sample image is correspondingly higher. Accordingly, if the mobile phone user deletes the favorite camera pose or changes a certain camera pose When the dislike label is set, the recommended value corresponding to the sample image is correspondingly lower.

Optionally, the mobile phone user can also pre-set a preset number of posture images recommended each time in the mobile phone, and the posture recommendation model can output the preset number of posture images for photo selection each time to satisfy the user’s requirements. Recommend willingness to improve user experience.

For example, when the mobile phone user selects the camera mode for capturing posture images for shooting, an input box can pop up in the mobile phone, and the mobile phone user can enter the recommended preset number each time (for example, 10 ), in each photo process, the pose recommendation model can output 10 pose images for photo selection.

It should be understood that the embodiment of the present application can also set the preset number recommended each time by default, for example, the preset number recommended each time can be set to 15 by default, when the mobile phone user has not set the preset number , The posture recommendation model can output posture images according to the preset number of default settings, such as outputting 15 posture images each time for photo selection.

Specifically, after the pose recommendation model obtains each sample image corresponding to the shooting category, it can further obtain the recommended value corresponding to each sample image, and can select a preset number of target sample images according to the recommended value as the target sample image to be recommended Posture image.

For example, after the posture recommendation model obtains the recommended value corresponding to each sample image, it can first arrange the sample images in descending order according to the recommended value to obtain a descending sort group. In the descending order group, the sample image with the higher the recommended value The higher the ranking, and the lower the recommended value of the sample images, the lower the ranking; then, the top N target sample images with the highest ranking can be selected from the descending order group, and the selected top N The target sample image is determined as the posture image to be recommended.

Optionally, when determining the posture image, the posture recommendation model can also be determined in conjunction with the individual characteristics of the subject, where the individual characteristics can be the subject’s preference for photographing actions and other photographic features, or In order to analyze the preferred photographing actions and other photographing features based on the behavior data of the photographed subject, for example, the photographic behavior data of the photographed subject can be searched for, the picture collection behavior data, the picture browsing behavior data and/or the historical photographed image of the photographed subject itself. The data is analyzed to obtain personalized features such as the subject's preference for taking pictures.

It should be understood that when the photographed object has a personalized feature, the posture recommendation model can firstly find a sample image matching the personalized feature from the sample images after acquiring each sample image corresponding to the shooting category, and then The recommended value corresponding to the found sample images is obtained, a preset number of target sample images can be selected according to the recommended value, and each target sample image is determined as the posture image to be recommended.

Optionally, the pose recommendation model may be a convolutional neural network model obtained by collecting a large number of training images for labeling learning.

Specifically, first collect the first training image and the second training image, and mark the preset shooting category corresponding to each first training image; secondly, identify the training scene characteristics of the training scene where the preset object is located in each first training image And the training facial features and/or training physical features of the preset object; subsequently, the training scene features and the training facial features and/or training physical features corresponding to each first training image are input to the initial posture recommendation model, respectively. Determine the training shooting category corresponding to each first training image through the initial posture recommendation model, and calculate the training error according to the training shooting category and the preset shooting category corresponding to each first training image; if the training error does not meet the preset Condition, adjust the model parameters of the posture recommendation model, and determine the posture recommendation model after adjusting the model parameters as the initial posture recommendation model, and return to execute the training scene feature corresponding to each first training image and the training face feature and/ Or the training body features are input to the initial posture recommendation model to determine the steps and subsequent steps of the training shooting category corresponding to each first training image through the initial posture recommendation model; if the training error meets the preset conditions, the posture recommendation model is determined The training is completed, and the trained posture recommendation model is used to classify each second training image into a corresponding preset shooting category, as a sample image corresponding to each preset shooting category. Wherein, the second training image and the first training image are both images with better shooting effect and good posture in a single-person photographing scene, and the second training image may include the first training image.

It should be understood that the sample image corresponding to each preset shooting category can not only include the corresponding second training image. In the embodiment of the present application, the image can also be crawled from the network in real time, and the crawled image Perform detection and analysis to determine whether the crawled image is a single-person scene image with good shooting effect and good posture. If so, the crawled image can be classified into the corresponding preset shooting category, that is, through the network Crawl to supplement the sample images of each preset shooting category, improve the diversity of posture image recommendation, and improve user experience.

Optionally, the posture recommendation model can also integrate the functions of a scene recognition model, a facial feature recognition model, and/or a body recognition model, and the first image can be directly input to the posture recommendation model, and the posture recommendation model is Scene recognition and facial feature recognition and/or physical feature recognition can be directly performed on the first image, so that the posture image to be recommended can be obtained directly according to the recognized scene feature, facial feature and/or physical feature.

For example, the pose recommendation model may be a convolutional neural network model based on Mask RCNN and face recognition technology. Specifically, after the posture recommendation model receives the first image, it can first perform preprocessing such as information conversion, denoising, smoothing, and transformation on the first image to enhance the important features of the image; then, Mask RCNN can be used to The preprocessed first image is subjected to target detection, target segmentation, and human body posture recognition, etc., to obtain the background part in the first image, the photographed object existing in the first image, and the human body posture feature corresponding to the photographed object; Subsequently, the background part can be extracted and selected, and the selected features can be analyzed to identify the scene features corresponding to the first image. At the same time, the facial recognition technology can also be used to capture the first image. The object performs face detection to obtain the facial features corresponding to the first image; finally, the shape features in the first image can be obtained according to the human body posture feature, and the convolutional neural network can be used to obtain the scene feature and the facial feature And/or the physical feature determines the shooting category corresponding to the first image, so that the posture image to be recommended can be obtained according to the sample image corresponding to the shooting category.

