Digital person business card generation method and device, equipment and medium

Abstract

The invention relates to a digital person business card generation method and device, equipment and a medium. The method comprises the steps that a face image of a user and a target style type of a digital person are acquired, the target style type of the digital person is selected by the user from multiple stylized digital human images, and the multiple stylized digital human images at least comprise one of the following stylized digital human images: an art photo, a cartoon style, a very simple style and a business style; based on a preset mapping relation and the target style type, determining a concerned object corresponding to the target style type, the concerned object being related to the five sense organs of the human face; based on the concerned object, performing verification processing on the user face image to obtain a target verification result; and under the condition that the target verification result is that the verification is passed, generating the digital person business card according to the user face image and the target style type. By adopting the method, the digital person business card generation efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment and medium for generating a digital person business card. Background Art

[0002] Digital human business cards are an innovative form of business cards that use digital human images as the core to display user information. In order to achieve a display effect that is closer to the user's image, the user's face image uploaded by the user needs to be verified during the generation of the digital human business card.

[0003] In traditional technology, the regional images corresponding to the key objects in the user's facial image are extracted through image recognition methods, and then each regional image is verified and processed to obtain verification results. When the verification results corresponding to each regional image are all verified, a digital business card is generated.

[0004] However, the current method for generating digital human business cards has the problem of low generation efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, equipment and medium for generating digital human business cards that can improve generation efficiency in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for generating a digital person business card, the method comprising:

[0007] Acquire a user face image and a target style type of a digital human, wherein the target style type of a digital human is selected by the user from a plurality of stylized digital human images, and the plurality of stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style;

[0008] Based on the preset mapping relationship and the target style type, determining the focus object corresponding to the target style type, where the focus object is related to the facial features of the person;

[0009] Based on the object of interest, the user's face image is verified and processed to obtain the target verification result;

[0010] When the target verification result is verified, a digital person business card is generated according to the user's face image and the target style type.

[0011] In one embodiment, the method provided herein performs verification processing on a user's face image based on an object of interest to obtain a target verification result, including:

[0012] When there is an object of interest in the user's face image, obtaining a target area image corresponding to the object of interest based on the user's face image;

[0013] The target area image is verified to obtain a target verification result.

[0014] In one embodiment, the provided method further includes: determining a target feature interval corresponding to the object of interest according to the target style type; in the provided method, performing verification processing on the target area image to obtain a target verification result includes:

[0015] Perform key point positioning processing on the target area image to obtain a target key point sequence;

[0016] Based on the preset feature rules, target key points are selected from the target key point sequence for feature value calculation processing to obtain feature data corresponding to the target area image;

[0017] The characteristic data is compared with the target characteristic interval to obtain the target verification result.

[0018] In one of the embodiments, the method provided has multiple target area images;

[0019] The process of performing verification processing on the target area image in the provided method to obtain the target verification result includes:

[0020] For each target area image, verification processing is performed on the target area image to obtain a verification sub-result;

[0021] According to each verification sub-result, the target verification result is determined.

[0022] In one embodiment, the method provides a process of determining a target verification result according to each verification sub-result, including:

[0023] When all verification sub-results are verified to be passed, the target verification result is determined to be verified to be passed;

[0024] When there is a verification sub-result indicating that the verification fails, the target verification result is determined as verification fails.

[0025] In one embodiment, the method provided further includes:

[0026] When the target verification result is verification failure, the target area image whose verification sub-result is verification success is stored as the historical area image, and the sub-object of interest corresponding to the target area image is stored as the index identifier corresponding to the historical area image.

[0027] In one embodiment, the method provides a process of determining a target verification result according to each verification sub-result, including:

[0028] If there is a verification sub-result that fails the verification, the verification sub-result that fails the verification is used as the target verification sub-result;

[0029] For each target verification sub-result, determining a sub-object of interest corresponding to the target verification sub-result;

[0030] Based on the sub-interest object, the historical region image corresponding to the sub-interest object in the current digital human business card generation cycle is obtained;

[0031] The target verification sub-result is updated to verification passed, and the target area image corresponding to the target verification sub-result in the user's face image is updated to the historical area image;

[0032] The target verification result is determined according to the updated target verification sub-results.

