CN117635453A

CN117635453A - Method, device, server and storage medium for generating poster

Info

Publication number: CN117635453A
Application number: CN202311491941.5A
Authority: CN
Inventors: 田为为; 赵松; 李晶晶; 李川; 刘传宝; 郝勇钢; 陈晓仕; 沈凯; 顾浩; 许浩; 陈亚斌
Original assignee: Rajax Network Technology Co Ltd; Koubei Shanghai Information Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd; Koubei Shanghai Information Technology Co Ltd
Priority date: 2023-11-09
Filing date: 2023-11-09
Publication date: 2024-03-01

Abstract

The application relates to the technical field of image processing, and provides a method, a device, a server and a storage medium for generating a poster, wherein the method comprises the following steps: acquiring an original image, wherein the original image comprises a foreground area and a background area where a shooting subject is located; detecting whether the background area is a white background; if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster, wherein the target poster comprises the shooting subject; and if the background area is a background other than the white background, generating the target poster by performing image processing on the original image. Based on the scheme of the application, the automatic generation of the poster based on the original image of the merchant can be realized; the problem that the release threshold of a merchant is high is solved, and the requirements of the merchant are met.

Description

Method, device, server and storage medium for generating poster

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, a server, and a storage medium for generating a poster.

Background

With the development of the digital intelligence era, electronic devices such as mobile phones and tablet computers occupy more and more important positions in the life of users, and functions of application programs (APP) used by users on the electronic devices are also more and more abundant, and interface contents presented for users in different APPs are more vivid and lively.

At present, the poster of each merchant is usually displayed in an APP interface, and consumers can be attracted to each merchant through the poster, so that the consumers can quickly know the products of the merchant for consumption; however, in general, the design of the poster needs to be completed by a professional designer, so that the release threshold of the merchant is high, and the requirement of the merchant cannot be met.

Therefore, how to automatically generate a poster based on an original image becomes a problem to be solved.

Disclosure of Invention

The application provides a method for generating a poster, which can realize automatic generation of the poster based on an original image of a merchant; the problem that the release threshold of a merchant is high is solved, and the requirements of the merchant are met.

In a first aspect, a method of generating a poster is provided, comprising:

acquiring an original image, wherein the original image comprises a foreground area and a background area where a shooting subject is located;

detecting whether the background area is a white background;

if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster, wherein the target poster comprises the shooting subject;

and if the background area is the background except the white background, generating the target poster by performing image processing on the original image.

In the embodiment of the application, after the original image is acquired, generating a target poster by adopting different processing modes according to whether a background area in the original image is a white background or not; if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster; if the background area is a background except a white background, generating a target poster by performing image processing on the original image; the target poster comprises a shooting main body; according to the scheme, the merchant poster can be automatically generated based on the original image without user operation; in addition, as different processing modes can be adopted for the original images with different backgrounds, the reasonable utilization of the original images can be realized; the problem that the release threshold of a merchant is high is solved, and the requirements of the merchant are met.

With reference to the first aspect, in some implementations of the first aspect, if the background area is a white background, the processing, by an artificial intelligence algorithm, the shooting subject to generate a target poster includes:

if the background area is the white background, performing matting processing on the original image through an artificial intelligence algorithm to obtain a matting result of the shooting subject;

Identifying the target type of the shooting subject, and matching a target poster template corresponding to the target type;

and carrying out fusion processing on the target poster template and the matting result to generate the target poster.

In the embodiment of the application, if the background area of the original image is a white background, the target type of the shooting subject can be identified through an artificial intelligence algorithm, and a target poster template corresponding to the target type is matched; carrying out fusion processing on the target poster template and the shooting subject to generate a target poster; in the scheme, when the background area is a white background, the shooting subject in the original image is subjected to the matting processing, and the obtained matting result of the shooting subject is high in accuracy; matching a target poster template corresponding to the target type by shooting the target type of the main body; the high-quality target poster can be ensured to be generated through the high-accuracy image matting result of the shooting main body and the matched target poster template, so that the attraction to consumers is enhanced; meeting the demands of merchants.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, the identifying, by the artificial intelligence algorithm, a target type of the shooting subject, and matching a target poster template corresponding to the target type includes:

And identifying the target type of the shooting subject through an AIGC model, and matching a target poster template corresponding to the target type.

In the embodiment of the application, the target type of the shooting subject is identified through an AIGC model, and a target poster template corresponding to the target type is matched; because the AIGC model has higher processing efficiency, the AIGC model is used for identifying the target type of the shooting subject and matching the target poster template corresponding to the target type, so that the processing efficiency of the target poster template corresponding to the matched target type can be improved.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, if the background area is a background other than the white background, generating the target poster by performing image processing on the original image includes:

if the background area is the background except the white background, determining a target processing mode according to the area occupation ratio of the foreground area in the original image, wherein the target processing mode comprises an image cutting processing mode or an image restoration processing mode;

and carrying out image processing on the original image in the target processing mode to generate the target poster.

In the embodiment of the present application, if the background area is a background other than a white background, different area ratios of the foreground area where the subject is located in the original image are taken, and different target processing modes may be adopted to perform image processing on the original image, so as to generate a target poster; according to the scheme, the processing mode for generating the target poster can be flexibly selected based on the size of the shooting subject in the original image; when the target poster is generated, the original image can be fully and reasonably utilized.

With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, the determining a target processing manner according to an area ratio of the foreground area in the original image includes:

if the area occupation ratio is larger than a first preset threshold value, determining that the target processing mode is the image restoration processing mode;

and if the area occupation ratio is smaller than or equal to a first preset threshold value, determining that the target processing mode is the image cutting processing mode.

In the embodiment of the present application, when the area ratio of the foreground area where the shooting subject is located in the original image is greater than the first preset threshold, that is, the area of the foreground area where the shooting subject is located in the original image is indicated to be greater; at this time, if the image cutting processing mode is adopted, the integrity of the shooting subject in the target poster cannot be ensured, and the integrity of the shooting subject in the generated target poster can be ensured by adopting the image restoration processing mode; when the area ratio of the foreground area of the shooting subject to the original image is smaller than or equal to a first preset threshold, the area of the foreground area of the shooting subject to the original image is moderate or smaller, and at this time, the image cutting processing mode is adopted to process the original image, so that the definition of the shooting subject in the generated target poster can be ensured.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, if the background area is a background other than the white background, the generating the target poster by performing image processing on the original image includes:

if the background area is a background other than the white background, determining a target processing mode according to the current calculation power demand, wherein the target processing mode comprises an image cutting processing mode or an image restoration processing mode;

In the embodiment of the application, if the background area is a background other than a white background, selecting an image cutting processing mode or an image restoration processing mode according to the current computing power requirement to perform image processing on the original image, so as to generate a target poster; according to the technical scheme, the processing mode for generating the target poster can be flexibly selected based on the current calculation force demand; when the target poster is generated, the original image can be fully and reasonably utilized.