It should be understood that each sample image may be an image collected and stored in the mobile phone in advance or stored in a cloud server connected to the mobile phone, or it may be an image captured from the network in real time during the photographing process. For example, the When the pose recommendation model performs target detection on the first image, it can also crawl images from the network through technologies such as web crawlers, and can perform target detection and analysis on the captured images, so as to realize real-time detection and analysis based on the detection and analysis results. The crawled images are classified into corresponding preset shooting categories, and used as sample images corresponding to the preset shooting categories.

Optionally, after obtaining the posture image to be recommended, the posture image can be displayed in the second display area of the mobile phone, and the posture image can be displayed to the subject or to the photographer, so that the subject can directly follow The posture image performs posture adjustment or it is convenient for the photographer to guide the subject to perform posture adjustment according to the posture image, thereby improving the image shooting effect and enhancing the user experience.

Specifically, in a double-sided screen mobile phone and a folding screen mobile phone in a folded state, after the posture image to be recommended is obtained, the posture image can also be displayed in the first display area viewable by the photographer and the subject viewable The second display area is convenient for the subject to directly adjust the posture according to the posture image, and it is also convenient for the photographer to assist in guiding the posture adjustment of the subject according to the posture image displayed in the first display area, or It is convenient for the photographer to understand the posture adjustment effect of the subject in real time, thereby improving the posture adjustment efficiency, improving the image shooting effect, and enhancing the user experience.

Optionally, after acquiring a plurality of posture images to be recommended, the display order corresponding to each posture image can be determined, and the posture images are sequentially displayed in the second display area according to the display order, so as to improve the effect of posture recommendation. It is convenient for the subject to quickly find a satisfactory recommended posture and enhance the user experience.

Specifically, the display sequence corresponding to each posture image can be determined according to the recommended value corresponding to each posture image, wherein the posture image with the larger the recommended value is displayed in the second display area first, and the posture with the smaller recommended value The image is later displayed in the second display area.

Optionally, when each posture image is displayed in the second display area, the recommended value corresponding to each posture image can also be displayed, so that it is convenient for the subject and/or the photographer to select the posture image according to the recommended value, and enhance the user Experience. Among them, the recommended value can be a specific value as shown in Figure 6, or a recommended index, such as a 5-star (★★★★★) recommendation index, a 4-star (★★★★) recommendation index, 3 Star (★★★) recommendation index and so on.

Optionally, after acquiring each posture image, AI recognition technology and target detection technology can also be used to recognize and detect the human body posture of the preset objects in each posture image, and each posture image can be generated according to the recognition and detection results The corresponding prompt voice and/or prompt text, wherein each generated prompt voice and/or each prompt text is mainly used to describe the specific posture of the preset object in the corresponding posture image.

Specifically, when the posture image is displayed in the second display area, the voice device such as the microphone in the mobile phone can also be used to play the prompt voice corresponding to the posture image, so as to combine the prompt voice to assist in prompting the subject to proceed. Posture adjustment to improve the speed and efficiency of posture adjustment. When the posture image is displayed in the second display area, the prompt text corresponding to the posture image can also be displayed in the second display area or the first display area, so that the subject can be combined with the displayed prompt The posture adjustment can be carried out by text, or the photographer can assist in guiding the subject to adjust the posture according to the displayed prompt text, thereby improving the speed and efficiency of posture adjustment.

Optionally, in the process of displaying the posture image, the subject or the photographer can select the posture image, that is, the subject or the photographer can select the desired posture image of the target from the multiple posture images. , The posture image of the target can be fixedly displayed in the second display area for the posture reference of the photographed object, which improves the satisfaction of image shooting and improves user experience.

For example, as shown in FIG. 7, the central position of the second display area can dynamically display posture images in the display order, and the edge position of the second display area can provide an "OK" or "OK" button for shooting The subject or the photographer selects the posture image, that is, during the display of a certain posture image, if the "OK" or "OK" button is triggered, the center position of the second display area will be The posture image is fixedly displayed to prompt the subject to adjust the posture according to the posture image.

As shown in FIG. 7, the edge position of the second display area can also provide buttons such as "up" and "down" to facilitate viewing the previous posture image or the next posture image, and improve user experience.

It should be understood that in the embodiments of the present application, the previous posture image or the next posture image can also be viewed by swiping to the left or swiping to the right. For example, the previous posture image can be viewed by swiping to the left. A posture image, swipe right to view the next image, or swipe left to view the next posture image, swipe right to view the previous image, or you can The previous posture image or the next posture image can be viewed through the upward swipe operation and the downward swipe operation, which is not limited in the embodiment of the present application.

Optionally, as shown in FIG. 8, in a double-sided screen mobile phone or a folding screen mobile phone in a folded state, the central position of the second display area can also be divided into two parts. The first part 81 is used to display the recommended For the posture image, the display content of the second part 82 can be the same as the display content in the first display area, that is, the second part 82 can be used to display the image corresponding to the current posture of the subject, so as to facilitate the subject to compare the two Right to adjust your camera posture and improve posture adjustment efficiency.

Optionally, after prompting the photographed subject to adjust the photographing posture according to the posture image in the second display area, the processor of the mobile phone can issue a photographing instruction to control the camera to take a photograph of the photographed object to obtain a photographed image.

