Self-service ID card photo generation method, system and readable storage medium

Abstract

The present application provides a method for generating a self-service ID card photo, comprising: obtaining skull image information and a high-definition face image of a target ID card applicant collected by a self-service ID card application machine; obtaining a series of face photos of the target ID card applicant at various previous age stages, and calculating a face aging rate parameter of the target ID card applicant based on the series of face photos; predicting initial predicted photos of the target ID card applicant at multiple subsequent age stages based on the face aging rate parameter, the skull image information, and the high-definition face image; generating at least three target predicted photos of the target ID card applicant at each age stage based on the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target ID card applicant at different fat and thin ranges at the age stage; and generating a standard ID photo using the at least three target predicted photos at each age stage and the high-definition face image.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing technology, and in particular to a method, system and readable storage medium for generating a self-service ID card photo. Background Art

[0002] Currently, facial image collection is required during the self-service ID application process, and the current photo is collected as the ID photo. However, there is a problem: as people age, their faces may change, especially as their fatness changes, the possibility of facial changes is greater. The image information of the ID card collected during the current self-service ID application may not be able to confirm the identity, which is not conducive to searching and confirming the target person.

[0003] Prior art CN108986132B discloses a method for generating a trimap image of a ID photo using a fully convolutional neural network, including the steps of: 1) data input; 2) training a fully convolutional neural network model; 3) using the trained model to segment the input image, which is mainly used for segmenting a human head including the shoulder area with high accuracy, and has the advantages of good noise resistance, simple use, high efficiency, and fast speed, and has achieved good results in the recognition and segmentation of shoulders and clothes. However, this solution cannot associate the impact of user age changes when generating ID photos, which is not convenient for improving the timeliness and accuracy of searching for people based on ID photos in subsequent related work. Therefore, the prior art has defects and is in urgent need of improvement. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the present invention proposes a method and system for generating self-service ID card photos.

[0005] In order to achieve the above object, the present invention provides a method for generating a self-service ID card photo, comprising:

[0006] Obtain the skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine;

[0007] Obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos;

[0008] Predicting initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image;

[0009] Generate at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage;

[0010] At least three target predicted photos for each age group and the high-definition facial image are used to generate a standard ID photo; wherein, the standard ID photo generated by the high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos for each age group and the standard ID photo generated by the high-definition facial image are used to be associated with the fingerprint information of the target applicant and the corresponding weight information and stored in a third-party system.

[0011] Optionally, in the self-service ID card photo generation method described in the embodiment of the present application, the step of obtaining a series of facial photos of the target ID card holder at various previous age stages, and calculating the facial aging speed parameter of the target ID card holder based on the series of facial photos, includes:

[0012] Obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information;

[0013] The series of facial photos are input into a first preset neural network model to obtain facial aging speed parameters of the target applicant.

[0014] Optionally, in the self-service ID card photo generation method described in the embodiment of the present application, the predicting of the initial predicted photos of the target ID card holder at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image includes:

[0015] Obtaining a pre-trained face aging prediction model, and optimizing the face aging prediction model using the face aging speed parameter to obtain a target face aging prediction model;

[0016] The skull image information and the high-definition face image are input into the target face aging prediction model to obtain initial predicted photos of the target applicant at multiple subsequent age groups.

[0017] Optionally, in the self-service ID card photo generation method described in the embodiment of the present application, generating at least three target predicted photos of the target ID card holder at each age stage according to the skull image information and the initial predicted photo includes:

[0018] Generate at least two target predicted photos of the target applicant for each age stage that are fatter than the current age stage according to the skull image information and the initial predicted photos;

[0019] At least two target predicted photos of the target applicant that are thinner than the current one for each age stage are generated based on the skull image information and the initial predicted photo.

[0020] Optionally, in the self-service ID card photo generation method described in the embodiment of the present application, generating at least three target predicted photos of the target ID card holder at each age stage according to the skull image information and the initial predicted photo includes:

[0021] The skull image information and the initial predicted photo are input into a second preset neural network model to obtain target predicted photos of the target applicant at each age stage in different fat and thin ranges.

