Fingerprint image generation method, electronic device, storage medium, and program product

Abstract

This application provides a method for generating a predicted fingerprint image, an electronic device, a storage medium, and a program product. Based on obtaining the original fingerprint image of any target object, the method preprocesses the original fingerprint image to obtain an original fingerprint vector. Further, it obtains a fingerprint prediction model corresponding to the target object, enabling the fingerprint prediction model to output a predicted fingerprint vector based on the input original fingerprint vector, a preset time interval, and a pre-generated target fingerprint variation coefficient. This allows the generation of a corresponding predicted fingerprint image based on the predicted fingerprint vector. This solves the problem of poor accuracy in predicted fingerprint images generated by existing solutions.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method for generating predictive fingerprint images, an electronic device, a storage medium, and a program product. Background Technology

[0002] With the development of fingerprint recognition technology, the identity information of a person can be determined by recognizing the fingerprint image. Since there is a time difference between the fingerprint image acquisition time and the actual usage time, it is necessary to estimate the predicted fingerprint image for the current usage time using the original fingerprint image.

[0003] In existing technologies, a predicted fingerprint image is typically generated by calculating the original fingerprint image based on a preset fingerprint aging formula.

[0004] However, the predicted fingerprint images generated by existing technologies suffer from poor accuracy. Summary of the Invention

[0005] This application provides a method for generating predictive fingerprint images, an electronic device, a storage medium, and a program product to solve the problem of poor accuracy in predictive fingerprint images generated based on existing technologies.

[0006] In a first aspect, embodiments of this application provide a method for generating a predicted fingerprint image, comprising: acquiring an original fingerprint image of any target object; preprocessing the original fingerprint image to obtain a processed original fingerprint image; acquiring an original fingerprint vector from the processed original fingerprint image; acquiring a fingerprint prediction model corresponding to the target object; inputting the original fingerprint vector, a preset time interval, and a pre-generated target fingerprint variation coefficient into the fingerprint prediction model to output a predicted fingerprint vector; and generating a predicted fingerprint image based on the predicted fingerprint vector.

[0007] In one possible implementation, the pre-generation process of the target fingerprint change coefficient includes: determining one or more occupational information of the target object according to the preset time interval; and obtaining the target fingerprint change coefficient according to the one or more occupational information.

[0008] In one possible implementation, obtaining the target fingerprint change coefficient based on the one or more occupational information includes: obtaining the corresponding occupational duration and the corresponding fingerprint change coefficient based on the one or more occupational information; generating an actual fingerprint change coefficient for each occupational information based on the corresponding occupational duration and the corresponding fingerprint change coefficient; and obtaining the target fingerprint change coefficient based on the actual fingerprint change coefficient corresponding to each occupational information.

[0009] In one possible implementation, obtaining the fingerprint prediction model corresponding to the target object includes: determining the target age of the target object based on the acquisition time of the original fingerprint image; and determining the fingerprint prediction model from multiple candidate fingerprint prediction models based on the age range corresponding to the target age.

[0010] In one possible implementation, the original fingerprint image includes a first original fingerprint image and a second original fingerprint image, wherein the first original fingerprint image and the second original fingerprint image are two fingerprint images of the target object at different locations within the same time interval; the preprocessing of the original fingerprint image to obtain a processed original fingerprint image includes: performing noise reduction processing on the first original fingerprint image to generate a first processed image; performing noise reduction processing on the second original fingerprint image to generate a second processed image; obtaining a common image region, a first non-common image region corresponding to the first processed image, and a second non-common image region corresponding to the second processed image based on the image regions of the first processed image and the image regions of the second processed image; if the area of ​​the first non-common image region is smaller than that of the second non-common image region... If the area of ​​the shared image region is equal to or greater than the area of ​​the second non-shared image region, then the area image corresponding to the first non-shared image region is corrected based on the area images of the shared image regions corresponding to the first and second processed images to generate a first corrected image. The processed original fingerprint image is then obtained based on the first corrected image and the second processed image. If the area of ​​the first non-shared image region is greater than or equal to the area of ​​the second non-shared image region, then the area image corresponding to the second non-shared image region is corrected based on the area images of the shared image regions corresponding to the first and second processed images to generate a second corrected image. The processed original fingerprint image is then obtained based on the second corrected image and the first processed image.