With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, determining, according to a current computing power requirement, a target processing manner includes:

If the current calculation force requirement is greater than a second preset threshold value, determining that the target processing mode is the image cutting processing mode;

and if the current calculation force requirement is smaller than or equal to a second preset threshold value, determining that the target processing mode is the image restoration processing mode.

In the embodiment of the application, because the image restoration processing mode needs to fill the missing image in the original image, the required calculation force requirement is larger; therefore, when the background of the original image is not white background and the current calculation force demand is large, the original image can be subjected to image processing in an image cutting processing mode to generate a target poster; thereby saving a certain degree of effort in the generation of the poster.

if the background area is the background except the white background, determining a target processing mode according to the definition requirement of the display area of the target poster, wherein the target processing mode comprises an image cutting processing mode or an image restoration processing mode;

In the embodiment of the application, if the background area is a background other than a white background, selecting an image cutting processing mode or an image restoration processing mode for image processing of an original image according to the definition requirement of the display area of the target poster, and generating the target poster; according to the technical scheme, the processing mode for generating the target poster can be flexibly selected based on the current calculation force demand; when the target poster is generated, the original image can be fully and reasonably utilized.

With reference to the first aspect and the foregoing implementation manners, in some implementation manners of the first aspect, the determining a target processing manner according to a definition of a display area of the target poster includes:

if the definition requirement of the display area of the target poster is greater than a third preset threshold, determining that the target processing mode is the image cutting processing mode;

and if the definition requirement of the display area of the target poster is smaller than or equal to a third preset threshold value, determining that the target processing mode is the image restoration processing mode.

In the embodiment of the application, because the image cutting processing mode is to cut on the basis of the original image, the definition of the original image obtained under normal conditions is better; therefore, when the display area of the target poster has high requirements on definition, the original image can be subjected to image processing in an image cutting processing mode to generate the target poster; thereby ensuring better definition of the target poster to a certain extent.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, when the target processing manner is the image cropping processing manner, the performing, by using the target processing manner, the image processing on an original image to generate the target poster includes:

determining a target coordinate position of a center point of the shooting subject in the original image;

determining a center point of a cutting frame in the image cutting processing mode according to the target coordinate position;

and cutting the original image based on the center point of the cutting frame and the cutting frame to generate the target poster.

In the embodiment of the application, in the process of performing image cutting processing on an original image, the center point of the cutting frame and the center point of the shooting main body can be kept aligned as much as possible; therefore, the shooting subject in the generated target poster is ensured to be positioned in the middle position, and the attraction of the target poster to consumers is improved.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, an area size of the trimming frame is determined according to a target size of a display area of the target poster.

In one implementation, the area size of the crop box is equal to the target size of the display area of the target poster.

In the embodiment of the application, the size of the area of the cutting frame in the image cutting processing mode is ensured according to the target size of the display area of the target poster, so that the generated target poster can be completely displayed in the display area, and the complete display of a shooting subject is ensured.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, when the target processing manner is the image restoration processing manner, the performing, by using the target processing manner, the image processing on an original image to generate the target poster includes:

acquiring a target size of a display area of the target poster;

performing filling processing on the original image according to the target size, and determining a target image area, wherein the target image area comprises the original image and a filling area, and the size of the target image area is the target size;

generating a target mask of the original image in the target image area, wherein the target mask is used for marking the position of the original image in the target image area;

And carrying out image processing on the filling area in the target image area through a deep learning algorithm and the target mask to generate the target poster.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, the detecting whether the background area is a white background includes:

and carrying out background detection processing on the original image to generate a background detection result, wherein the background detection result indicates whether the background area is the white background or not.

With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, the performing a background detection process on an original image to generate a background detection result includes:

determining a target position in an original image, wherein the target position is used for indicating an image edge of the original image;

and generating the background detection result according to the gray value of the pixel of the target position.

In one implementation, if the gradient of the gray value of the pixel at the target position is greater than the preset threshold, it indicates that the background area is not a white background, that is, the background detection result indicates that the background area of the original image is a white background; if the gradient of the gray value of the pixel at the target position is smaller than or equal to the preset threshold value, the background area is indicated to be a white background, namely the background detection result indicates that the background area of the original image is not the white background.

determining whether the original image meets a preset image condition;

if the original image does not meet the preset image condition, preprocessing the original image to obtain a processed original image;

and detecting whether the background area in the processed original image is the white background or not.

In the embodiment of the application, if the original image does not meet the preset image condition, the original image may be preprocessed to obtain the processed original image; on the basis that the processed original image meets the preset image conditions, different processing modes are adopted to generate a target poster; thereby ensuring the full and reasonable utilization of the original image in the poster generation process.

In a second aspect, there is provided an apparatus for generating a poster, comprising:

the acquisition module is used for acquiring an original image, wherein the original image comprises a foreground area and a background area where a shooting subject is located;

the detection module is used for detecting whether the background area is a white background or not;

The processing module is used for processing the shooting subject through an artificial intelligence algorithm to generate a target poster if the background area is a white background, wherein the target poster comprises the shooting subject; and if the background area is the background except the white background, generating the target poster by performing image processing on the original image.

With reference to the second aspect, in certain implementations of the second aspect, the processing module is specifically configured to:

identifying the target type of the shooting subject through the artificial intelligence calculation, and matching a target poster template corresponding to the target type;

and fusing the target poster template and the matting result through the artificial intelligence calculation to generate the target poster.

With reference to the second aspect and the foregoing implementation manner, in some implementation manners of the second aspect, the processing module is specifically configured to:

With reference to the second aspect and the foregoing implementation manner, in some implementation manners of the second aspect, when the target processing manner is the image cropping processing manner, the processing module is specifically configured to:

With reference to the second aspect and the foregoing implementation manner, in some implementation manners of the second aspect, an area size of the trimming frame is determined according to a target size of a display area of the target poster.

With reference to the second aspect and the foregoing implementation manner, in some implementation manners of the second aspect, when the target processing manner is the image restoration processing manner, the processing module is specifically configured to:

Acquiring a target size of a display area of the target poster;

With reference to the second aspect and the foregoing implementation manner, in some implementation manners of the second aspect, the detection module is specifically configured to:

determining whether the original image meets a preset image condition;

In a third aspect, a server is provided, comprising a memory for storing executable program code and a processor for calling and running the executable program code from the memory, such that the server performs the method of the first aspect or any one of the possible implementations of the first aspect.

In a fourth aspect, there is provided a chip system for application to an electronic device, the chip system comprising one or more processors for invoking computer instructions to cause the electronic device to perform the method of the first aspect or any of the first aspects.

In a fifth aspect, there is provided a computer program product comprising: computer program code which, when run on a computer, causes the computer to perform the control method of the first aspect or any one of the possible implementation manners of the first aspect.