[0022] Optionally, in the self-service card application photo generation method described in the embodiment of the present application, before acquiring the skull image information and the high-definition face image of the target card applicant collected by the self-service card application machine, the method further includes:

[0023] Obtain the ID card number, fingerprint collection information and face collection information of the target applicant;

[0024] Authentication is performed based on the ID number, fingerprint collection information and face collection information of the target applicant to determine whether the target applicant is the person himself.

[0025] Optionally, in the self-service ID card photo generation method described in the embodiment of the present application, the step of obtaining a series of facial photos of the target ID card holder at various previous age stages includes:

[0026] Obtain a series of facial photos uploaded by the target applicant at various previous age stages.

[0027] In a second aspect, an embodiment of the present application provides a self-service ID card photo generation system, the system comprising: a memory and a processor, the memory comprising a self-service ID card photo generation method program, the self-service ID card photo generation method program when executed by the processor to implement the following steps:

[0028] Obtain the skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine;

[0029] Obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos;

[0030] Predicting initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image;

[0031] Generate at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage;

[0032] At least three target predicted photos for each age group and the high-definition facial image are used to generate a standard ID photo; wherein, the standard ID photo generated by the high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos for each age group and the standard ID photo generated by the high-definition facial image are used to be associated with the fingerprint information of the target applicant and the corresponding weight information and stored in a third-party system.

[0033] Optionally, in the self-service ID card photo generation system described in the embodiment of the present application, the self-service ID card photo generation method program implements the following steps when executed by the processor:

[0034] Obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information;

[0035] The series of facial photos are input into a first preset neural network model to obtain facial aging speed parameters of the target applicant.

[0036] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a self-service ID card photo generation method program. When the self-service ID card photo generation method program is executed by a processor, the steps of a self-service ID card photo generation method described in any one of the above items are implemented.

[0037] As can be seen from the above, the self-service certificate application photo generation method and system provided in the embodiment of the present application obtains the skull image information and high-definition facial image of the target certificate applicant collected by the self-service certificate application machine; obtains a series of facial photos of the target certificate applicant at various previous age stages, and calculates the facial aging rate parameter of the target certificate applicant based on the series of facial photos; predicts the initial predicted photos of the target certificate applicant at multiple subsequent age stages based on the facial aging rate parameter, the skull image information and the high-definition facial image; generates at least three target predicted photos of the target certificate applicant at each age stage based on the skull image information and the initial predicted photos; wherein the at least three predicted photos include the target photographs of the applicant at different fat and thin ranges at the said age stages; generating a standard ID photo by combining at least three target predicted photos at each age stage and the said high-definition facial image; wherein the standard ID photo generated by the said high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos at each age stage and the standard ID photo generated by the said high-definition facial image are used to be associated with the fingerprint information and corresponding weight information of the said target applicant and stored in a third-party system; thereby realizing the prediction of the target predicted photos of the user at various subsequent age stages based on the skull image information and the high-definition facial image of the target applicant, so as to improve the timeliness and accuracy of the search personnel in subsequent related work.

[0038] Additional aspects and advantages of the present invention will be given in part in the following description and, in part, will be obvious from the following description or learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A first flow chart of a method for generating a self-service ID card photo according to the present invention is shown;

[0040] Figure 2 A second flow chart of a method for generating a self-service ID card photo according to the present invention is shown;

[0041] Figure 3 A third flow chart of a method for generating a self-service ID card photo according to the present invention is shown;

[0042] Figure 4 A block diagram of a self-service ID card photo generation system of the present invention is shown. DETAILED DESCRIPTION

[0043] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0045] Figure 1 The present invention provides a flowchart of a self-service ID card photo generation method. The method is used in a self-service ID card machine, which is equipped with a fingerprint collection module, a high-definition camera, and a human skeleton collection lens. The human skeleton collection lens is used to emit electromagnetic waves of a special wavelength to collect human skull information. The self-service ID card photo generation method includes the following steps:

[0046] S100, obtaining skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine;

[0047] S101, obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos;

[0048] S102, predicting initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter and the high-definition face image;

[0049] S103, generating at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage;

[0050] S104. Generate a standard ID photo using at least three predicted target photos for each age group and the high-definition facial image; wherein the standard ID photo generated from the high-definition facial image is used to be set on the ID card, and the standard ID photo generated from at least three predicted target photos for each age group and the standard ID photo generated from the high-definition facial image are associated with the fingerprint information of the target applicant and the corresponding weight information and stored in a third-party system.