In a possible implementation manner, the mobile phone may also take a picture of the photographed object to obtain a photographed image after determining that the photographed object has adjusted its posture according to the posture image displayed in the second display area.

Specifically, the mobile phone can determine whether the subject has adjusted his posture according to whether the voice confirmation instruction issued by the subject has been received, and can also determine whether the subject has adjusted himself according to whether the posture adjustment period reaches the preset adjustment period. The camera posture of the camera is not limited in the embodiment of this application.

For example, in automatic shooting without the photographer's operation, if the subject makes a voice that contains keywords such as "OK" or "adjusted" during the posture adjustment process, the mobile phone can confirm that it has received the subject's voice Voice confirmation instruction, at this time, the processor of the mobile phone can issue a photographing instruction to control the camera to take a picture and obtain a photographed image. For another example, after the subject selects the target posture image, the timer in the mobile phone can be started in time to calculate the adjustment duration, and when the counted duration reaches the preset adjustment duration of 30 seconds, the mobile phone can confirm the subject The camera posture has been adjusted, and the processor of the mobile phone can now issue a camera command to control the camera to take a photo.

It should be understood that the mobile phone may also control the camera to take a picture of the subject after receiving the photographing instruction from the photographer to obtain the photographed image, that is, the photographer may send the photographing instruction to the mobile phone according to the adjustment of the posture image of the photographed object. The camera can then be controlled to take pictures of the subject according to the photographing instruction.

For example, when the photographer determines that the posture of the subject is adjusted, the photographer can click the camera button in the mobile phone or trigger a voice command to send a camera command to the mobile phone, and the mobile phone can control the camera to take a photo according to the camera command. Take pictures.

In a possible implementation manner, to determine whether the subject has adjusted its own photographing posture can be determined according to the degree of matching between the second image and the posture image during the posture adjustment process. Specifically, the Display the second image corresponding to the area, and recognize the current photographing posture of the subject in the second image and the target photographing posture of the preset object in the selected target posture image through AI recognition technology, and then calculate the current photographing posture and The degree of matching between the target's camera posture; if the degree of matching is less than the first threshold, it can be considered that the subject has not adjusted the camera posture. At this time, the difference between the current camera posture and the target camera posture can be determined , And prompt the subject to adjust the photographing posture according to the distinguished position until the matching degree between the adjusted current photographing posture and the target photographing posture is greater than or equal to the first threshold. When the degree of matching between the adjusted current camera posture and the target camera posture is greater than or equal to the first threshold, it is determined that the subject has adjusted the camera posture. At this time, the camera can be controlled to take a photo to obtain a photo image to pass the matching The calculation of the degree to further realize the confirmation and correction of the photographing posture can improve the effect of image shooting and enhance the user experience.

Optionally, the histogram HistA of the current photographing posture and the histogram HistB of the target photographing posture can be calculated first, and then the normalized correlation coefficient between HistA and HistB, or the Bhattacharyya distance, or the histogram intersection distance can be calculated , Etc., so that the matching degree between the current camera pose and the target camera pose can be determined according to the normalized correlation coefficient or the Bhattacharyya distance, or the intersection distance of the histogram, and when the calculated matching degree is less than At the first threshold, the difference between the current photographing posture and the target’s photographing posture can be found by comparing histograms, so that the photographic subject can be prompted to adjust the posture according to the different position, for example, it can be played by voice The method prompts the subject to adjust the posture and/or the manner of text display can be used to prompt the subject to adjust the posture.

It should be understood that the determination of the matching degree between the current photographing posture and the target photographing posture by calculating the normalized correlation coefficients between the histograms described above is only an example and not a limitation, and the embodiment of the present application may also Other methods such as matrix decomposition are used to determine the degree of matching between the current camera posture and the target camera posture.

Optionally, after calculating the matching degree between the current photographing posture and the target photographing posture, the matching degree can also be displayed in the first display area and/or the second display area in real time, so that the object can be photographed and /Or the photographer clearly understands the specific fit between the photographing posture of the subject and the posture image.

Scene two

This scene can be a scene where many people take a group photo. The photographing method in this scene can be applied to a single-sided screen mobile phone as shown in Figure 2, or can be applied to a double-sided screen mobile phone as shown in Figure 3. Among the folding screen mobile phones, the single screen mobile phone may also be a single screen mobile phone formed after the folding screen mobile phone is unfolded.

For example, when the photographing method is applied to a double-sided screen mobile phone or a folding screen mobile phone, both the double-sided screen mobile phone and the folding screen mobile phone in the folded state may include a first display area 20 and a second display area 21. At this time, the first display area 20 can face the photographer to serve as the photographer’s operating terminal, and the second display area 21 can face the subject for viewing the posture image of the subject, so that the subject can directly follow the second display The image displayed in the area 21 undergoes posture adjustment to improve posture adjustment efficiency.

As shown in Figures 2 and 9, when the photographing method is applied to a single-sided screen mobile phone, the display screen of the single-sided screen mobile phone may include a first display area 20 and a second display area 21, and the first display area 20 and The second display areas 21 all face the photographer or both face the subject.

It should be understood that the positions and sizes of the first display area 20 and the second display area 21 shown in FIG. 2 and FIG. 9 are only for schematic explanation and should not be construed as limiting the embodiments of the present application. In the embodiments of the present application, Both the first display area 20 and the second display area 21 can be located at any position in the display screen of a mobile phone with a single screen. For example, the positions of the first display area 20 and the second display area 21 can also be as shown in FIG. 10 position. In addition, during the photographing process, the content displayed in the first display area 20 and the second display area 21 can also be exchanged. For example, the posture image displayed in the second display area 21 can be switched to the first display area. 20, and the first image previewed in the first display area 20 can be switched to the second display area 21 for display, so as to facilitate the photographer/or subject to clearly view the first image or the posture image.