[0011] In one possible implementation, the step of correcting the region image corresponding to the first non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a first corrected image includes: generating a first tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correcting the region image corresponding to the first non-public image region based on the first tensor group to generate the first corrected image. The step of correcting the region image corresponding to the second non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a second corrected image includes: generating a second tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correcting the region image corresponding to the second non-public image region based on the second tensor group to generate the second corrected image.

[0012] Secondly, embodiments of this application provide a fingerprint image generation apparatus, comprising:

[0013] The acquisition module is used to acquire the original fingerprint image of any target object;

[0014] The processing module is used to preprocess the original fingerprint image to obtain a processed original fingerprint image; obtain the original fingerprint vector from the processed original fingerprint image; obtain the fingerprint prediction model corresponding to the target object; and input the original fingerprint vector, a preset time interval, and a pre-generated target fingerprint change coefficient into the fingerprint prediction model to output a predicted fingerprint vector.

[0015] The generation module is used to generate a predicted fingerprint image based on the predicted fingerprint vector.

[0016] In one possible implementation, the predictive fingerprint image generation device, during the pre-generation process of the target fingerprint variation coefficient, is specifically used to: determine one or more occupational information of the target object according to the preset time interval; and obtain the target fingerprint variation coefficient according to the one or more occupational information.

[0017] In one possible implementation, when the predictive fingerprint image generation device obtains the target fingerprint change coefficient based on the one or more occupational information, it is specifically used to: obtain the corresponding occupational duration and the corresponding fingerprint change coefficient based on the one or more occupational information; generate an actual fingerprint change coefficient for each occupational information based on the corresponding occupational duration and the corresponding fingerprint change coefficient; and obtain the target fingerprint change coefficient based on the actual fingerprint change coefficient corresponding to each occupational information.

[0018] In one possible implementation, when the processing module acquires the fingerprint prediction model corresponding to the target object, it is specifically used to: determine the target age of the target object based on the acquisition time of the original fingerprint image; and determine the fingerprint prediction model from multiple candidate fingerprint prediction models based on the age range corresponding to the target age.

[0019] In one possible implementation, the original fingerprint image includes a first original fingerprint image and a second original fingerprint image, wherein the first original fingerprint image and the second original fingerprint image are two fingerprint images of the target object at different locations within the same time interval; when the processing module preprocesses the original fingerprint image to obtain a processed original fingerprint image, it specifically performs the following: denoising the first original fingerprint image to generate a first processed image; denoising the second original fingerprint image to generate a second processed image; and, based on the image regions of the first processed image and the image regions of the second processed image, obtaining a common image region, a first non-common image region corresponding to the first processed image, and a second non-common image region corresponding to the second processed image; if the area of ​​the first non-common image region is smaller than the first processed image region, the processing module performs the following: If the area of ​​the second non-public image region is greater than or equal to the area of ​​the second non-public image region, then the area image corresponding to the first non-public image region is corrected based on the area images of the public image regions corresponding to the first and second processed images to generate a first corrected image; the processed original fingerprint image is obtained based on the first corrected image and the second processed image; if the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, then the area image corresponding to the second non-public image region is corrected based on the area images of the public image regions corresponding to the first and second processed images to generate a second corrected image; the processed original fingerprint image is obtained based on the second corrected image and the first processed image.

[0020] In one possible implementation, when the processing module corrects the region image corresponding to the first non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a first corrected image, it is specifically used to: generate a first tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correct the region image corresponding to the first non-public image region based on the first tensor group to generate the first corrected image. When the processing module corrects the region image corresponding to the second non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a second corrected image, it is specifically used to: generate a second tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correct the region image corresponding to the second non-public image region based on the second tensor group to generate the second corrected image.