[0051] It should be noted that the high-definition face image is the face image data of the user collected by the self-service ID card machine. The series of face photos are photos of the ID card user at different ages stored in the system. The initial predicted photo is a photo of the target ID card user at multiple future ages predicted based on the face aging speed parameter and the high-definition face image. The standard ID photo is the ID photo of the user displayed on the ID card.

[0052] In step S101, each age stage can be a stage of 2 years, and multiple face photos are obtained in each stage. The face aging parameters can include wrinkle generation speed parameters and skin color change speed parameters, etc. The face aging parameters are quantified speed parameters, and the user's future wrinkles and skin color can be predicted and calculated by the speed parameters, but they are not limited to this. When calculating the face aging parameters, a pre-trained neural network model can be used for calculation. The face aging parameters can be calculated by marking the multiple face images with age tags and inputting them into the neural network model.

[0053] In step S102, the initial prediction photo is predicted without considering the change of obesity. The face aging model in the prior art can be used for prediction. However, before prediction, the face aging model needs to be optimized and updated in combination with the face aging speed parameter to improve the accuracy of prediction.

[0054] In step S103, the at least three predicted photos include photos of the target applicant at different fat and thin intervals at the age stage. For example, based on the current face image, the generated multiple target predicted photos include multiple target predicted photos with the same fat and thin levels as the current one, multiple target predicted photos with fatter than the current one by a preset degree, and multiple target predicted photos with thinner than the current one by a preset degree. Each age stage has multiple target predicted photos with different fat and thin levels.

[0055] Among them, in step S104, at least three target prediction photos of each age group and the high-definition face image are cropped and scaled to obtain multiple standard ID photos that meet the ID card processing standards. And the standard ID photo generated by the high-definition face image is used as the main photo set on the ID card. The standard ID photos generated by at least three target prediction photos of each age group are stored in a third-party system, and are used as associated photos of the main photo when searching for people in the future. The main photo and the associated photos are both configured with corresponding fat and thin parameters, so that when searching for people, the fat and thin degree and the photo can be combined to quickly locate the target person, which can improve efficiency.

[0056] In some embodiments, step S101 may include the following sub-steps: obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information; and obtaining the facial aging speed parameter of the target applicant by inputting the series of facial photos into a first preset neural network model. The social account may include QQ, WeChat, Twitter, and Facebook, but is not limited thereto. The first preset neural network model is trained using a sample set of facial images of multiple people at different ages.

[0057] In some embodiments, step S101 may include the following sub-steps: obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information; and obtaining the facial aging speed parameter of the target applicant by inputting the series of facial photos into a first preset neural network model. The first preset neural network model is a trained model used to obtain the facial aging speed parameter of the applicant, input facial photos of each user at different ages, and output the facial aging speed parameter through analysis and calculation by the first preset neural network model.

[0058] In some embodiments, Figure 2 As shown, step S102 may include the following sub-steps: S1021, obtain a pre-trained face aging prediction model, and use the face aging speed parameters to optimize the face aging prediction model to obtain a target face aging prediction model; S1022, input the high-definition face image into the target face aging prediction model to obtain the initial predicted photos of the target applicant in multiple subsequent age groups. Among them, the face aging model is a face aging model pre-trained using big data. Since different people have different aging speeds, it is necessary to optimize and calibrate the corresponding coefficients within the face aging model in combination with the face aging speed parameters of specific personnel, so as to improve the accuracy of the prediction. The face aging model can first classify users, and then call different coefficients according to different categories of users to output the results. During training, users can also be classified first, and then the corresponding coefficients can be optimized by training photos of such users.