For this scenario, when taking a picture, the processor of the mobile phone can obtain the first image corresponding to the first display area 20, and can recognize the first image through AI recognition technology to obtain the recognition result, which is used for Indicate whether there is a photographed object in the first image, and indicate the target feature of the photographed object when the photographed object exists, and indicate the scene characteristic of the scene where the photographed object is located when the photographed object exists. If there is a subject in the first image, the posture image to be recommended is acquired according to the identified target feature and scene feature of the subject, and the posture image is displayed in the second display area to prompt the subject to follow the posture The posture adjustment of the image is performed, and after the posture adjustment of the subject is prompted, the subject can be photographed to obtain the photographed image. Wherein, the target feature of the subject may include the facial feature of the subject and/or the physical feature of the subject, and the scene feature may include the scene type, such as beach/beach scene, forest scene, field scene, grass scene, Desert scene, mountain peak scene, ocean scene, lake/pond scene, snow scene, blue sky scene, etc. The embodiment of the application obtains the posture image by combining the target feature of the shooting object and the scene feature, which can improve the accuracy and effectiveness of the posture image acquisition, and displays the posture image through the second display area, so that the shooting object can directly follow The displayed posture image directly performs posture adjustment, or it is convenient for the photographer to guide the subject to perform posture adjustment according to the displayed posture image, so as to improve the image shooting effect and enhance the user experience.

The difference between this scene and scene one is that the identified objects in the scene can include multiple, that is, the target features corresponding to the multiple objects in the first image (that is, facial features and/or shapes can be identified). Feature), and when acquiring the posture image to be recommended according to the scene feature and the target feature (ie, facial feature and/or physical feature), the target feature corresponding to the multiple shooting objects (ie, facial feature and/or Or physical characteristics) perform statistical analysis to obtain the group characteristics in the first image, where the group characteristics may include the total number of photographed objects, the proportion of different facial features, and/or the proportion of different physical characteristics, etc., For example, when the facial features include facial features, the group features may include the proportion of fat faces, thin faces, etc. among the multiple subjects, or may include the proportion of round faces among the subjects. , The proportion of square faces, the proportion of melon seeds, etc. For another example, when the facial features include gender features, the group features may include the proportion of women and the proportion of men among the multiple photographed subjects. For example, when the facial features include age characteristics, the group characteristics may include the proportion of young people, the proportion of teenagers, the proportion of middle-aged people, and the proportion of old people among the multiple subjects. Similarly, when the physical characteristics include body characteristics, the group characteristics may include the proportions of different body types among the multiple photographed objects, and when the physical characteristics include height characteristics, the group characteristics may also include the multiple photographed objects. The proportion of different height ranges and so on. Subsequently, the posture image to be recommended can be obtained according to the scene characteristics and the group characteristics, wherein the recommended posture image can include the cardioid alignment, V-shape alignment, and alignment corresponding to the preset objects in the posture image. The co-op formation of simple stances, etc., for example, the posture image shown in Figure 9 can be determined based on the scene characteristics of the campus scene where the subject is located in the first image, the number of subjects, and the age of the subjects. Displayed in the second display area.

It should be understood that in a double-sided screen mobile phone and a folding screen mobile phone in a folded state, after the posture image to be recommended is obtained, the posture image can also be displayed in the first display area viewable by the photographer and the viewable object by the photographer. The second display area, on the basis of facilitating the posture adjustment of the subject directly according to the posture image, can also facilitate the photographer to assist in guiding the posture adjustment of the subject according to the posture image displayed in the first display area, or it can be convenient The photographer understands the position adjustment effect of the subject in real time, thereby improving the posture adjustment efficiency, improving the image shooting effect, and enhancing the user experience.

In a possible implementation manner, after obtaining the scene feature and the group feature corresponding to the first image, at least one sample image can be obtained according to the scene feature and the group feature, and a preset number of target samples can be selected from the sample image Image, and the selected target sample image is determined as the posture image to be recommended.

Specifically, the scene feature and group feature corresponding to the first image can be matched with the scene feature and group feature corresponding to each sample image in the sample image library to obtain a match between the first image and each sample image According to the matching degree, obtain multiple sample images from the sample image library, and then select N target sample images from the multiple sample images, and determine the selected N target sample images as the pose to be recommended For example, multiple sample images with matching degrees greater than a first threshold can be obtained from a sample image library, and N target sample images can be selected from the multiple sample images according to the recommended value of each sample image, and the selected The N target sample images of are determined to be posture images to be recommended, where N is an integer greater than or equal to 1.

For example, the first feature vector corresponding to the scene feature and the group feature of the first image can be constructed first, and the second feature vector corresponding to the scene feature and the group feature of each sample image in the sample image library can be constructed respectively, and then the second feature vectors corresponding to The matching degree between the first feature vector and each second feature vector, so that multiple sample images can be obtained from the sample image library according to the matching degree, and N target sample images can be selected according to the recommended value corresponding to each sample image As the posture image to be recommended.