In a sixth aspect, a computer readable storage medium is provided, the computer readable storage medium storing computer program code which, when run on a computer, causes the computer to perform the method of the first aspect or any one of the possible implementations of the first aspect.

In the embodiment of the application, after the original image is acquired, generating a target poster by adopting different processing modes according to whether a background area in the original image is a white background or not; if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster; if the background area is a background except a white background, generating a target poster by performing image processing on the original image; the target poster comprises a shooting main body; according to the scheme, the automatic generation of the merchant poster can be ensured to be realized without user operation based on the original image; in addition, as different processing modes can be adopted for the original images with different backgrounds, the reasonable utilization of the original images can be realized; the problem that the release threshold of a merchant is high is solved, and the requirements of the merchant are met.

In addition, in the embodiment of the application, if the background area is a white background, the accuracy of the obtained matting result of the shooting subject is higher by performing matting processing on the shooting subject in the original image; matching a target poster template corresponding to the target type by shooting the target type of the main body; the high-quality target poster can be ensured to be generated through the high-accuracy image matting result of the shooting main body and the matched target poster template, so that the attraction to consumers is enhanced; if the background area is a background other than a white background, the original image can be subjected to image processing by adopting different target processing modes through different area occupation ratios of the foreground area where the main body is located in the original image, the current calculation power requirement and the definition requirement of the display area of the target poster, so as to generate the target poster; according to the scheme, the processing mode for generating the target poster can be flexibly selected based on the size of the shooting subject in the original image; when the target poster is generated, the original image can be fully and reasonably utilized.

Drawings

Fig. 1 is a schematic diagram of an application scenario of a method for generating a poster according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of a method of generating a poster provided by embodiments of the present application;

FIG. 3 is a schematic illustration of an original image provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a poster layout provided by embodiments of the present application;

FIG. 5 is a schematic flow chart diagram of another method of generating a poster provided by embodiments of the present application;

fig. 6 is a schematic diagram of an original image, a matting result, a template and a poster provided in an embodiment of the present application;

FIG. 7 is a schematic flow chart diagram of another method of generating a poster provided by embodiments of the present application;

fig. 8 is a schematic structural diagram of a device for generating a poster according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

The technical solutions in the present application will be clearly and thoroughly described below with reference to the accompanying drawings. Wherein, in the description of the embodiments of the present application, "/" means or is meant unless otherwise indicated, for example, a/B may represent a or B: the text "and/or" is merely an association relation describing the associated object, and indicates that three relations may exist, for example, a and/or B may indicate: the three cases where a exists alone, a and B exist together, and B exists alone, and in addition, in the description of the embodiments of the present application, "plural" means two or more than two.

The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

For ease of understanding, a scenario in which an operation interface of the application a is displayed for a user in a first application (for example, the application a) installed on a mobile phone will be specifically described below with reference to the accompanying drawings.

Fig. 1 is a schematic diagram of an example of a graphical user interface (Graphical User Interface, GUI) for a user to run an application a launch.

By way of example, fig. 1 (a) shows an interface 101 displayed by a mobile phone in an unlock mode, the interface 101 displaying a weather clock component, and a plurality of Application a programs (apps), etc. The application a program may include telephone, information, settings, application a, etc.

It should be understood that the interface 101 may also include many more applications, and the embodiments of the present application are not limited in this regard.

For example, as shown in (a) of fig. 1, the mobile phone detects a click operation of an icon of the application a by a user, and in response to the click operation by the user, the mobile phone displays a main interface 102 of the application a as shown in (b) of fig. 1; the main interface 102 may display interface content such as a plurality of sort menus, operable controls or buttons, pictures, etc., to meet the user's needs.

Alternatively, the home interface 102 may also be referred to as the "home page of application A".

Illustratively, as shown in fig. 1 (b), on the main interface 102 of the application a, a current distribution address (e.g. "XX area XX street"), a search box, and various sort menus of food take-out, supermarket, fruit, medicine, dessert, hamburger, lobster, and barbecue, etc., and the display area 10 of the merchant are displayed; displaying a poster 10-1 of the commodity on a display area 10 of the merchant; for example, the merchant's display area 10 may be a display area of a hamburger store; the commercial poster 10-1 may be a poster associated with a hamburger; the poster can display images, characters, or information such as a poster background related to the hamburger.

As shown in fig. 1 (c), the mobile phone detects a sliding operation of the user on the main interface 102, and in response to the sliding operation of the user, the mobile phone displays an interface 103 as shown in fig. 1 (d); displaying display areas of different merchants on an interface 103, wherein the display areas of each of the display areas display posters of products corresponding to the merchants; for example, the display area 10 of a hamburger, the display area 20 of a light eating establishment, and the display area 30 of a tea establishment are displayed on the interface 103; wherein, on the display area 10 of the hamburger shop, the poster 10-1 of the hamburger is displayed; displaying a poster 20-1 of a commodity corresponding to the light food restaurant on a display area 20 of the light food restaurant; for example, the poster includes sandwiches, salad, etc.; on the display area 30 of the tea shop, a poster 30-1 of the drink is displayed.

For example, information such as my score of each merchant, the number of sales per month, the distance from the delivery address, the delivery time, the delivery cost, the delivery start cost, etc. may also be displayed in the interface 103 shown in fig. 1 (d).

In the embodiment of the present application, the display content, the size of the display area, and the like in each interface in fig. 1 (a) to 1 (d) are not limited.

Optionally, the above is illustrated with a poster displayed in an application program in a mobile phone; the method for generating the poster is suitable for any scene displaying the poster.

Currently, on the interface 103 of the application a, users are usually attracted to each merchant through the poster of each merchant displayed in different display areas, so that the users can quickly know the products of the merchant; however, in general, the design of the poster needs to be completed by a professional designer, so that the release threshold of the merchant is high, and the requirement of the merchant cannot be met.

In view of this, the present application will provide a method for generating a poster, by which a merchant poster can be automatically generated without user operation in the process of generating a poster based on an image of a merchant; the problem that the release threshold of a merchant is high is solved, and the requirements of the merchant are met.

The method for generating the poster provided in the embodiments of the present application is described in detail below with reference to fig. 2 to 7.

Fig. 2 is a schematic flow chart of another method of generating a poster provided by embodiments of the present application. As shown in fig. 2, the method 200 includes S201 to S207, and S201 to S207 are described in detail below, respectively.

S201, acquiring an original image.

For example, the original image may refer to an image of merchandise uploaded by a different merchant; for example, merchandise images may include, but are not limited to: dish images, dessert images, drink images, etc.

S202, judging whether an original image meets preset image conditions or not; if yes, executing S203; if not, S204 is performed.

Exemplary, the preset image conditions include: whether the shooting subject in the original image is complete, whether text information (e.g., watermark information) is included in the original image, and whether the image definition of the original image is greater than a preset definition.