[0059] In some embodiments, Figure 3As shown, step S103 may include the following sub-steps: S1031, generating at least two target predicted photos of the target applicant for each age stage that are fatter than the current one according to the skull image information and the initial predicted photos; S1032, generating at least two target predicted photos of the target applicant for each age stage that are thinner than the current one according to the skull image information and the initial predicted photos. It should be noted that the basic facial contour can be determined according to the skull image, the skin and other appearances can be determined according to the age stage, and then prediction and simulation can be performed to simulate fatter or thinner photos based on the basic facial contour. Among them, in step S1031, the human face image fattening and thinning model in the prior art can be used to realize the generation of the corresponding target predicted photos from the initial predicted photos. Of course, the neural network model can be trained based on the sample set. Thereby achieving the generation of the target predicted photos. The sample set includes the skull image of the sample person and multiple photos of different fatness and thinness for training.

[0060] In some embodiments, step S103 may include the following sub-steps: inputting the skull image information and the initial predicted photo into a second preset neural network model to obtain the target predicted photo of the target applicant at each age stage in different fat and thin intervals. The second preset neural network model is pre-trained using big data. The second preset neural network model is a neural network that has undergone a large amount of training and is used to predict photos of users at each age stage in different fat and thin intervals. The skull image information and the initial predicted photo are input, and the target predicted photo of the target applicant at each age stage in different fat and thin intervals is output through analysis and calculation by the second preset neural network model.

[0061] In some embodiments, before step S101, the following steps may be included: obtaining the ID number, fingerprint collection information, and face collection information of the target applicant; performing authentication processing based on the ID number, fingerprint collection information, and face collection information of the target applicant to determine whether the target applicant is the applicant himself. Based on the ID number, the photo and fingerprint of the target applicant when applying for the certificate last time can be obtained, and then matched with the current face collection information and fingerprint collection information. This allows the determination of whether the applicant is the applicant himself.

[0062] As can be seen from the above, the self-service certificate application photo generation method provided in the embodiment of the present application obtains the skull image information and high-definition face image of the target certificate applicant collected by the self-service certificate application machine; obtains a series of face photos of the target certificate applicant at various previous age stages, and calculates the face aging rate parameter of the target certificate applicant based on the series of face photos; predicts the initial predicted photos of the target certificate applicant at multiple subsequent age stages based on the face aging rate parameter, the skull image information and the high-definition face image; generates at least three target predicted photos of the target certificate applicant at each age stage based on the skull image information and the initial predicted photos; wherein the at least three predicted photos include the target certificate applicant photographs of the witness at different fat and thin ranges in the said age stages; generating a standard ID photo by combining at least three target predicted photos at each age stage and the said high-definition face image; wherein the standard ID photo generated by the said high-definition face image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos at each age stage and the standard ID photo generated by the said high-definition face image are used to be associated with the fingerprint information and corresponding weight information of the said target ID holder and stored in a third-party system; thereby realizing the prediction of the target predicted photos of the user at various subsequent age stages based on the skull image information and the high-definition face image of the target ID holder, so as to improve the timeliness and accuracy of the search personnel in the subsequent related work.

[0063] like Figure 4 As shown, the embodiment of the present application provides a self-service ID card photo generation system, the system comprising: a memory 201 and a processor 202, the memory 201 comprising a self-service ID card photo generation method program, the self-service ID card photo generation method program when executed by the processor 202 implements the following steps: obtaining skull image information and high-definition face images of a target ID card issuer collected by a self-service ID card issuer; obtaining a series of face photos of the target ID card issuer at various previous age stages, and calculating a face aging speed parameter of the target ID card issuer based on the series of face photos; predicting the target ID card issuer's age in multiple subsequent age stages based on the face aging speed parameter, the skull image information and the high-definition face image; Initial predicted photo; generating at least three target predicted photos of the target applicant at each age stage based on the skull image information and the initial predicted photo; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stages; generating a standard ID photo by using at least three target predicted photos at each age stage and the high-definition face image; wherein the standard ID photo generated by the high-definition face image is used to be set on the ID card, and the standard ID photos generated by at least three target predicted photos at each age stage and the standard ID photo generated by the high-definition face image are used to be associated with the fingerprint information and corresponding weight information of the target applicant and stored in a third-party system.