For example, before calculating the degree of matching between the first image and each sample image, the first weight corresponding to the scene feature and the second weight corresponding to the group feature can be preset according to the importance of the scene feature and the group feature. Therefore, in the calculation When the first image is matched with each sample image, the first feature vector corresponding to the scene feature and group feature of the first image can be constructed first, and the first feature vector corresponding to the scene feature and group feature of each second sample image can be constructed respectively. Two feature vectors, and then calculate the matching degree between the first feature vector and each second feature vector according to the first weight corresponding to the scene feature and the second weight corresponding to the group feature, so that the matching degree can be obtained from the sample image library A plurality of sample images are obtained, and N target sample images can be selected as the posture images to be recommended according to the recommended value corresponding to each sample image.

It should be understood that, in the embodiments of the present application, each feature included in the group feature can be set to a unified second weight, or can be set to a different second weight according to the importance of each feature.

It should be understood that in the embodiment of the present application, the target sample image can also be directly selected from the sample image library according to the matching degree. For example, the first M sample images with high matching degree can be selected from the sample image library as the target sample image. Optionally, in the embodiment of the present application, a pre-built pose recommendation model may also be used to obtain the pose image. For example, the recognized scene feature and group feature may be input into the pose recommendation model, and the pose recommendation model That is, the recommended posture image can be obtained according to the scene characteristics and the group characteristics.

Specifically, the pose recommendation model may first determine the shooting category corresponding to the first image according to the scene characteristics and the group characteristics; then, each sample image corresponding to the shooting category may be obtained, and the preset images may be selected from the sample images. Set a number of target sample images, and determine each selected target sample image as the posture image. That is, the co-op formation corresponding to the preset object in each target sample image can be output to the subject to remind the subject to follow the co-photograph Formation to adjust the photo posture, where the photo posture adjustment can include the adjustment of the camera position and/or the adjustment of the camera action, etc., to comprehensively recommend the best co-op formation to guide each shooting based on the scene characteristics and group characteristics The subject performs photographing actions and/or adjustment of the photographing station to improve the image shooting effect in the co-photographing and enhance the user experience.

Specifically, first collect the first training image and the second training image, where the first training image and the second training image are both images in a co-photographed scene, and mark the preset shooting category corresponding to each first training image; , Identify the training scene features of the training scene where the preset objects are located in each first training image and the training facial features and/or training physical features of each preset object, and compare the recognized training facial features and/or each Perform statistical analysis on the training body features to obtain the training group features in each first training image; then, respectively input the training scene features and training group features corresponding to each first training image to the initial posture recommendation model to pass the initial The posture recommendation model determines the training shooting category corresponding to each first training image, and calculates the training error according to the training shooting type and the preset shooting category corresponding to each first training image; if the training error does not meet the preset conditions, adjust The model parameters of the posture recommendation model, and the posture recommendation model adjusted by the model parameters is determined as the initial posture recommendation model, and return to execution. Input the training scene features and training group features corresponding to each first training image to the initial posture recommendation. The model is used to determine the steps and subsequent steps of the training shooting category corresponding to each first training image through the initial pose recommendation model; if the training error meets the preset conditions, it is determined that the training of the pose recommendation model is completed, and the trained pose recommendation is used The model classifies each second training image into a corresponding preset shooting category as a sample image corresponding to each preset shooting category. Wherein, the second training image may include the first training image, and each second training image is an image with a better shooting effect in a co-production scene and a good co-production formation.

It should be understood that the sample image corresponding to each preset shooting category can not only include the corresponding second training image. In the embodiment of the present application, the image can also be crawled from the network in real time, and the crawled image Perform detection and analysis to determine whether the crawled image is a co-photographed scene image with a better shooting effect and a better co-production formation. If so, the crawled image can be classified into the corresponding preset shooting category to pass Web crawling supplements the sample images of each preset shooting category, improves the diversity of posture image recommendation, and improves user experience.

Optionally, the pose recommendation model may first construct a first feature vector corresponding to the scene feature and the group feature, and respectively construct a second feature vector corresponding to the scene feature and the group feature in each preset shooting category, and then The matching degree between the first feature vector and each second feature vector is calculated respectively, and the shooting category to which the first image belongs is determined according to the matching degree.

Specifically, the pose recommendation model may first construct the first feature vector corresponding to the scene feature and the group feature, and respectively construct the second feature vector corresponding to the scene feature and the group feature in each preset shooting category, and then according to The first weight corresponding to the scene feature and the second weight corresponding to the group feature respectively calculate the matching degree between the first feature vector and each second feature vector, and determine the shooting category to which the first image belongs according to the matching degree.

Optionally, after determining the shooting category to which the first image belongs, a preset number of target sample images in the shooting category can be acquired, and each target sample image can be determined as the posture image to be recommended and displayed on the double-sided screen mobile phone Or in the second display area of the folding screen mobile phone for the subject to view the posture image, so that the subject can directly adjust his own photographing action and/or photographing position according to the posture image to improve the posture adjustment efficiency.

Optionally, after determining the shooting category to which the first image belongs, a preset number of target sample images in the shooting category can be acquired, and each target sample image can be determined as the posture image to be recommended and displayed on the single-screen mobile phone In the second display area, the photographer can guide the subject to adjust the photographing posture according to the posture image.

It should be understood that the preset number and acquisition method corresponding to the target sample images in the scene are similar to the preset number and acquisition method corresponding to the target sample images in scene 1, and the basic principles are the same, and will not be repeated here.