[0021] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0022] The memory stores computer-executed instructions;

[0023] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0024] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0025] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0026] The predictive fingerprint image generation method, electronic device, storage medium, and program product provided in this application, based on the acquisition of the original fingerprint image of any target object, preprocess the original fingerprint image to obtain the original fingerprint vector from the processed original fingerprint image; further, obtain the fingerprint prediction model corresponding to the target object, so that the fingerprint prediction model outputs the predicted fingerprint vector according to the input original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient; thereby generating the corresponding predicted fingerprint image based on the predicted fingerprint vector; that is, it solves the problem of poor accuracy of the predicted fingerprint image generated by the existing technology. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0028] Figure 1 A schematic diagram illustrating a scenario for the predictive fingerprint image generation method provided in this application;

[0029] Figure 2 A flowchart illustrating a method for generating a predicted fingerprint image according to an embodiment of this application;

[0030] Figure 3 A flowchart of a method for generating a predicted fingerprint image provided in another embodiment of this application;

[0031] Figure 4 This is a schematic diagram of the structure of a predictive fingerprint image generation apparatus provided in one embodiment of this application;

[0032] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0033] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] The technical solution of this application involves the collection, storage, use, processing, transmission, provision and disclosure of user personal information and data, which comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0036] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0037] With the development of fingerprint recognition technology, the identity of a person can be determined by recognizing their fingerprint image. Since there is a time difference between the time a fingerprint image is acquired and the time it is actually used, it is necessary to estimate the predicted fingerprint image for the current usage time from the original acquired fingerprint image. In existing technologies, a preset fingerprint aging formula is typically used to calculate the predicted fingerprint image from the original fingerprint image, which is then used to determine the person's identity. However, the predicted fingerprint images generated by existing technologies suffer from poor accuracy.

[0038] The application scenarios of the embodiments of this application are explained below:

[0039] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0040] Figure 1 This is a schematic diagram illustrating a scenario for the predictive fingerprint image generation method provided in this application, such as... Figure 1 As shown, the specific application scenario of this application is to generate a predicted fingerprint image of the target object at a preset age based on the fingerprint image of the target object at a certain age. The execution subject of the method provided in this application embodiment can be an electronic control unit, a terminal device, or a server. Taking a terminal device as the execution subject, for example, after obtaining the original fingerprint image of the target object at age 12, the terminal device, according to the predicted fingerprint image generation method provided in this application embodiment, can output the corresponding predicted fingerprint vector by calling the fingerprint prediction model, according to the preset time interval of 18 years, combined with the pre-generated target fingerprint change coefficient, and then obtain the predicted fingerprint image of the target object at age 30 based on the predicted fingerprint vector.

[0041] Figure 2 A flowchart of a predictive fingerprint image generation method provided in one embodiment of this application is shown below. Figure 2 As shown, the execution subject of the predicted fingerprint image generation method provided in this embodiment can be an electronic control unit, a terminal device, or a server. For example, this embodiment uses a terminal device as the execution subject of the method. The predicted fingerprint image generation method provided in this embodiment includes the following steps:

[0042] Step S101: Obtain the original fingerprint image of any target object.

[0043] Step S102: Preprocess the original fingerprint image to obtain the processed original fingerprint image.

[0044] For example, the terminal device receives the original fingerprint image of any target object input by the user, and then preprocesses the original fingerprint image, such as binarizing the original fingerprint image, to process the color original fingerprint image or grayscale original fingerprint image into a black and white original fingerprint image, that is, to obtain the processed original fingerprint image, that is, the processed original fingerprint image is a black and white original fingerprint image; wherein, the algorithm used for binarization processing is any binarization algorithm that can convert the color or grayscale original fingerprint image into a black and white original fingerprint image.

[0045] Step S103: Obtain the original fingerprint vector from the processed original fingerprint image.

[0046] For example, after obtaining the processed original fingerprint image, the processed original fingerprint image is encoded to obtain the corresponding original fingerprint vector.

[0047] Step S104: Obtain the fingerprint prediction model corresponding to the target object.

[0048] For example, a fingerprint prediction model is obtained based on the object group to which the target object belongs. Specifically, for example, the fingerprint pattern features of different object groups are different. Therefore, when training the fingerprint prediction model, multiple fingerprint prediction models are trained according to different object groups. Then, based on the object features of the target object, the object group to which the target object belongs is determined, and the fingerprint prediction model corresponding to the object group is determined, thus obtaining the fingerprint prediction model corresponding to the target object.

[0049] In one possible implementation, step S104 is specifically implemented as follows:

[0050] Step S1041: Determine the target age of the target object based on the acquisition time of the original fingerprint image.