[0064] It should be noted that the high-definition face image is the face image data of the user collected by the self-service ID card machine. The series of face photos are photos of the ID card user at different ages stored in the system. The initial predicted photo is a photo of the target ID card user at multiple future ages predicted based on the face aging speed parameter and the high-definition face image. The standard ID photo is the ID photo of the user displayed on the ID card.

[0065] The various age stages can be 2 years as one stage, and multiple face photos are obtained for each stage. The face aging parameters can include wrinkle generation speed parameters and skin color change speed parameters, etc. The face aging parameters are quantified speed parameters, and the user's future wrinkles and skin color can be predicted and calculated by the speed parameters, but they are not limited to this. When calculating the face aging parameters, a pre-trained neural network model can be used for calculation. The face aging parameters can be calculated by marking the multiple face images with age tags and inputting them into the neural network model.

[0066] The initial prediction photo is a prediction without considering the change of obesity. The prediction can be made using the face aging model in the prior art. However, before the prediction, the face aging model needs to be optimized and updated in combination with the face aging speed parameter to improve the accuracy of the prediction.

[0067] The at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage. For example, based on the current face image, the generated multiple target predicted photos include multiple target predicted photos with the same fat and thin levels as the current one, multiple target predicted photos with fatter than the current one by a preset degree, and multiple target predicted photos with thinner than the current one by a preset degree. Each age stage has multiple target predicted photos with different fat and thin levels.

[0068] Among them, at least three target prediction photos of each age group and the high-definition face image are cropped and scaled to obtain multiple standard ID photos that meet the ID card application standards. In addition, the standard ID photo generated by the high-definition face image is used as the main photo set on the ID card. The standard ID photo generated by at least three target prediction photos of each age group is stored in a third-party system and used as an associated photo of the main photo when searching for people in the future. The main photo and the associated photos are both configured with corresponding fat and thin parameters, so that when searching for people, the fat and thin degree and the photo can be combined to quickly locate the target person, which can improve efficiency.

[0069] In some embodiments, when the self-service certificate application photo generation method program is executed by the processor 202, the following steps are implemented: obtaining the social account information of the target certificate applicant, and collecting a series of facial photos of the target certificate applicant at different ages based on the social account information; inputting the series of facial photos into a first preset neural network model to obtain the facial aging speed parameter of the target certificate applicant. Among them, the social account may include QQ, WeChat, Twitter and Facebook, but of course it is not limited to this. The first preset neural network model is trained using a sample set of facial images of multiple people at different ages.

[0070] In some embodiments, when the self-service ID card photo generation method program is executed by the processor 202, the following steps are implemented: obtaining the social account information of the target ID card issuer, and collecting a series of face photos of the target ID card issuer at different ages based on the social account information; inputting the series of face photos into a first preset neural network model to obtain the face aging speed parameter of the target ID card issuer. The first preset neural network model is a trained model, which is used to obtain the face aging speed parameter of the ID card issuer, inputting the face photos of each user at different ages, and outputting the face aging speed parameter through analysis and calculation by the first preset neural network model.

[0071] In some embodiments, when the self-service certificate application photo generation method program is executed by the processor 202, the following steps are implemented: obtaining a pre-trained face aging prediction model, and optimizing the face aging prediction model using the face aging speed parameter to obtain a target face aging prediction model; inputting the high-definition face image into the target face aging prediction model to obtain the initial predicted photos of the target certificate applicant in multiple subsequent age groups. Among them, the face aging model is a face aging model pre-trained using big data. Since different people have different aging speeds, it is necessary to optimize and calibrate the corresponding coefficients within the face aging model in combination with the face aging speed parameters of specific personnel, thereby improving the accuracy of the prediction. The face aging model can first classify users, and then call different coefficients according to different categories of users to output results. During training, users can also be classified first, and then the corresponding coefficients can be optimized by training photos of such users.