Optionally, the preset image condition may further include whether the background area of the original image includes more than two objects or more than two colors; that is, it can be understood whether the background area of the original image is complicated in color or content.

It should be noted that the foregoing is an illustration of the preset image condition; the preset image conditions are not limited in any way; the judgment by the preset image condition is to ensure whether the acquired original image is suitable for generating a poster.

S203, judging whether the background of the image is a white background; if yes, executing S205; if not, S207 is performed.

For example, if the original image satisfies the preset image condition, it is determined whether the background of the original image is a white background.

It should be understood that, for an image with a white background, on the one hand, the white background can ensure that the light transmittance is better when the subject is photographed when the image is photographed, that is, the image quality of the image is better; on the other hand, when the matting processing of the shooting subject is performed on the white background image, the matting result has higher accuracy.

S204, preprocessing the original image to obtain a preprocessed image.

For example, if the original image does not meet the preset image condition, preprocessing the original image to obtain a preprocessed image, so that the preprocessed image meets the preset image condition.

In one example, as shown in (a) of fig. 3, if the sharpness of the original image does not meet the preset image condition, the sharpness processing may be performed on the original image, so as to ensure that the sharpness of the processed image is greater than the preset sharpness threshold.

Alternatively, the sharpness process may use any existing algorithm, which is not limited in this application.

In one example, as shown in (b) of fig. 3, if the subject in the original image is incomplete, an image restoration process may be performed on the original image, thereby ensuring the integrity of the subject in the processed image.

Alternatively, the algorithm used in the image restoration process may be any existing processing algorithm, which is not limited in this application.

In one example, as shown in (c) of fig. 3, if the original image includes text information, text removal processing may be performed on the text information in the original image, so as to ensure that the processed image does not include text information.

Alternatively, the text removal process may use any existing processing algorithm, which is not limited in this application.

S205, carrying out matting processing on a shooting subject in the image, and generating a matting result.

In one example, if the original image satisfies a preset image condition and the background of the original image is a white background, the image capture subject in the original image is subjected to image capture processing, and a image capture result is generated.

In one example, if the original image does not meet the preset image condition, obtaining a processed image; and the background of the processed image is a white background, and the photographic subject in the processed image is subjected to the matting processing to generate a matting result.

It should be understood that, in general, the foreground region and the background region are included in the image, and the subject may refer to the foreground region in the image; the foreground region may refer to an image region in which the subject is photographed.

S206, processing the matting result through an AIGC algorithm to generate the poster.

Illustratively, matching the poster template corresponding to the category according to the category corresponding to the image content included in the matting result.

For example, if the image content of the matting result corresponds to the beverage, the poster template corresponding to the beverage can be matched; if the image content of the matting result corresponds to barbecue, matching the poster template corresponding to barbecue; if the image content of the matting result is the simple meal, the poster template corresponding to the simple meal can be matched.

It should be understood that the generated artificial intelligence algorithm (Artificial Intelligence Generated Content, AIGC) refers to a technical method based on generating artificial intelligence for a countermeasure network, a large pre-training model, etc.; techniques for generating relevant content with appropriate generalization capability through learning and recognition of existing data. The core idea of the AIGC technique is to generate content with a certain creative and quality using artificial intelligence algorithms. By training the model and learning the large amount of data, the AIGC can generate content related thereto according to the inputted conditions or instructions. For example, by entering keywords, descriptions, or samples, the AIGC may generate articles, images, audio, etc. that match it.

S207, performing image restoration processing or image cutting processing on the image to generate a poster.

For example, if the original image satisfies the preset image condition and the original image is not a white background, the poster is generated by performing an image restoration process or an image cropping process on the original image.

Exemplary, if the original image does not meet the preset image condition, preprocessing the original processing to obtain a processed image; and the background of the processed image is not white background, and the poster is generated by carrying out image restoration processing or image cutting processing on the original image.

Example 1

In one example, the generation of the poster using the image restoration process or the image cropping process is determined according to the occupation ratio of the subject to be photographed in the image.

For example, if the duty ratio of the shooting subject in the image is greater than a preset threshold, generating a poster by adopting an image restoration algorithm; for example, the image is modified according to the target size of the poster to generate the poster.

Alternatively, in embodiments of the present application, any existing image restoration algorithm may be used, which is not limited in any way herein.

In the embodiment of the present application, if the ratio of the shooting subject in the image is greater than the preset threshold, it means that the shooting subject in the image, that is, the foreground area in the image, is relatively large; at this time, if an image cutting processing method is adopted, the range of allowing cutting is smaller; therefore, when the occupation of the subject in the image is relatively large, the poster can be generated from the image by adopting the image restoration algorithm.

For example, if the duty ratio of the shooting subject in the image is smaller than or equal to a preset threshold value, generating a poster by adopting an image cutting algorithm; alternatively, the implementation may be described with respect to the second processing approach in fig. 5.

In the embodiment of the present application, if the duty ratio of the shooting subject in the image is smaller than or equal to the preset threshold, it means that the duty ratio of the shooting subject in the image, that is, the foreground area in the image is moderate or smaller; at this time, the definition of the generated poster can be ensured by adopting an image cutting processing algorithm; therefore, when the occupation of the subject in the image is relatively small or moderate, the poster can be generated from the image by adopting the image cropping processing algorithm.

Example 2

In one example, the generation of the poster using an image restoration process or an image cropping process is determined based on an operator demand or a definition demand of the poster.

It should be appreciated that, since the image restoration processing algorithm needs to perform extension processing on the image, that is, generate missing image information in the image; therefore, the image restoration processing algorithm has higher requirement on calculation force requirement; if the demand of the calculation force for generating the poster has a certain requirement, the image cutting processing algorithm can be adopted to generate the poster in order to save the calculation force.

It should also be appreciated that since the image cropping process is to generate a poster by cropping the original image content of the image; the poster is a partial area in the image, so that the definition of the poster generated by the image cutting processing is better; if the definition of the generated poster has a certain requirement, the poster can be generated by adopting an image cutting processing method.

Optionally, on the basis of the above examples 1 and 2, text information may also be added to the generated poster in other existing manners; the algorithm for adding text information is not limited in any way.

Illustratively, as shown in fig. 4, the poster generally includes two layouts as shown in fig. 4 (a) and fig. 4 (b).

In one example, as shown in (a) of FIG. 4, the poster 40 includes an identified display area 40-1 therein; the display area 40-2 of the document and the display area 40-3 of the main picture; the display area 40-2 of the document may be located above the display area 40-3 of the main body picture; the identified display area 40-1 is located uppermost in the poster 40.

In another example, as shown in (b) of fig. 4, the poster 50 includes an identified display area 50-1 therein; a display area 50-2 of the main body picture and a display area 50-3 of the document; the display area 50-2 of the main body picture is positioned above the display area 50-3 of the document; the identified display area 50-1 is located uppermost in the poster 50.