[0051] Step S1042: Based on the age range corresponding to the target age, determine the fingerprint prediction model from multiple candidate fingerprint prediction models.

[0052] For example, based on the acquisition time of the original fingerprint image and the birth time of the target object, the target age of the target object is determined, i.e., the age of the target object at the time the original fingerprint image was acquired. Then, based on the age range corresponding to the target age, the corresponding fingerprint prediction model can be determined from multiple candidate fingerprint prediction models. Specifically, for example, the candidate fingerprint prediction models include a first age range fingerprint prediction model, a second age range fingerprint prediction model, a third age range fingerprint prediction model, and a fourth age range fingerprint prediction model. Then, based on the target age of the target object determined by the acquisition time of the original fingerprint image, the age range to which the target age belongs is determined. For example, if the target age belongs to the second age range, then based on the second age range, the corresponding prediction model is selected from the first age range fingerprint prediction model, the second age range fingerprint prediction model, the third age range fingerprint prediction model, and the fourth age range fingerprint prediction model, thus determining the corresponding fingerprint prediction model, i.e., the determined fingerprint prediction model is the second age range fingerprint prediction model.

[0053] In this embodiment, the fingerprints of people of different ages change to varying degrees over the same time span. For example, the change in fingerprints of target subject A at age 10 and age 30 is change_1, and the change in fingerprints of target subject B at age 20 and age 40 is change_2. Although the time span is 20 years, the change_1 and change_2 are different. Therefore, the fingerprint prediction model determined based on the age range to which the target subject's target age belongs can accurately generate predicted fingerprint images in subsequent steps because it takes into account the influence of age differences.

[0054] Step S105: Input the original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient into the fingerprint prediction model to output the predicted fingerprint vector.

[0055] For example, after obtaining the original fingerprint vector and the fingerprint prediction model, the preset time interval input by the user is obtained, and the target fingerprint change coefficient is generated based on the preset time interval and the object information of the target object; then the fingerprint prediction model can output the corresponding predicted fingerprint vector according to the input original fingerprint vector, the preset time interval and the pre-generated target fingerprint change coefficient.

[0056] In one possible implementation, the pre-generation process of the target fingerprint variation coefficient includes: obtaining first geographical location information and acquisition time when the original fingerprint image was acquired based on the object information of the target object; then determining corresponding first humidity information based on the first geographical location information and acquisition time; then determining the current (or possible) second geographical location information of the target object based on a preset time interval and the object information of the target object; determining an estimated time based on the preset time interval; then determining corresponding second humidity information based on the second geographical location information and the estimated time; and finally generating the target fingerprint variation coefficient based on the first humidity information and the second humidity information. It is understood that... Within the same time interval, the fingerprint patterns of the same target object differ under dry and wet conditions. Therefore, for example, when the difference between the first and second humidity information is less than a preset threshold, the target fingerprint change coefficient is num_1. That is, when the fingerprint prediction model generates the predicted fingerprint vector, the target fingerprint change coefficient num_1 is used to calculate the influence of humidity on the fingerprint pattern. When the difference between the first and second humidity information is greater than the preset threshold, the target fingerprint change coefficient is num_2. That is, when the fingerprint prediction model generates the predicted fingerprint vector, the target fingerprint change coefficient num_2 is used to calculate the influence of humidity on the fingerprint pattern.

[0057] In another possible implementation, the pre-generation process of the target fingerprint variation coefficients includes:

[0058] Step S1001: Determine one or more occupational information of the target object according to a preset time interval.

[0059] Step S1002: Obtain the target fingerprint variation coefficient based on one or more occupational information.