[0072] In some embodiments, when the self-service certificate application photo generation method program is executed by the processor 202, the following steps are implemented: generating at least two target prediction photos of the target certificate applicant for each age stage that are fatter than the current one according to the skull image information and the initial prediction photos; generating at least two target prediction photos of the target certificate applicant for each age stage that are thinner than the current one according to the skull image information and the initial prediction photos. It should be noted that the basic facial contour can be determined according to the skull image, the skin and other appearances can be determined according to the age stage, and then prediction and simulation can be performed to simulate fatter or thinner photos based on the basic facial contour. The human face image fattening and thinning model in the prior art can be used to realize the generation of the corresponding target prediction photos from the initial prediction photos. Of course, the neural network model can be trained based on the sample set. Thereby achieving the generation of the target prediction photos. The sample set includes the skull image of the sample person and a plurality of photos of different fatness and thinness for training.

[0073] In some embodiments, when the self-service certificate application photo generation method program is executed by the processor 202, the following steps are implemented: the skull image information and the initial predicted photo are input into the second preset neural network model to obtain the target predicted photo of the target certificate applicant at each age stage in different fat and thin intervals. The second preset neural network model is obtained by pre-training using big data. The second preset neural network model is a neural network that has been trained in large quantities, and is used to predict the photos of the user at each age stage in different fat and thin intervals. The skull image information and the initial predicted photo are input, and the target predicted photo of the target certificate applicant at each age stage is output through analysis and calculation by the second preset neural network model. In some embodiments, when the self-service certificate application photo generation method program is executed by the processor 202, the following steps are implemented: obtaining the ID card number, fingerprint collection information and face collection information of the target certificate applicant; performing authentication processing according to the ID card number, fingerprint collection information and face collection information of the target certificate applicant to determine whether the target certificate applicant is the person himself. The photo and fingerprint of the target certificate applicant at the last time the certificate was applied for can be obtained based on the ID card number, and then matched with the current face collection information and fingerprint collection information. This enables judgment on whether the person is the real person.

[0074] As can be seen from the above, the self-service certificate application photo generation system provided in the embodiment of the present application obtains the skull image information and high-definition facial image of the target certificate applicant collected by the self-service certificate application machine; obtains a series of facial photos of the target certificate applicant at various previous age stages, and calculates the facial aging rate parameter of the target certificate applicant based on the series of facial photos; predicts the initial predicted photos of the target certificate applicant at multiple subsequent age stages based on the facial aging rate parameter, the skull image information and the high-definition facial image; generates at least three target predicted photos of the target certificate applicant at each age stage based on the skull image information and the initial predicted photos; wherein the at least three predicted photos include the target photographs of the applicant at different fat and thin ranges at the said age stages; generating a standard ID photo by combining at least three target predicted photos at each age stage and the said high-definition facial image; wherein the standard ID photo generated by the said high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos at each age stage and the standard ID photo generated by the said high-definition facial image are used to be associated with the fingerprint information and corresponding weight information of the said target applicant and stored in a third-party system; the target predicted photos of the user at various subsequent age stages are predicted by using the skull image information and the high-definition facial image of the target applicant, so as to improve the timeliness and accuracy of the search personnel in subsequent related work.

[0075] On the third aspect, the embodiments of the present application also provide a computer-readable storage medium, wherein the computer-readable storage medium includes a self-service certificate application photo generation method program, and when the self-service certificate application photo generation method program is executed by a processor, the steps of a self-service certificate application photo generation method described in any of the above embodiments are implemented. Specific implementation: obtaining the skull image information and high-definition facial image of the target certificate applicant collected by the self-service certificate application machine; obtaining a series of facial photos of the target certificate applicant at various previous age stages, and calculating the facial aging rate parameters of the target certificate applicant based on the series of facial photos; predicting the initial predicted photos of the target certificate applicant at multiple subsequent age stages based on the facial aging rate parameters, the skull image information, and the high-definition facial image; generating at least three target predicted photos of the target certificate applicant at each age stage based on the skull image information and the initial predicted photos; wherein the at least three predicted photos include the target certificate applicant at the age stage. Photos of different fat and thin ranges; generating a standard ID photo by combining at least three target predicted photos of each age stage and the high-definition face image; wherein, the standard ID photo generated by the high-definition face image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos of each age stage and the standard ID photo generated by the high-definition face image are used to be associated with the fingerprint information and corresponding weight information of the target applicant and stored in a third-party system; the target applicant's skull image information and high-definition face image are used to predict the user's target predicted photos at various subsequent age stages, thereby facilitating the improvement of the timeliness and accuracy of the search personnel in subsequent related work.