[0033] In a second aspect, the present application further provides a state information determination device, the device comprising:

[0034] A data acquisition module, used to acquire a user's face image and a target style type of a digital human, wherein the target style type of a digital human is selected by the user from a plurality of stylized digital human images, and the plurality of stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style;

[0035] A region determination module, used to determine the focus object corresponding to the target style type based on a preset mapping relationship and the target style type, where the focus object is related to the facial features of the human face;

[0036] The target verification module is used to verify the user's face image based on the object of interest and obtain the target verification result;

[0037] The business card generation module is used to generate a digital person business card according to the user's face image and the target style type when the target verification result is verification passed.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method of the first aspect are implemented.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the first aspect when the computer program is executed by a processor.

[0040] The above-mentioned digital person business card generation method, device, equipment and medium, in one aspect, provides a digital person business card generation method by obtaining a user face image and a target style type of a digital person, wherein the target style type of a digital person is selected by the user from a variety of stylized digital person images, and the various stylized digital person images include at least one of the following: artistic photo, cartoon style, minimalist style, business style; based on a preset mapping relationship and a target style type, determining the object of interest corresponding to the target style type, the object of interest is related to the facial features of the face; based on the object of interest, verifying the user face image to obtain a target verification result; when the target verification result is a verification pass, generating a digital person business card according to the user face image and the target style type. In this way, in the process of verifying the user face image, the corresponding object of interest is determined according to different target style types, and the user face image is verified with emphasis. Compared with the verification process in the prior art, it can effectively reduce the verification scope, reduce the computing resource occupancy rate to improve the verification efficiency, and thus improve the efficiency of the digital person business card generation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] FIG1 is a diagram showing an application environment of a method for generating a digital person's business card in one embodiment;

[0043] FIG2 is a schematic diagram of a flow chart of a method for generating a digital person business card in one embodiment;

[0044] FIG3 is a schematic flow chart of steps for obtaining a target verification result in one embodiment;

[0045] FIG4 is a schematic diagram of a flow chart of a method for generating a digital person business card in another embodiment;

[0046] FIG5 is a structural block diagram of a device for generating a digital person business card in one embodiment;

[0047] FIG. 6 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The digital person business card generation method provided in the embodiment of the present application can be applied in the application environment shown in FIG. 1. The terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 is used to generate or receive a user face image, and send the user face image and the target style type to the server 104, and the server 104 is used to obtain the user face image and the target style type of the digital person, wherein the target style type of the digital person is selected by the user from a variety of stylized digital human images, and the various stylized digital human images include at least one of the following: art photo, cartoon style, minimalist style, business style; based on the preset mapping relationship and the target style type, determine the object of interest corresponding to the target style type, and the object of interest is related to the facial features of the face; based on the object of interest, the user face image is verified and processed to obtain a target verification result; when the target verification result is a verification pass, generate a digital person business card according to the user face image and the target style type.

[0050] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0051] In an exemplary embodiment, as shown in FIG2 , a method for generating a digital person business card is provided, and the method is applied to the server 104 in FIG1 as an example for description, including the following steps 202 to 208. Among them:

[0052] Step 202: Obtain the user's face image and the target style type of the digital human.

[0053] The target style type of the digital human is selected by the user from a variety of stylized digital human images, and the various stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style.

[0054] In the embodiment of the present application, the user face image is an image sent by the terminal 102 to the server 104. The server 104 may send image upload rules to the terminal 102 in advance to improve the efficiency of generating the digital business card. The image upload rules include: the user face image must include the facial image of the digital business card user. Exemplarily, the image upload rules may also include restrictive provisions on the image format, size, size, light or background.

[0055] Optionally, the target style type is a style type selected from multiple style types by the terminal 102. Exemplarily, the style type may also include: fresh style, classical style, cute style and casual style.

[0056] Step 204: determining the object of interest corresponding to the target style type based on the preset mapping relationship and the target style type.

[0057] The focus object is related to the facial features of a person, and different target style types correspond to different focus objects. The mapping relationship may be pre-stored in the server 104, and the server 104 matches one or more focus objects corresponding to the target style type based on the mapping relationship.