[0060] For example, within a preset time interval, the target object may engage in one or more jobs. Due to different job environments and job content, the degree of wear and tear on the fingerprint is different. Therefore, based on the preset time interval, the job information corresponding to the one or more jobs engaged in by the target object is determined. Then, based on the determined job information, the fingerprint change coefficient of each job information is obtained. Furthermore, based on the fingerprint change coefficient corresponding to each job information, the target fingerprint change coefficient can be calculated. Specifically, for example, with a preset time interval of 20 years, the occupations of the target object are determined to include occupation job_1, occupation job_2, and occupation job_3. The occupational information corresponding to occupation job_1 is info_1, the occupational information corresponding to occupation job_2 is info_2, and the occupational information corresponding to occupation job_3 is info_3. Then, the fingerprint change coefficient data_1 is obtained based on the occupational information info_1, the fingerprint change coefficient data_2 is obtained based on the occupational information info_2, and the fingerprint change coefficient data_3 is obtained based on the occupational information info_3. Further, the target fingerprint change coefficient is calculated based on the fingerprint change coefficients data_1, fingerprint change coefficients data_2, and fingerprint change coefficients data_3, for example, by summing.

[0061] Furthermore, in another possible implementation, step S1002 includes the following specific steps:

[0062] Step S10021: Based on one or more occupational information, obtain the corresponding occupational duration and the corresponding fingerprint change coefficient.

[0063] Step S10022: For each occupational information, generate the actual fingerprint change coefficient based on the corresponding occupational duration and the corresponding fingerprint change coefficient.

[0064] Step S10023: Obtain the target fingerprint change coefficient based on the actual fingerprint change coefficient corresponding to each occupational information.

[0065] For example, since different occupational environments and occupational content result in different degrees of wear and tear on fingerprints, and the duration of each occupation also affects the degree of wear and tear, based on one or more occupational information determined for the target object, the corresponding occupational duration and corresponding fingerprint change coefficient are determined respectively; then, based on the occupational duration of the target object in each occupation and the corresponding fingerprint change coefficient, the actual fingerprint change coefficient corresponding to each occupational information is calculated, and then the target fingerprint change coefficient is calculated.

[0066] Specifically, for example, with a preset time interval of 20 years, the occupations of the target object are determined to include occupations job_1, job_2, and job_3. The occupational information corresponding to job_1 is info_1, the occupational information corresponding to job_2 is info_2, and the occupational information corresponding to job_3 is info_3. Then, based on the occupational information info_1, the corresponding fingerprint change coefficient data_1 is obtained, and the corresponding occupational duration is time_1; based on the occupational information info_2, the corresponding fingerprint change coefficient data_2 is obtained, and the corresponding occupational duration is time_2; based on the occupational information info_3, the corresponding fingerprint change coefficient data_3 is obtained, and the corresponding occupational duration is time_3. 3; Then, based on the occupational engagement duration time_1 and fingerprint change coefficient data_1, the actual fingerprint change coefficient r_data_1 corresponding to occupational information info_1 is calculated; based on the occupational engagement duration time_2 and fingerprint change coefficient data_2, the actual fingerprint change coefficient r_data_2 corresponding to occupational information info_2 is calculated; based on the occupational engagement duration time_3 and fingerprint change coefficient data_3, the actual fingerprint change coefficient r_data_3 corresponding to occupational information info_3 is calculated; furthermore, based on the actual fingerprint change coefficients r_data_1, r_data_2, and r_data_3, the target fingerprint change coefficient is calculated, for example, by summing.

[0067] In this embodiment, by obtaining one or more occupations that the target object engages in within a preset time interval, the influence of each occupation on the fingerprint is determined. Then, based on all the occupations that the target object engages in within the preset time interval, a target fingerprint change coefficient is generated. This enables the fingerprint prediction model to output an accurate predicted fingerprint vector based on the original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient.

[0068] Step S106: Generate a predicted fingerprint image based on the predicted fingerprint vector.

[0069] For example, after obtaining the predicted fingerprint vector output by the fingerprint prediction model, the terminal device can generate the corresponding predicted fingerprint image by encoding the predicted fingerprint vector.

[0070] The fingerprint prediction model training process includes: acquiring the first fingerprint vector corresponding to the first fingerprint image of the training object, the second fingerprint vector corresponding to the second fingerprint image of the training object, and the pre-generated target fingerprint change coefficient, wherein the time difference between the acquisition time of the first fingerprint image and the acquisition time of the second fingerprint image is N years; then, the initial fingerprint prediction model outputs a test fingerprint vector based on the input time difference N years, the first fingerprint vector, and the pre-generated target fingerprint change coefficient; then, the spatial distance between the test fingerprint vector and the second fingerprint vector is calculated, and the calculated spatial distance is used as the model loss to optimize and train the initial fingerprint prediction model to obtain the fingerprint prediction model corresponding to the target object obtained in this embodiment of the application.