An implementation manner of the method for generating a poster provided in the embodiment of the present application is described in detail below with reference to fig. 5.

Fig. 5 is an interactive flow chart of another method of generating a poster provided by embodiments of the present application. As shown in fig. 5, the method 300 includes S301 to S328, and S301 to S328 are described in detail below, respectively.

As shown in fig. 5, the method 300 of generating a poster includes the following stages:

the first stage: offline configuration phase

It should be appreciated that this first phase is a manual configuration phase for the developer. For example, in this first stage, poster templates corresponding to objects of different categories may be configured by a developer based on big data. The first stage comprises the steps of:

s301, a developer configures a template.

Illustratively, the developer may include a user experience design (User Experience Design, UED) developer and a backend developer (e.g., an algorithm developer); the UED developer can manually configure information related to the display interface; the back-end developer may manually configure the operating algorithms associated with displaying the relevant interfaces.

For example, a UED developer may configure a poster template; different types of objects may configure different poster templates; the food is exemplified by the subject; different types of food may include, but are not limited to: beverage, western-style food, chinese style food, barbecue, chafing dish, dessert, etc.; for different food types, a poster template corresponding to the food type can be configured.

In the embodiments of the present application, the above-described templates may be referred to as "poster templates" for ease of understanding; i.e. the template and the poster template may indicate the same concept.

S302, the developer sends the background image and the configuration information in the template to the image access gateway in the server.

It should be noted that, the image capability access gateway in the server is configured to receive a request instruction of a developer or a client, and send an instruction to a called corresponding module according to the request instruction.

Exemplary, the poster template includes: a text layer, a background layer or a product layer; the background image may refer to an image of a background layer in a poster template.

For example, the configuration information may include a size of an area occupied by the main body in the poster template, position information of the main body, or a target size of a poster display position, etc.

S303, the developer sends the background image in the template to a storage module in the server.

For example, a developer sends a background image to a storage module in a server through a device; after the storage module receives the background image, the storage module stores the background image.

It should be appreciated that the storage module in the server is used to store data.

And a second stage: image background detection stage

It should be understood that the second stage is used for performing background detection processing on the original image uploaded by the electronic device of the client; the background detection process is for detecting whether the background of the original image is a white background. The second stage comprises the steps of:

S304, the client acquires the original image.

It should be understood that the client described in fig. 5 may refer to the electronic device of the client.

The original image acquired by the client may be an original image acquired by other devices and sent to the image of the client; alternatively, if the electronic device of the client has a module for capturing an image, such as a camera, the original image may be an image captured by the electronic device of the client.

For example, a client may refer to devices of different merchants corresponding to a server; different merchants can acquire original images of the commodities; for example, if the business is a restaurant business, the original image may be an image of dishes in the business.

S305, the client sends a request instruction of background detection to the image capability access gateway in the server.

For example, after the electronic device of the client acquires the original image, the electronic device of the client sends a request instruction for background detection to the image capability access gateway in the server; by checking the background of the original image, the processing mode adopted for generating the poster of the original image can be determined.

In one implementation, the request instruction for background detection may refer to a request instruction for white background detection; alternatively, the request instruction for background detection may refer to a request instruction for white background detection.

It should be understood that, when the image is a white background, if the main body in the image is subjected to the matting processing, the obtained matting result has higher accuracy; thus, in embodiments of the present application, different poster generation algorithms may be employed for the original image of the white background versus the original image that is not the white background; therefore, the original images uploaded by the electronic equipment of the client can be ensured to be used for generating the poster; the method and the device realize automatic generation of the poster based on the original image uploaded by the electronic equipment of the client.

S306, the image capability access gateway in the server sends a background detection instruction to the AI processing module in the server.

It should be appreciated that the AI processing module is used to run AI-related algorithms in image processing.

S307, an AI processing module in the server calculates a gray value according to the information of the original image; and determining whether the background of the original image is a white background according to the gray value.

For example, if the gradient of the gray value of the image edge of the original image is greater than the preset threshold, it indicates that the background area is not a white background, that is, the background detection result indicates that the background area of the original image is a white background; if the gradient of the gray value of the image edge is smaller than or equal to the preset threshold value, the background area is indicated to be a white background, namely the background detection result indicates that the background area of the original image is not the white background.

And S308, an AI processing module in the server sends a background detection result to the image capability access gateway in the server.

The background detection result is used for indicating whether the background of the original image is a white background or not.

And a third stage: according to the background detection result, adopting different processing modes to generate poster

It should be understood that in the third stage, the original image is determined to be processed by adopting different processing modes to generate a poster according to the background detection result; the third stage includes a first treatment mode or a second treatment mode; when the background of the original image is a white background, processing the original image by adopting a first processing mode to generate a poster; against the background of the original image.

If the background detection result indicates that the background of the original image is a white background, executing a first processing mode in a third stage; the first processing mode comprises the following steps:

s309, if the background detection result indicates that the background of the original image is white background, the image capability access gateway in the server sends an instruction for calling image mapping processing to the image processing module in the server.

It should be understood that an image of a white background may be understood as an image of a white background; i.e. the original image is a white background image.

It should be noted that, the image processing module is configured to execute an image processing algorithm, where the image processing algorithm does not include an AI image processing algorithm; the AI image processing algorithm is executed in the AI processing module.

For example, the image mapping process may refer to generating a matting result of the subject by performing a matting process on the subject in the original image; and carrying out fusion processing on the matting result and the background image in the template to generate a related algorithm of the poster.

It should be understood that the subject in the original image may refer to a foreground image in the original image; i.e., an image area where a subject (also referred to as a subject) is located.

And S310, an image processing module in the server sends a matting processing instruction to the AI processing module.

Optionally, the above-mentioned matting processing instruction may refer to an instruction for calling an arbitrary matting processing algorithm; the present application is not limited in any way.

S311, an AI processing module in the server performs matting processing on the original image to obtain a matting result.

Illustratively, an original image is shown in (a) of fig. 6; fig. 6 (b) shows a matting result; it is understood that the matting result refers to an image area of the subject photographed in the original image.

S312, an AI processing module in the server sends the matting result to an image capability access gateway in the server.

Illustratively, the matting result refers to information of an image area where the subject is photographed.

S313, the image capability access gateway in the server caches the matting result, and acquires a corresponding template according to the type.

Illustratively, the configured templates are stored in a storage module in the server; the image capability access gateway in the server can acquire a configured template corresponding to the type according to the type corresponding to the shooting subject in the matting result; for example, a plurality of templates corresponding to the type may be acquired.

S314, the image capability access gateway in the server sends each template and instruction to the image processing module.

For example, each time the image capability access gateway may send a template to the image processing module and an instruction to invoke image mapping processing.

S315, an image processing module in the server performs image mapping processing according to a color superposition algorithm to generate a poster.