[0058] For example, the business style type generally requires the mouth to be closed or slightly open, and the face to be unobstructed to maintain authenticity and solemnity. Therefore, for the business style type, the objects of attention may include the mouth, eyes and head outline, among which the eyes and head outline are used to confirm whether the face is obstructed by glasses, hats, etc.

[0059] As another example, the focus object of the cartoon style may include a face outline; and the focus object of the casual style may include light.

[0060] Step 206: Based on the object of interest, the user's facial image is verified to obtain a target verification result.

[0061] The verification process refers to the process of determining whether the user's face image and the area corresponding to the object of interest in the user's face image meet the verification standard corresponding to the target style type under the target style type. If the verification standard is met, the target verification result is determined as passed; if the verification standard is not met, the target verification result is determined as failed. Under different target style types, the object of interest can be different, and the verification standard for verifying the object of interest can also be different.

[0062] Exemplarily, the verification standards may include image status verification standards and image information verification standards, wherein image status verification may include standards for verifying the format, size and resolution corresponding to the user's facial image; image information verification standards may include standards for verifying the characteristics of the object of interest, such as the degree of mouth opening, eye opening, and facial occlusion.

[0063] Step 208: When the target verification result is that the verification is passed, a digital human business card is generated according to the user's face image and the target style type.

[0064] Among them, the process of generating a digital person business card refers to stylizing the user's face image according to the style processing algorithm corresponding to the target style type to obtain a stylized image in the digital person business card; and fusing the stylized image with the business card template corresponding to the target style type to obtain a digital person business card.

[0065] Exemplarily, obtaining the stylized image may include: performing size adjustment, background separation, color correction, and style enhancement processing on the user's face image in sequence according to a preset business card generation program.

[0066] In another exemplary embodiment, obtaining the stylized image may include: performing image conversion processing on the user's face image using a preset stylized model to obtain the stylized image. The stylized model may be a pre-trained model based on GANs (Generative Adversarial Nets) or a style transfer method.

[0067] In the above-mentioned digital person business card generation method, by obtaining the user's face image and the target style type of the digital person, wherein the target style type of the digital person is selected by the user from a variety of stylized digital human images, and the various stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, business style; based on the preset mapping relationship and the target style type, the focus object corresponding to the target style type is determined, and the focus object is related to the facial features of the face; based on the focus object, the user's face image is verified and processed to obtain the target verification result; when the target verification result is that the verification is passed, the digital person business card is generated according to the user's face image and the target style type. In this way, in the process of verifying the user's face image, the corresponding focus object is determined according to different target style types, and the user's face image is verified and processed with emphasis. Compared with the verification process in the prior art, it can effectively reduce the verification scope, reduce the computing resource occupancy rate to improve the verification efficiency, and thus improve the efficiency of the digital person business card generation method.

[0068] In an exemplary embodiment, based on the embodiment shown in FIG. 2 , as shown in FIG. 3 , the method provided in which the user's face image is verified based on the object of interest and the process of obtaining the target verification result may include:

[0069] Step 302: When there is an object of interest in the user's face image, a target area image corresponding to the object of interest is obtained based on the user's face image.

[0070] The target area image is a specific area corresponding to the object of interest in the user's face image.

[0071] Exemplarily, the object of interest determined based on the target style type is the eyes. The server 104 recognizes that there is an eye object of interest in the user's face image by performing image recognition processing on the user's face image, determines the center and range of the object of interest based on preset image capture rules, and captures the area image corresponding to the object of interest as the target area image.

[0072] In a possible implementation, before acquiring the target area image, the method further includes: determining an image recognition standard according to the target style type; and performing image recognition processing on the user's face image based on the image recognition standard to obtain the target area image. Different target style types correspond to different image recognition standards. Exemplarily, for a casual style, light occlusion such as wearing glasses and hats is allowed, and the image recognition standard may include: when targets such as glasses and hats are identified, determining the recognition result as the existence of an object of interest. Another exemplary example is that for a formal style, occlusion is not allowed, and when targets such as glasses and hats are identified, determining the recognition result as the absence of an object of interest.