In a possible implementation manner, after determining that each subject has adjusted the photographing posture, the second image currently corresponding to the first display area can be acquired first, and the second image can be identified through AI recognition technology and image segmentation technology. Each subject in the image and the height feature, and/or body shape feature, and/or face feature corresponding to each subject; subsequently, the height feature between the subjects can be compared, and/or the height feature between the subjects can be compared. Body shape features and/or facial features between subjects are compared to obtain the corresponding comparison results, and based on the comparison results, it is determined whether the subject needs to be adjusted in position, if the subject does not need to be positioned To adjust, perform the photographing operation to obtain the photographed image; if the position adjustment of the photographed subject is needed, the position adjustment method is determined according to the comparison result, and the position adjustment between the photographed objects is carried out according to the position adjustment method , So as to prevent the occurrence of occlusion in the co-production scene, improve the image shooting effect, and enhance the user experience.

It should be understood that the above-mentioned acquiring the height features, and/or body shape features, and/or facial features corresponding to each shooting object may be acquiring the height features corresponding to each shooting object, or acquiring the body shape characteristics corresponding to each shooting object, or Obtain the facial features corresponding to each subject, or obtain the height and body features corresponding to each subject, or obtain the height and facial features corresponding to each subject, or the body and facial features corresponding to each subject , Or obtain the height feature, body shape feature, and face shape feature corresponding to each subject.

Specifically, the stance adjustment method can be determined according to the comparison result of the height characteristics. The stance adjustment method at this time is mainly to adjust the taller subject to the rear row farther from the camera to ensure the front and rear rows There will be no occlusion between the subjects in between, thus improving the image capture effect.

For example, if it is determined according to the comparison result between the height features that the first photographic subject in the first row occludes the second photographic subject in the second row, the determined position adjustment method may be the first photographic subject Position adjustment with the second subject.

Optionally, the stance adjustment method can be determined according to the comparison result between the facial features. At this time, the stance adjustment method is mainly to adjust the subject with a larger face to the rear row farther from the camera to improve the image The shooting effect increases the satisfaction of shooting the subject.

For example, if it is determined that the face of the third subject in the first row is larger than the face of the fourth subject in the second row according to the comparison result between facial features, the determined position adjustment method may be The position adjustment of the third photographic subject and the fourth photographic subject.

Optionally, the stance adjustment method can be determined according to the comparison result between the body shape features. At this time, the stance adjustment method is mainly to adjust the larger object to the rear row or the distance from the camera. The far sides of the shooting center to improve the image shooting effect.

For example, as shown in FIG. 11, if it is determined according to the comparison result between the body shape features that the body shape of the subject 1100 in the first row is larger than the body shape of the subject 1101 in the first row, the determined position adjustment method The position adjustment of the shooting object 1100 and the shooting object 1101 may be performed.

It should be noted that when determining the position adjustment method according to two or three of the height feature, body shape feature and face shape feature, the position adjustment can be determined according to the priority order of height feature> face shape feature> body shape feature The method, that is, the position adjustment method is determined based on the height characteristics first, and when the height characteristics are the same, the position adjustment method can be determined according to the facial features, and when the height characteristics and facial features are the same, you can Determine the position adjustment method according to the body type characteristics.

Optionally, as shown in FIG. 12, in a double-sided screen mobile phone and a folding screen mobile phone in a folded state, the determined position adjustment method can be displayed in a second display area viewable by the subject through an image indication, This allows the subject to adjust the position directly according to the displayed image instructions, improving the efficiency of the position adjustment.

It should be understood that in a double-sided screen mobile phone and a folding screen mobile phone in a folded state, the determined position adjustment method can also be displayed in the first display area viewable by the photographer through image instructions, so that the photographer can follow the first display area. The image indication displayed in a display area assists in guiding the subject to adjust the position, or to facilitate the photographer to understand the effect of the position adjustment of the subject, improve the image shooting effect, and enhance the user experience.

Optionally, in a single-screen mobile phone, the determined position adjustment method can be used to guide the subject to adjust the position in the form of voice playback, or can be displayed in the first display area through image instructions, so that the photographer can According to the displayed image instructions, guide the subject to adjust the position.

It should be understood that in the double-sided screen mobile phone and the folding screen mobile phone in the folded state, the determined position adjustment method can of course also be used in the form of voice playback to assist in guiding the subject to adjust the position, or can also be displayed by image instructions In the first display area, the photographer can assist in guiding the subject to adjust the position according to the displayed image instructions, which is not limited in the embodiment of the present application.

In a possible implementation manner, after completing the adjustment of the position of the shooting object, a third image corresponding to the first display area can be further obtained, and the location of the shooting object in the third image can be identified through AI recognition technology. Corresponding to the overall camera posture, then the degree of matching between the overall camera posture and the target co-photographing posture of the preset object in the selected target posture image can be calculated; if the degree of matching is less than the second threshold, it is determined that the overall camera posture is The different positions between the target co-photographing postures, and the subject is prompted to adjust the photographing posture according to the different positions, until the matching degree between the adjusted overall photo-taking posture and the target co-photographing posture is greater than or equal to a second threshold. When the degree of matching between the adjusted overall photographing posture and the target co-photographing posture is greater than or equal to the second threshold, the camera can be controlled to take pictures to obtain a photographed image, which improves the image photographing effect and improves user experience.

Optionally, after the degree of matching between the overall photographing posture and the target co-photographing posture is calculated, the degree of matching can also be displayed in the first display area and/or the second display area in real time to facilitate the shooting of the subject and / Or the photographer clearly understands the specific fit between the photographing posture of the subject and the posture image. For example, as shown in Figure 9, the calculated matching degree of 9.5 can be displayed in the second display area to facilitate the photographer Clearly understand the specific fit between the photographing posture of the subject and the posture image.