For example, a color overlay algorithm may refer to an effect achieved by overlaying colors, changing the color values of pixels.

Illustratively, one example of a template corresponding to the beverage is shown in fig. 6 (c); the image shown in (d) in 6 is a poster; the poster includes a text layer 60-1, a background layer 60-2 and a main body layer 60-3.

Alternatively, the poster shown in (d) of fig. 6 above is exemplified; the poster may not include a text layer, which is not limited in this application.

S316, the image processing module in the server sends the poster to the image capability access gateway in the server.

And S317, the image capability access gateway in the server sends the poster to a storage module in the server.

Illustratively, in performing S313, a plurality of templates may be acquired; s314 to S317 are performed for each of the plurality of templates, respectively.

If the background detection result indicates that the background of the original image is not white background, executing a second processing mode in the third stage; the second processing mode comprises the following steps:

s318, if the background detection result indicates that the background of the original image is not white background, the image capability access gateway in the server sends an instruction for calling image cutting processing to the image processing module in the server.

It is understood that when the background of the original image is not a white background, the original image which is not the white background is subjected to the matting processing, and the obtained matting result of the main body is poor in accuracy; if the poster is generated by adopting image mapping, the fineness of the edge area of the main body in the poster is poor; therefore, when the background of the original image is not a white background, an image cropping process may be employed to generate a poster in order to ensure the image quality of the generated poster.

S319, the image processing module in the server sends a matting processing instruction to the AI processing module in the server.

S320, an AI processing module in the server performs matting processing on the original image to obtain a matting result.

S321, an AI processing module in the server sends a matting result to an image capability access gateway in the server.

It should be noted that, the matting processing is performed in the second processing manner to determine the coordinates of the center point of the shooting subject in the original image; when the original image is subjected to image cutting processing, the center point of a cutting frame adopted by the image cutting processing is kept consistent with the center point of a shooting main body; therefore, in the poster generated after the image cutting processing, the shooting subject is located at the center of the poster.

S322, an image processing module in the server calculates the center coordinates of the shooting subject according to the matting result.

Illustratively, the matting result refers to an image area of the subject photographed in the original image.

S323, performing scaling processing on the trimming frame according to the configuration information, so that the size of the trimming frame after scaling meets the minimum size of the coverage target size.

It should be appreciated that in order to enable the size of the image obtained after the image cropping process to fully cover the poster display location; therefore, the scaling process is required to be performed on the trimming frame so that the size of the trimming frame after scaling is equal to the target size of the poster display position; thereby ensuring that the poster generated after the cutting process can be filled in the poster display position; in addition, the size of the scaled cutting frame is enabled to meet the minimum size of the covering target size, so that the poster generated after the image cutting processing through the cutting frame can be completely displayed at the poster display position; if the size of the cutting frame is larger than the target size of the poster display position, the size of the poster generated after the image cutting processing is larger than the size of the poster display position, and the poster cannot be completely displayed at the poster display position; the content in a portion of the poster may have problems with occlusion.

S324, moving the center of the cutting frame according to the center coordinates of the main body, and cutting to generate the poster.

In the embodiment of the application, the center of the cutting frame can be moved, so that the center of the cutting frame and the center of the main body are positioned at the same position, and the main body in the poster generated after cutting is positioned at the center of the poster.

S325, calculating the related information of the main body in the poster.

Illustratively, the subject-related information includes: the area ratio of the main body in the poster, the reserved proportion of the main body after cutting, the coordinate information after cutting and the like.

In the embodiment of the application, the main body related information in the poster is calculated to ensure that the poster generated after cutting meets the preset conditions; for example, the preset conditions include: the poster generated after cutting does not comprise the cut text information; the area occupation ratio of the main body in the poster generated after cutting is larger than a preset threshold value 1, and the retention ratio of the main body is larger than a preset threshold value 2; the area ratio of the main body in the poster and the retention ratio of the main body after cutting are calculated to ensure that the whole main body image information can be included in the poster generated after cutting.

S326, the image processing module in the server sends the relevant information of the main body to the image capability access gateway in the server.

S327, the image capability access gateway in the server determines whether the poster comprises cutting characters according to ocr coordinates.

Optical character recognition (Optical Character Recognition, OCR) refers to a process of scanning text information and then analyzing and processing an image file to obtain text and layout information.

By way of example, the location information of text in the original image may be determined by ocr coordinates in the original image; the coordinate of the cutting frame for cutting is compared with the ocr coordinate to determine whether the poster includes the cutting characters

And S328, if the poster does not comprise the cutting text, the image capability access gateway in the server sends the poster to the storage module.

The storage module in the server is used for storing the generated poster; the stored posters can be screened through the consumption behaviors of the user, and the posters with the user attraction are screened; for example, stored posters may be scored by the consumer's consumption behavior, and posters with score values greater than a preset score threshold may be screened.

Optionally, the foregoing S318 to S328 exemplify a manner of generating a poster by using an image cropping process when the background of the original image is not a white background; under the condition that the background of the original image is not white, generating a poster in an image restoration processing mode; see the relevant description of S207 in fig. 2; and will not be described in detail herein.

Alternatively, before the second stage is performed on the original image, it may be determined whether the original image satisfies a preset image condition; if the original image meets the preset image condition, the background detection can be directly carried out on the original image; if the original image does not meet the preset image condition, preprocessing the original image to obtain a preprocessed image; performing background detection on the preprocessed image; see the relevant descriptions of S201 to S204 in fig. 2, which are not repeated here.

Optionally, the server may further include an odps result table, where the odps result table may be used to record a link address of the data stored in the storage module.

Fig. 7 is a schematic flow chart diagram of another method of generating a poster provided by embodiments of the present application. As shown in fig. 7, the method 400 includes S410 to S440, and S410 to S440 are described in detail below, respectively.

S410, acquiring an original image.

The original image comprises a foreground area and a background area where a shooting subject is located.

By way of example, the original image may refer to an image uploaded by a merchant; alternatively, the manner of acquiring the original image may be referred to as S201 in fig. 2 or S304 in fig. 5, which will not be described herein.

S420, detecting whether the background area is a white background.

Optionally, detecting whether the background area is a white background includes:

and carrying out background detection processing on the original image to generate a background detection result, wherein the background detection result indicates whether the background area is a white background or not.

Optionally, performing background detection processing on the original image to generate a background detection result, including:

determining a target position in the original image, wherein the target position is used for indicating an image edge of the original image;

and generating a background detection result according to the gray value of the pixel of the target position.

determining whether the original image meets a preset image condition;

Detecting whether the background area in the processed original image is a white background.

Alternatively, the implementation of S420 may refer to S203 in fig. 2 or the related description of the second stage (e.g., S304 to S308) in fig. 5, which will not be described herein.

S430, if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster.

Wherein the target poster includes a photographing subject.