[0073] Exemplarily, face position recognition may be performed based on the RetinaFace face detection model to obtain face position information; based on the face position information, a target area image corresponding to the object of interest is obtained.

[0074] Step 304: perform verification processing on the target area image to obtain a target verification result.

[0075] In a possible implementation, the provided method further includes: determining a target feature interval corresponding to the object of interest according to the target style type. Step 304 may further include: performing key point positioning processing on the target area image to obtain a target key point sequence; based on a preset feature rule, selecting target key points from the target key point sequence to perform feature value calculation processing to obtain feature data corresponding to the target area image; and comparing the feature data with the target feature interval to obtain a target verification result.

[0076] Among them, the key point positioning process refers to analyzing and positioning the target area image, determining a group of key points, and forming a target key point sequence. Exemplarily, the object of interest is the mouth, and the key points obtained by performing key point positioning process on the target area image may include the center point of the upper lip, the center point of the lower lip, the left corner of the mouth, and the right corner of the mouth. Another exemplary case is that the object of interest is the eye, and the key points obtained by performing key point positioning process on the target area image may include the center point of the upper edge of the eyelid, the center point of the lower edge of the eyelid, the inner corner of the eye, and the outer corner of the eye.

[0077] The feature rules may include performing linear or nonlinear operations on key points at specific locations to obtain feature data. For example, the feature rules corresponding to the degree of mouth opening and closing may include: using the distance between the center point of the upper lip and the center point of the lower lip to represent the vertical distance of the mouth; using the distance between the left and right corners of the mouth to represent the horizontal width of the mouth; and determining the degree of mouth opening and closing according to the ratio of the vertical distance to the horizontal width.

[0078] Among them, the feature data is compared with the target feature interval. If the feature data meets the target feature interval, the target verification result is determined as verification passed. The feature rules and feature intervals corresponding to different target style types may be different. For example, for the cartoon image style, the mouth is allowed to open and close to a large extent, and the feature interval may be [0.3, 0.8); while for the business style, the mouth is required to be closed or slightly open, and the feature interval may be [0, 0.3).

[0079] In this embodiment, the target area image is verified by means of key point positioning processing to obtain a target verification result, which can accurately identify the feature data corresponding to the target area image and improve the accuracy of the target verification result; the corresponding target feature intervals are determined for different target style types, so that the digital business card generated based on the target verification result is more in line with the target style type.

[0080] In an exemplary embodiment, based on the embodiment shown in FIG3 , there are multiple target area images. In the provided method, the process of performing verification processing on the target area images to obtain the target verification result includes: for each target area image, performing verification processing on the target area image to obtain a verification sub-result; and determining the target verification result according to each verification sub-result.

[0081] Wherein, each target region image is a target region image corresponding to each sub-target of interest in the same target of interest. Exemplarily, if the target of interest is an eye, it includes two sub-targets of interest, the left eye and the right eye, and each sub-target of interest may correspond to a target region image.

[0082] In a possible implementation, the process of determining the target verification result according to each verification sub-result in the provided method may further include: when all verification sub-results are verified to be passed, determining the target verification result as verified to be passed; when there is a verification sub-result that is verified to be failed, determining the target verification result as verified to be failed.

[0083] In a possible implementation, the provided method also includes: when the target verification result is verification failure, storing the target area image with the verification sub-result as verification pass as a historical area image, and storing the sub-object of interest corresponding to the target area image as an index identifier corresponding to the historical area image.

[0084] Exemplarily, in combination with the aforementioned embodiment, when the verification sub-result corresponding to the left eye is verification passed and the verification sub-result corresponding to the right eye is verification failed, the target verification result is verification failed, the target area image corresponding to the left eye is stored as a historical area image, and the left eye sub-focus object is stored as an index identifier corresponding to the historical area image.