It should be noted that the matching degree calculation in this scenario is similar to the matching degree calculation in scenario 1, and the basic principle is the same, so it will not be repeated here.

The difference between this scene and scene one is that this scene can be applied to a co-photographing scene of multiple people, and can guide the action of each subject in the co-photographing, adjusting the position of each subject according to the posture image, and improve the co-photographing effect and user experience .

As shown in FIG. 13, an embodiment of the present application provides a photographing method, which can be applied to the above-mentioned mobile terminal, and the photographing method may include:

S1301: Acquire a first image corresponding to a first display area;

S1302: Identify the target feature of the shooting object in the first image and the scene feature where the shooting object is located;

S1303. Obtain a posture image to be recommended according to the target feature of the subject and the scene feature of the scene in which the subject is located, and display the posture image in a second display area to prompt the subject according to the The posture image displayed in the second display area is adjusted for posture;

S1304. Take a photo of the subject to obtain a photo image.

It should be noted that the first image may be the first frame of preview image, or the Nth frame of preview image after the first frame, or the first frame of image collected by the camera, or the Nth frame after the first frame. For the image, N is an integer greater than 1; the characteristics of the subject include, but are not limited to, the facial features and physical characteristics of the subject; the posture image to be recommended can be obtained locally or from the network.

In a possible implementation manner, the acquiring the posture image to be recommended according to the target feature of the shooting object and the scene feature of the scene in which the shooting object is located includes:

Specifically, the selecting a preset number of target sample images from the sample images includes:

Optionally, when there is a photographed object in the first image, the acquiring at least one sample image according to the target feature of the photographed object and the scene characteristic of the scene in which the photographed object is located includes:

Determining the shooting category corresponding to the first image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

At least one sample image corresponding to the shooting category is acquired.

In a possible implementation manner, when there are multiple photographed objects in the first image, the identifying target characteristics of the photographed objects in the first image includes:

Identifying the target feature of each shooting object in the first image;

In a possible implementation manner, the taking a picture of the subject to obtain a photographed image includes:

Acquiring a second image corresponding to the first display area;

Optionally, after displaying the posture image in the second display area, the method further includes:

In a possible implementation manner, the photographing method is applied to a mobile terminal. The mobile terminal includes a first display screen and a second display screen. The display area of the first display screen is the first display area. The display area of the second display screen is the second display area. When taking a picture, the first display area faces the photographer, and the second display area faces the photographic object.

Optionally, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, the display area of the display screen is a first display area, and the second display area is a partial display area of the first display area, When taking a picture, the first display area and the second display area face the photographer or the subject.

In a possible implementation, the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, and the first display area and the second display area are located in different display areas of the display screen. , The first display area and the second display area face the photographer or the photographed subject.

The embodiment of the application obtains the posture image by combining the target feature of the shooting object and the scene feature, which can improve the accuracy and effectiveness of the posture image acquisition, and display the posture image in the second display area, thereby facilitating shooting The object directly adjusts the posture according to the displayed posture image, or it is convenient for the photographer to guide the subject to adjust the posture according to the displayed posture image, which effectively improves the image shooting effect and enhances the user experience.

Corresponding to the photographing method described in the above embodiment, FIG. 14 shows a structural block diagram of a photographing device provided in an embodiment of the present application. For ease of description, only the parts related to the embodiment of the present application are shown.

Referring to FIG. 14, the photographing device may be applied to the above-mentioned mobile terminal, and the photographing device may include:

The image acquisition module 1401 is configured to acquire a first image corresponding to the first display area;

The feature recognition module 1402 is configured to recognize the target feature of the shooting object in the first image and the scene feature of the scene in which the shooting object is located;

The posture image recommendation module 1403 is configured to obtain a posture image to be recommended according to the target feature of the subject and the scene feature of the scene where the subject is located, and display the posture image in the second display area to prompt The shooting object performs posture adjustment according to the posture image displayed in the second display area;

The photographing module 1404 is used to photograph the subject to obtain a photographed image.

In a possible implementation, the posture image recommendation module 1403 includes:

Specifically, the posture image determining unit is specifically configured to obtain the recommended value of each sample image, and select the first N sample images with high recommended value as the target sample image, and N is an integer greater than or equal to 1.

Optionally, when there is a subject in the first image, the sample image acquisition unit includes:

In a possible implementation, when there are multiple shooting objects in the first image, the feature recognition module 1402 is further configured to identify the target feature of each shooting object in the first image;

Correspondingly, the sample image acquisition unit includes:

Specifically, the sample image acquisition second subunit is specifically configured to acquire from a pre-stored sample image library according to the group characteristic and the scene characteristic, and the degree of matching with the group characteristic and the scene characteristic is greater than At least one sample image of the first threshold.

Optionally, the photographing module 1404 includes:

Specifically, the posture adjustment determining unit includes:

In a possible implementation manner, the photographing device further includes:

Optionally, the photographing device is applied to a mobile terminal, the mobile terminal includes a first display screen and a second display screen, the display area of the first display screen is the first display area, and the second display screen The display area is a second display area. When taking a picture, the first display area faces the photographer, and the second display area faces the photographic object.

In a possible implementation manner, the photographing device is applied to a mobile terminal, the mobile terminal includes a display screen, a display area of the display screen is a first display area, and the second display area is a first display area When taking a photo, the first display area and the second display area face the photographer or the photographed subject.