In the embodiment of the application, if the background area is a white background, the accuracy of the obtained matting result of the shooting subject is higher by matting the shooting subject in the original image; matching a target poster template corresponding to the target type by shooting the target type of the main body; through the high-accuracy image matting result of the shooting main body and the matched target poster template, high-quality target posters can be ensured to be generated, the attractive force to consumers is enhanced, and the demands of merchants are met.

Optionally, if the background area is a white background, processing the shooting subject by an artificial intelligence algorithm to generate a target poster, including:

if the background area is a white background, performing matting processing on the original image through an artificial intelligence algorithm to obtain a matting result of the shooting subject;

identifying the target type of the shooting subject through artificial intelligence calculation, and matching with a target poster template corresponding to the target type;

and fusing the target poster template and the matting result through artificial intelligence calculation to generate the target poster.

Optionally, identifying the target type of the shooting subject through artificial intelligence calculation and matching the target poster template corresponding to the target type, including:

and identifying the target type of the shooting subject through the AIGC model, and matching the target poster template corresponding to the target type.

Alternatively, the implementation of S430 may refer to S205 and S206 in fig. 2, or the related description of the first processing manner (e.g., S309 to S317) in fig. 5, which is not repeated here.

S440, if the background area is a background except a white background, generating a target poster by performing image processing on the original image.

In the embodiment of the present application, if the background area is a background other than a white background, different area ratios of the foreground area where the subject is located in the original image, the current calculation power requirement, and the definition requirement of the display area of the target poster are taken, and different target processing modes may be adopted to perform image processing on the original image to generate the target poster; according to the scheme, the processing mode for generating the target poster can be flexibly selected based on the size of the shooting subject in the original image; when the target poster is generated, the original image can be fully and reasonably utilized.

Example 1

Optionally, if the background area is a background other than a white background, generating the target poster by performing image processing on the original image includes:

if the background area is a background except a white background, determining a target processing mode according to the area ratio of the foreground area in the original image, wherein the target processing mode comprises an image cutting processing mode or an image restoration processing mode;

and performing image processing on the original image in a target processing mode to generate a target poster.

Optionally, determining the target processing mode according to the area occupation ratio of the foreground region in the original image includes:

if the area occupation ratio is larger than a first preset threshold value, determining that the target processing mode is an image restoration processing mode;

If the area ratio is smaller than or equal to a first preset threshold value, determining that the target processing mode is an image cutting processing mode.

Example 2

If the background area is a background except a white background, determining a target processing mode according to the current calculation force demand, wherein the target processing mode comprises an image cutting processing mode or an image restoration processing mode;

Optionally, determining the target processing mode according to the current computing power requirement includes:

if the current calculation force requirement is greater than a second preset threshold value, determining that the target processing mode is an image cutting processing mode;

if the current calculation force requirement is smaller than or equal to a second preset threshold value, determining that the target processing mode is an image restoration processing mode.

Example 3

if the background area is a background other than the white background, determining a target processing mode according to the definition requirement of the display area of the target poster, wherein the target processing mode comprises an image cutting processing mode or an image repairing processing mode;

Optionally, determining the target processing mode according to the definition of the display area of the target poster includes:

if the definition requirement of the display area of the target poster is greater than a third preset threshold, determining that the target processing mode is an image cutting processing mode;

If the definition requirement of the display area of the target poster is smaller than or equal to a third preset threshold value, determining that the target processing mode is an image restoration processing mode.

Specific implementations of the image trimming processing manner in the above examples 1 to 3 include the following procedures.

Optionally, when the target processing mode is an image cutting processing mode, performing image processing on the original image by using the target processing mode to generate a target poster, including:

determining a target coordinate position of a center point of a shooting subject in an original image;

determining a center point of a cutting frame in an image cutting processing mode according to the target coordinate position;

and cutting the original image based on the center point of the cutting frame and the cutting frame to generate the poster.

Optionally, the area size of the cut frame is determined according to a target size of the display area of the target poster.

Optionally, the foregoing is illustrative of an image cropping process; other existing image restoration methods may also be used, and are not limited in this application.

Specific implementations of the image restoration processing in the above examples 1 to 3 include the following procedures.

Optionally, when the target processing mode is an image restoration processing mode, performing image processing on the original image by the target processing mode to generate a target poster, including:

Acquiring a target size of a display area of a target poster; filling the original image according to the target size, and determining a target image area, wherein the target image area comprises the original image and the filling area, and the size of the target image area is the target size; generating a target mask of the original image in the target image area, wherein the target mask is used for marking the position of the original image in the target image area; and performing image processing on the filling area in the target image area through a deep learning algorithm and a target mask to generate a target poster.

Optionally, the foregoing is illustrative of an image restoration process; other existing image restoration methods may also be used, and are not limited in this application.

Alternatively, the implementation of S440 may refer to S207 in fig. 2, or the related description of the second processing manner (e.g., S318 to S328) in fig. 5, which is not repeated herein.

Alternatively, the embodiments shown in fig. 2 to 7 are illustrated with the background of the original image as a white background; the method of the embodiment of the application is not limited to a white background, and can be applied to other solid-color backgrounds with higher accuracy in matting processing; for example, a light gray background, a gray background, or a solid background that is similar to other white colors may be used in the method for generating a poster provided in the embodiments of the present application.

It should be appreciated that the above illustration is to aid one skilled in the art in understanding the embodiments of the application and is not intended to limit the embodiments of the application to the specific numerical values or the specific scenarios illustrated. It will be apparent to those skilled in the art from the foregoing description that various equivalent modifications or variations can be made, and such modifications or variations are intended to be within the scope of the embodiments of the present application.

The method for generating the poster provided in the embodiments of the present application is described in detail above with reference to fig. 1 to 7; embodiments of the device of the present application will be described in detail below with reference to fig. 8 and 9. It should be understood that the apparatus in the embodiments of the present application may perform the methods in the embodiments of the present application, that is, specific working procedures of the following various products may refer to corresponding procedures in the embodiments of the methods.

Fig. 8 is a schematic structural diagram of a device for generating a poster according to an embodiment of the present application. The apparatus 500 includes an acquisition module 510, a detection module 520, and a processing module 530.

Wherein, the obtaining module 510 is configured to: acquiring an original image, wherein the original image comprises a foreground area and a background area where a shooting subject is located; the detection module 520 is configured to: detecting whether the background area is a white background; the processing module 530 is configured to: if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster, wherein the target poster comprises the shooting subject; and if the background area is the background except the white background, generating the target poster by performing image processing on the original image.

Optionally, as an embodiment, the processing module 530 is specifically configured to:

identifying the target type of the shooting subject through the artificial intelligence calculation, and matching a target poster template corresponding to the target type; and fusing the target poster template and the matting result through the artificial intelligence calculation to generate the target poster.

if the definition requirement of the display area of the target poster is greater than a third preset threshold, determining that the target processing mode is the image cutting processing mode; and if the definition requirement of the display area of the target poster is smaller than or equal to a third preset threshold value, determining that the target processing mode is the image restoration processing mode.