[0085] In a possible implementation, when there is a verification sub-result of verification failure, the target verification result is verification failure, each target area image is stored as a reference area image, and the sub-focus object corresponding to each target area image is stored as a reference identifier corresponding to the reference area image. In a subsequent digital human business card generation cycle, the sub-focus object is determined according to the target style type corresponding to the subsequent digital human business card generation cycle, and the verification sub-result corresponding to the sub-focus object is determined based on the target area image and the reference area image corresponding to the sub-focus object. When all verification sub-results are verification passed, the target verification result is determined as verification passed; when there is a verification sub-result of verification failure, the target verification result is determined as verification failure. Among them, the subsequent digital human business card generation cycle is the process of generating a digital human business card when the user of the same digital human business card selects different target style types.

[0086] In an exemplary embodiment, the method provided is a process of determining a target verification result based on each verification sub-result, including: in the event that a verification sub-result is a verification failure, using the verification sub-result that fails the verification as the target verification sub-result; for each target verification sub-result, determining the sub-focus object corresponding to the target verification sub-result; based on the sub-focus object, obtaining the historical area image corresponding to the sub-focus object in the current digital human business card generation cycle; updating the target verification sub-result to a verification pass, and updating the target area image corresponding to the target verification sub-result in the user's face image to a historical area image; and determining the target verification result based on each updated target verification sub-result.

[0087] The current digital human business card generation cycle is the process of generating a digital human business card when the same digital human business card user selects the same target style type. After the target verification result is verified passed and a digital human business card corresponding to the target style type is generated, the current digital human business card generation cycle ends.

[0088] Exemplarily, when the verification sub-result corresponding to the left eye is verification passed and the verification sub-result corresponding to the right eye is verification failed, the verification sub-result corresponding to the right eye is the target verification sub-result, and the sub-attention object corresponding to the target verification sub-result is the right eye. If there is a historical region image corresponding to the sub-attention object of the right eye in the current digital human business card generation cycle, it means that in the current digital human business card generation cycle, there is at least one case where the verification result of the sub-attention object of the right eye is verification passed. The target verification sub-result is updated to verification passed, and the target region image corresponding to the target verification sub-result in the user's face image is updated to the historical region image.

[0089] Optionally, if the historical area image corresponding to the sub-focus object cannot be obtained, indicating that in the current digital human business card generation cycle, the verification of the sub-focus object has not passed, the target verification sub-result will be maintained as verification failure. If there is a target verification sub-result of verification failure, the target verification result will be determined as verification failure.

[0090] Optionally, if multiple historical area images are obtained for a sub-focus object, indicating that multiple verifications of the sub-focus object have been passed in the current digital business card generation cycle, the target verification sub-result is updated to passed verification, and the historical area object corresponding to the sub-focus object in the verification process closest to the current verification process is selected to update the target area image corresponding to the target verification sub-result in the user's face image. Alternatively, each historical area image is input into a preset object reconstruction model, and each historical area image and the object reconstruction model are used for fitting and reconstruction to obtain a reconstructed area image, and the target area image corresponding to the target verification sub-result in the user's face image is updated to the reconstructed area image. Exemplarily, the object reconstruction model can be a reconstruction model based on 3DMM (3D Morphable Model) or PIFu (Pixel-aligned Implicit Function).

[0091] In a possible implementation, the provided method also includes: when the target verification result is verification failure, generating correction prompt information based on the target verification sub-result and sub-focus object, and sending the correction prompt information to the terminal, so that the digital business card user can correct the user's facial image based on the correction prompt information.

[0092] In this embodiment, the target area image with the verification sub-result of failed verification is updated using the historical area image corresponding to the sub-focus object. In this way, in a digital human business card generation cycle, if there is a verification sub-result of passed verification, the verification result corresponding to the sub-focus object can be determined as passed verification, avoiding the problem of digital human business card users repeatedly verifying the same sub-focus object in the same digital human business card generation cycle, thereby improving the generation efficiency of the digital human business card generation method.

[0093] In an exemplary embodiment, as shown in FIG. 4 , a method for generating a digital person business card is provided, and the method is applied to the server 104 in FIG. 1 as an example for description, including the following steps 401 to 408 . Among them:

[0094] Step 401, obtaining a user's face image and a target style type of a digital human.

[0095] The target style type of the digital human is selected by the user from a variety of stylized digital human images, and the various stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style.