[0076] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0077] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0078] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0079] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0080] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0081] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating self-service ID card photos. It is characterized in that include: Obtain the skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine; Obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos; Predicting initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image; Generate at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage; At least three target predicted photos for each age group and the high-definition facial image are used to generate a standard ID photo; wherein, the standard ID photo generated by the high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos for each age group and the standard ID photo generated by the high-definition facial image are used to be associated with the fingerprint information of the target applicant and the corresponding weight information and stored in a third-party system.

2. The self-service ID card photo generation method according to claim 1, It is characterized in that The step of obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos, includes: Obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information; The series of facial photos are input into a first preset neural network model to obtain facial aging speed parameters of the target applicant.

3. The self-service ID card photo generation method according to claim 2, It is characterized in that The predicting of initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image includes: Obtaining a pre-trained face aging prediction model, and optimizing the face aging prediction model using the face aging speed parameter to obtain a target face aging prediction model; The skull image information and the high-definition face image are input into the target face aging prediction model to obtain initial predicted photos of the target applicant at multiple subsequent age groups.

4. The self-service ID card photo generation method according to claim 2, It is characterized in that The step of generating at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photo includes: Generate at least two target predicted photos of the target applicant for each age stage that are fatter than the current age stage according to the skull image information and the initial predicted photos; At least two target predicted photos of the target applicant for each age stage that are thinner than the current one are generated based on the skull image information and the initial predicted photo.

5. The self-service ID card photo generation method according to claim 2, It is characterized in that The step of generating at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photo includes: The skull image information and the initial predicted photo are input into a second preset neural network model to obtain target predicted photos of the target applicant at each age stage in different fat and thin ranges.

6. The self-service ID card photo generation method according to claim 1, It is characterized in that Before obtaining the skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine, the method further includes: Obtain the ID card number, fingerprint collection information and face collection information of the target applicant; Authentication is performed based on the ID number, fingerprint collection information and face collection information of the target applicant to determine whether the target applicant is the person himself.

7. The self-service ID card photo generation method according to claim 1, It is characterized in that The step of obtaining a series of facial photos of the target applicant at various previous ages includes: Obtain a series of facial photos uploaded by the target applicant at various previous age stages.

8. A self-service ID card photo generation system, It is characterized in that The system includes: a memory and a processor, wherein the memory includes a self-service ID card photo generation method program, and when the self-service ID card photo generation method program is executed by the processor, the following steps are implemented: Obtain the skull image information and high-definition face image of the target applicant collected by the self-service card issuing machine; Obtaining a series of facial photos of the target applicant at various previous age stages, and calculating a facial aging speed parameter of the target applicant based on the series of facial photos; Predicting initial predicted photos of the target applicant at multiple subsequent age groups based on the face aging speed parameter, the skull image information, and the high-definition face image; Generate at least three target predicted photos of the target applicant at each age stage according to the skull image information and the initial predicted photos; wherein the at least three predicted photos include photos of the target applicant at different fat and thin ranges at the age stage; At least three target predicted photos for each age group and the high-definition facial image are used to generate a standard ID photo; wherein, the standard ID photo generated by the high-definition facial image is used to be set on the ID card, and the standard ID photo generated by at least three target predicted photos for each age group and the standard ID photo generated by the high-definition facial image are used to be associated with the fingerprint information of the target applicant and the corresponding weight information and stored in a third-party system.

9. The self-service ID card photo generation system according to claim 8, It is characterized in that When the self-service ID card photo generation method program is executed by the processor, the following steps are implemented: Obtaining the social account information of the target applicant, and collecting a series of facial photos of the target applicant at different ages based on the social account information; The series of facial photos are input into a first preset neural network model to obtain facial aging speed parameters of the target applicant.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a self-service ID card photo generation method program. When the self-service ID card photo generation method program is executed by a processor, the steps of a self-service ID card photo generation method as described in any one of claims 1 to 7 are implemented.

Images