Optionally, as an embodiment, when the target processing manner is the image cropping processing manner, the processing module 530 is specifically configured to:

determining a target coordinate position of a center point of the shooting subject in the original image; determining a center point of a cutting frame in the image cutting processing mode according to the target coordinate position; and cutting the original image based on the center point of the cutting frame and the cutting frame to generate the target poster.

Optionally, as an embodiment, the area size of the trimming frame is determined according to a target size of the display area of the target poster.

Optionally, as an embodiment, when the target processing manner is the image restoration processing manner, the processing module 530 is specifically configured to:

acquiring a target size of a display area of the target poster;

performing filling processing on the original image according to the target size, and determining a target image area, wherein the target image area comprises the original image and a filling area, and the size of the target image area is the target size; generating a target mask of the original image in the target image area, wherein the target mask is used for marking the position of the original image in the target image area; and carrying out image processing on the filling area in the target image area through a deep learning algorithm and the target mask to generate the target poster.

Optionally, as an embodiment, the detection module 520 is specifically configured to:

determining whether the original image meets a preset image condition; if the original image does not meet the preset image condition, preprocessing the original image to obtain a processed original image; and detecting whether the background area in the processed original image is the white background or not.

The aforementioned apparatus 500 for generating a poster is embodied in the form of a functional unit. The term "module" herein may be implemented in software and/or hardware, and is not specifically limited thereto.

For example, a "module" may be a software program, a hardware circuit, or a combination of both that implements the functionality described above. The hardware circuitry may include application specific integrated circuits (application specific integrated circuit, ASICs), electronic circuits, processors (e.g., shared, proprietary, or group processors, etc.) and memory for executing one or more software or firmware programs, merged logic circuits, and/or other suitable components that support the described functions.

Thus, the elements of the examples described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

Fig. 9 shows a schematic structural diagram of a server provided in the present application. The dashed line in fig. 9 indicates that the unit or the module is optional. The server 600 may be used to implement the method of generating a poster described in the above method embodiments.

The server 600 illustratively includes one or more processors 601, which one or more processors 601 may support the server 600 to implement the method of generating a poster in a method embodiment. The processor 601 may be a general purpose processor or a special purpose processor. For example, the processor 601 may be a central processing unit (central processing unit, CPU), digital signal processor (digital signal processor, DSP), application specific integrated circuit (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA), or other programmable logic device such as discrete gates, transistor logic, or discrete hardware components.

By way of example, the processor 601 may be configured to control the server 600, execute software programs, and process data of the software programs. The server 600 may further comprise a communication unit 605 for enabling input (reception) and output (transmission) of signals.

For example, the server 600 may be a chip, the communication unit 605 may be an input and/or output circuit of the chip, or the communication unit 605 may be a communication interface of the chip, which may be an integral part of a terminal device or other server.

For another example, the server 600 may be a terminal device, the communication unit 605 may be a transceiver of the terminal device, or the communication unit 605 may be a transceiver circuit of the terminal device.

For example, the server 600 may include one or more memories 602, on which a program 604 is stored, where the program 604 may be executed by the processor 601 to generate instructions 603, so that the processor 601 performs the method described in the method embodiment above according to the instructions 603.

Optionally, the memory 602 may also have data stored therein. Alternatively, the processor 601 may also read data stored in the memory 602, which may be stored at the same memory address as the program 604, or which may be stored at a different memory address than the program 604.

The processor 601 and the memory 602 may be provided separately or may be integrated together, for example, on a System On Chip (SOC) of the terminal device.

Illustratively, the memory 602 may be used to store the relevant program 604 of the method for generating a poster provided in the embodiments of the present application, and the processor 601 may be used to invoke the relevant program 604 of the method for generating a poster stored in the memory 602 when generating a poster, to execute the method for generating a poster of the embodiments of the present application; for example, an original image is acquired, wherein the original image comprises a foreground area and a background area where a shooting subject is located; detecting whether the background area is a white background; if the background area is a white background, processing the shooting subject through an artificial intelligence algorithm to generate a target poster, wherein the target poster comprises the shooting subject; and if the background area is a background other than the white background, generating the target poster by performing image processing on the original image.

The present application also provides a computer program product which, when executed by the processor 601, implements the method described in any of the method embodiments of the present application.

The computer program product may be stored in the memory 602, for example, the program 604, and the program 604 is finally converted into an executable object file capable of being executed by the processor 601 through preprocessing, compiling, assembling, and linking.

The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a computer, implements a method according to any of the method embodiments of the present application. The computer program may be a high-level language program or an executable object program.

The computer-readable storage medium is, for example, memory 602. The memory 602 may be volatile memory or nonvolatile memory, or the memory 602 may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working processes and technical effects of the apparatus and device described above may refer to corresponding processes and technical effects in the foregoing method embodiments, which are not described in detail herein.

In several embodiments provided in the present application, the disclosed systems, apparatuses, and methods may be implemented in other manners. For example, some features of the method embodiments described above may be omitted, or not performed. The above-described apparatus embodiments are merely illustrative, the division of units is merely a logical function division, and there may be additional divisions in actual implementation, and multiple units or components may be combined or integrated into another system. In addition, the coupling between the elements or the coupling between the elements may be direct or indirect, including electrical, mechanical, or other forms of connection.

It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

In addition, the terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely one association relationship describing the associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In summary, the foregoing description is only a preferred embodiment of the technical solution of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method of generating a poster, comprising:

detecting whether the background area is a white background;

2. The method of claim 1, wherein if the background area is a white background, processing the subject by an artificial intelligence algorithm to generate a target poster comprises:

3. The method according to claim 2, wherein the identifying, by the artificial intelligence algorithm, the target type of the subject and matching the target poster template corresponding to the target type includes:

4. The method according to claim 1, wherein if the background area is a background other than the white background, generating the target poster by performing image processing on the original image, comprises:

5. The method according to claim 1, wherein if the background area is a background other than the white background, the generating the target poster by performing image processing on the original image includes:

6. The method according to claim 1, wherein if the background area is a background other than the white background, generating the target poster by performing image processing on the original image, comprises:

7. The method according to any one of claims 4 to 6, wherein when the target processing mode is the image cropping processing mode, the performing the image processing on the original image by the target processing mode to generate the target poster includes:

8. The method according to any one of claims 4 to 6, wherein when the target processing manner is the image restoration processing manner, the performing the image processing on the original image by the target processing manner to generate the target poster includes:

acquiring a target size of a display area of the target poster;

9. The method according to any one of claims 1 to 6, wherein said detecting whether the background area is a white background comprises:

10. The method according to any one of claims 1 to 6, wherein said detecting whether the background area is a white background comprises:

determining whether the original image meets a preset image condition;