[0096] Step 402: determining the object of interest corresponding to the target style type based on the preset mapping relationship and the target style type.

[0097] Among them, the object of attention is related to the facial features.

[0098] Step 403: when there is a focus object in the user's face image, a target area image corresponding to the focus object is obtained according to the user's face image, and there are multiple target area images.

[0099] Step 404: for each target area image, perform verification processing on the target area image to obtain a verification sub-result.

[0100] Among them, step 404 may further include: determining the target feature interval corresponding to the object of interest according to the target style type; the process of obtaining the verification sub-result may include: performing key point positioning processing on the target area image to obtain a target key point sequence; based on preset feature rules, selecting target key points from the target key point sequence to perform feature value calculation processing to obtain feature data corresponding to the target area image; comparing the feature data with the target feature interval to obtain a verification sub-result.

[0101] Step 405: When all verification sub-results are verified to be passed, the target verification result is determined to be verified to be passed.

[0102] Step 406: If there is a verification sub-result that is verification failure, determine the target verification result as verification failure.

[0103] Step 407 , storing the target region image whose verification sub-result is verification passed as a historical region image, and storing the sub-object of interest corresponding to the target region image as an index identifier corresponding to the historical region image.

[0104] Optionally, when there is a verification sub-result that is a verification failure, the verification sub-result that is a verification failure is used as the target verification sub-result; for each target verification sub-result, the sub-focus object corresponding to the target verification sub-result is determined; based on the sub-focus object, the historical area image corresponding to the sub-focus object in the current digital human business card generation cycle is obtained; the target verification sub-result is updated to verification passed, and the target area image corresponding to the target verification sub-result in the user's face image is updated to the historical area image; based on the updated target verification sub-results, the target verification result is determined.

[0105] Step 408: When the target verification result is that the verification is passed, a digital human business card is generated according to the user's face image and the target style type.

[0106] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0107] Based on the same inventive concept, the embodiment of the present application also provides a digital person business card generation device for implementing the digital person business card generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more digital person business card generation device embodiments provided below can refer to the limitations of the digital person business card generation method above, and will not be repeated here.

[0108] In an exemplary embodiment, as shown in FIG. 5 , a digital person business card generation device is provided, comprising: a data acquisition module 502 , an area determination module 504 , a target verification module 506 and a business card generation module 508 , wherein:

[0109] The data acquisition module 502 is used to acquire the user's face image and the target style type of the digital human, wherein the target style type of the digital human is selected by the user from a plurality of stylized digital human images, and the plurality of stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style;

[0110] The region determination module 504 is used to determine the focus object corresponding to the target style type based on the preset mapping relationship and the target style type, where the focus object is related to the facial features of the person;

[0111] The target verification module 506 is used to verify the user's face image based on the object of interest and obtain a target verification result;

[0112] The business card generation module 508 is used to generate a digital person business card according to the user's face image and the target style type when the target verification result is verification passed.

[0113] In one of the embodiments, the target verification module 506 is also used to obtain a target area image corresponding to the object of interest based on the user's face image when there is an object of interest in the user's face image; and perform verification processing on the target area image to obtain a target verification result.

[0114] In one of the embodiments, the data acquisition module 502 is also used to determine the target feature interval corresponding to the object of interest based on the target style type; the target verification module 506 is also used to perform key point positioning processing on the target area image to obtain a target key point sequence; based on preset feature rules, target key points are selected from the target key point sequence for feature value calculation processing to obtain feature data corresponding to the target area image; the feature data is compared with the target feature interval to obtain a target verification result.

[0115] In one embodiment, there are multiple target area images; the target verification module 506 is further used to perform verification processing on each target area image to obtain a verification sub-result; and determine the target verification result according to each verification sub-result.

[0116] In one embodiment, the target verification module 506 is further configured to determine the target verification result as passed verification if all verification sub-results are passed verification; and determine the target verification result as failed verification if there is a verification sub-result that is failed verification.

[0117] In one embodiment, the target verification module 506 is also used to store the target area image with a verification sub-result of passed verification as a historical area image when the target verification result is failed verification, and store the sub-object of interest corresponding to the target area image as an index identifier corresponding to the historical area image.