Optionally, the photographing device is applied to a mobile terminal. The mobile terminal includes a display screen. The first display area and the second display area are located in different display areas of the display screen. The display area and the second display area face the photographer or the subject.

Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In actual applications, the above functions can be allocated to different functional units, Module completion, that is, divide the internal structure of the device into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Form realization can also be realized in the form of software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, which is not repeated here.

FIG. 15 is a schematic structural diagram of a mobile terminal provided by an embodiment of this application. As shown in FIG. 15, the mobile terminal 15 of this embodiment includes: at least one processor 1500 (only one is shown in FIG. 15), a memory 1501, and stored in the memory 1501 and available in the at least one processor 1500 A computer program 1502 running on the computer, and a display screen 1503. The display screen 1503 includes a first display area and a second display area. When the processor 1500 executes the computer program 1502, the mobile terminal implements any of the above Examples of photographing methods.

Those skilled in the art can understand that FIG. 15 is only an example of the mobile terminal 15 and does not constitute a limitation on the mobile terminal 15. It may include more or less components than shown in the figure, or a combination of certain components, or different components. , For example, can also include input and output devices, network access devices, etc.

The embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it realizes the steps that can realize the above-mentioned method embodiments.

The embodiments of the present application provide a computer program product. When the computer program product is run on a mobile terminal, the above-mentioned photographing method embodiments can be implemented when the mobile terminal is executed.

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

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail or recorded in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may be aware that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the system embodiment described above is merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be Combined or can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; 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 Within the scope of protection of this application.

Claims

A photographing method, characterized in that it comprises:

Acquiring a first image corresponding to the first display area;

Identifying the target feature of the shooting object in the first image and the scene feature of the scene where the shooting object is located;

Obtain the posture image to be recommended according to the target feature of the subject and the scene feature of the scene in which the subject is located, and display the posture image in the second display area to prompt the subject according to the second Adjust the posture image displayed in the display area;

Taking a picture of the subject to obtain a photographed image.
The photographing method according to claim 1, wherein the acquiring the posture image to be recommended according to the target characteristics of the photographed object and the scene characteristic of the scene in which the photographed object is located comprises:

Acquiring at least one sample image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

A preset number of target sample images are selected from the sample images, and the selected target sample images are determined as the pose images to be recommended.
3. The photographing method according to claim 2, wherein the selecting a preset number of target sample images from the sample images comprises:

Obtain the recommended value of each sample image, and select the first N sample images with high recommended value as the target sample image, where N is an integer greater than or equal to 1.
The photographing method according to claim 2, wherein when there is a photographed subject in the first image, the acquisition of at least the characteristics of the scene in which the photographed subject is located is at least A sample image, including:

Determine the shooting category corresponding to the first image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located;

At least one sample image corresponding to the shooting category is acquired.
3. The photographing method according to claim 2, wherein when there are multiple photographed objects in the first image, the identifying target features of the photographed objects in the first image comprises:

Identifying the target feature of each shooting object in the first image;

Correspondingly, the acquiring at least one sample image according to the target feature of the shooting object and the scene feature of the scene where the shooting object is located includes:

Determining the group characteristics of the multiple photographing objects in the first image according to the target characteristic of each photographing object;

At least one sample image is acquired according to the group characteristics and the scene characteristics.
The photographing method according to claim 5, wherein said acquiring at least one sample image according to said group characteristics and said scene characteristics comprises:

According to the group feature and the scene feature, at least one sample image whose matching degree with the group feature and the scene feature is greater than a first threshold is acquired from a pre-stored sample image library.
The photographing method according to claim 1, wherein the photographing the subject to obtain a photographed image comprises:

After it is determined that the photographed object has adjusted its posture according to the posture image displayed in the second display area, the photographed object is photographed to obtain a photographed image.
8. The photographing method according to claim 7, wherein after determining that the photographed object is adjusted according to the posture image displayed in the second display area, the photographed object is photographed to obtain the photographed image, include:

Acquiring a second image corresponding to the first display area;

When the degree of matching between the second image and the posture image displayed in the second display area is greater than a second threshold, it is determined that the posture adjustment of the shooting object is completed, and the shooting object is photographed to obtain a photographed image.
The photographing method according to claim 1, wherein after displaying the posture image in the second display area, the method further comprises:

Acquire the prompt voice and/or prompt text corresponding to the posture image, and prompt the photographic subject to adjust the posture through the prompt voice and/or the prompt text.
The photographing method according to any one of claims 1 to 9, wherein the photographing method is applied to a mobile terminal, and the mobile terminal includes a first display screen and a second display screen. The display area is a first display area, and the display area of the second display screen is a second display area. When taking a picture, the first display area faces the photographer, and the second display area faces the subject.
The photographing method according to any one of claims 1 to 9, wherein the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, and the display area of the display screen is the first display area. The second display area is a part of the display area of the first display area. When taking a picture, the first display area and the second display area face the photographer or the photographed subject.
The photographing method according to any one of claims 1 to 9, wherein the photographing method is applied to a mobile terminal, the mobile terminal includes a display screen, and the first display area and the second display area are located in the Different display areas of the display screen, when taking a picture, the first display area and the second display area face the photographer or the photographed object.
A mobile terminal includes a display screen, a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program so that all The mobile terminal implements the photographing method according to any one of claims 1 to 12.
A computer-readable storage medium storing a computer program, wherein the computer program implements the photographing method according to any one of claims 1 to 12 when the computer program is executed by a processor.