[0118] In one of the embodiments, the target verification module 506 is also used to, when there is a verification sub-result that is a verification failure, use the verification sub-result that failed the verification as the target verification sub-result; for each target verification sub-result, determine the sub-focus object corresponding to the target verification sub-result; based on the sub-focus object, obtain the historical area image corresponding to the sub-focus object in the current digital human business card generation cycle; update the target verification sub-result to verification passed, and update the target area image corresponding to the target verification sub-result in the user's face image to the historical area image; and determine the target verification result based on the updated target verification sub-results.

[0119] Each module in the above-mentioned digital person business card generation device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0120] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store user face images, target style types and target verification results. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for generating a digital person business card is implemented.

[0121] Those skilled in the art will understand that the structure shown in FIG. 6 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0122] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0123] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0124] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0126] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0127] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a digital person business card, characterized in that: The method comprises: Acquire a user face image and a target style type of a digital human, wherein the target style type of a digital human is selected by the user from a plurality of stylized digital human images, wherein the plurality of stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style; Based on a preset mapping relationship and the target style type, determining an object of interest corresponding to the target style type, where the object of interest is related to facial features of the person; Based on the object of interest, verify the user's face image to obtain a target verification result; When the target verification result is verification passed, a digital person business card is generated according to the user face image and the target style type.

2. The method according to claim 1, characterized in that The step of performing verification processing on the user's face image based on the object of interest to obtain a target verification result includes: In the case where the object of interest exists in the user's facial image, acquiring a target area image corresponding to the object of interest based on the user's facial image; Verification processing is performed on the target area image to obtain the target verification result.

3. The method according to claim 2, characterized in that The method further includes: determining a target feature interval corresponding to the object of interest according to the target style type; The performing verification processing on the target area image to obtain the target verification result includes: Performing key point positioning processing on the target area image to obtain a target key point sequence; Based on a preset feature rule, a target key point is selected from the target key point sequence to perform feature value calculation processing to obtain feature data corresponding to the target area image; The characteristic data is compared with the target characteristic interval to obtain the target verification result.

4. The method according to claim 2, characterized in that: There are multiple target area images; The performing verification processing on the target area image to obtain the target verification result includes: For each of the target area images, verification processing is performed on the target area image to obtain a verification sub-result; The target verification result is determined according to each of the verification sub-results.

5. The method according to claim 4, characterized in that Determining the target verification result according to each of the verification sub-results includes: When all the verification sub-results are verified to be passed, determining the target verification result as verified to be passed; In the case that the verification sub-result is verification failure, the target verification result is determined as verification failure.

6. The method according to claim 5, characterized in that The method further comprises: When the target verification result is verification failure, the target area image whose verification sub-result is verification success is stored as a historical area image, and the sub-object of interest corresponding to the target area image is stored as an index identifier corresponding to the historical area image.

7. The method according to claim 4, characterized in that Determining the target verification result according to each of the verification sub-results includes: In the case where there is a verification sub-result that fails the verification, taking the verification sub-result that fails the verification as the target verification sub-result; For each target verification sub-result, determining a sub-object of interest corresponding to the target verification sub-result; Based on the sub-object of interest, obtaining a historical area image corresponding to the sub-object of interest in the current digital human business card generation cycle; The target verification sub-result is updated to verification passed, and the target area image corresponding to the target verification sub-result in the user face image is updated to the historical area image; The target verification result is determined according to each of the updated target verification sub-results.

8. A device for generating a digital person business card, characterized in that: The device comprises: A data acquisition module, used to acquire a user's face image and a target style type of a digital human, wherein the target style type of a digital human is selected by the user from a plurality of stylized digital human images, wherein the plurality of stylized digital human images include at least one of the following: artistic photo, cartoon style, minimalist style, and business style; A region determination module, configured to determine an object of interest corresponding to the target style type based on a preset mapping relationship and the target style type, wherein the object of interest is related to the facial features of a person; A target verification module, used to verify the user's face image based on the object of interest to obtain a target verification result; The business card generation module is used to generate a digital person business card according to the user face image and the target style type when the target verification result is verification passed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images