[0071] As an example, in one possible implementation, the core architecture of the fingerprint prediction model is based on the ResNet-101 network model.

[0072] Optionally, the dataset used in the model training process of the fingerprint prediction model is determined from the national standard fingerprint database.

[0073] In this embodiment, based on the acquisition of the original fingerprint image of any target object, the original fingerprint image is preprocessed to obtain the original fingerprint vector from the processed original fingerprint image; further, a fingerprint prediction model corresponding to the target object is obtained so that the fingerprint prediction model outputs a predicted fingerprint vector based on the input original fingerprint vector, a preset time interval, and a pre-generated target fingerprint change coefficient; thereby generating a corresponding predicted fingerprint image based on the predicted fingerprint vector; thus solving the problem of poor accuracy of predicted fingerprint images generated by existing solutions.

[0074] Figure 3 A flowchart of a predictive fingerprint image generation method provided in another embodiment of this application is shown below. Figure 3 As shown, the predictive fingerprint image generation method provided in this embodiment... Figure 2 Based on the fingerprint image generation method provided in the illustrated embodiment, step S102 is further refined. Therefore, the fingerprint image generation method provided in this embodiment includes the following steps:

[0075] Step S201: Obtain the original fingerprint image of any target object. The original fingerprint image includes a first original fingerprint image and a second original fingerprint image. The first original fingerprint image and the second original fingerprint image are two fingerprint images of the target object at different locations within the same time interval.

[0076] Step S202: Denoise reduction processing is performed on the first original fingerprint image to generate a first processed image.

[0077] Step S203: Denoise the second original fingerprint image to generate a second processed image.

[0078] For example, the terminal device performs noise reduction processing on the first original fingerprint image and the second original fingerprint image respectively to reduce noise in the images, thereby obtaining the first processed image and the second processed image; wherein, the noise reduction processing includes noise reduction using a median filter and noise reduction using a mean filter.

[0079] Step S204: Based on the image regions of the first processed image and the second processed image, obtain the common image region, the first non-common image region corresponding to the first processed image, and the second non-common image region corresponding to the second processed image.

[0080] Step S205: Determine the relationship between the area of ​​the first non-public image region and the area of ​​the second non-public image region.

[0081] For example, after obtaining the first processed image and the second processed image, the image regions of the first processed image and the second processed image are divided according to the image features in the image regions of the first processed image and the image regions of the second processed image, thereby obtaining a common image region corresponding to both the first and second processed images, a first non-common image region corresponding to the first processed image, and a second non-common image region corresponding to the second processed image. Further, the area of ​​the first non-common image region is calculated to obtain the area of ​​the first non-common image region, and the area of ​​the second non-common image region is calculated to obtain the area of ​​the second non-common image region. Then, the size relationship between the areas of the first and second non-common image regions is determined.

[0082] Step S206: If the area of ​​the first non-public image region is smaller than the area of ​​the second non-public image region, then the area image corresponding to the first non-public image region is corrected according to the area image of the public image region corresponding to the first processed image and the area image of the public image region corresponding to the second processed image, and a first corrected image is generated.

[0083] Step S207: Based on the first corrected image and the second processed image, the processed original fingerprint image is obtained.

[0084] For example, if the area of ​​the first non-public image region is smaller than the area of ​​the second non-public image region, then the second processed image is used as the reference image, that is, the area image of the public image region corresponding to the second processed image is used as the reference image. Then, based on the degree of distortion of the area image of the public image region corresponding to the first processed image relative to the area image of the public image region corresponding to the second processed image, the area image corresponding to the first non-public image region is corrected to generate a first corrected image. Further, based on the first corrected image and the second processed image, image fusion and stitching are performed to obtain the processed original fingerprint image.

[0085] In one possible implementation, step S206 is specifically implemented as follows:

[0086] Step S2061: Generate a first tensor group based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image.

[0087] Step S2062: Based on the first tensor group, the region image corresponding to the first non-common image region is corrected to generate the first corrected image.

[0088] For example, based on the fact that the area of ​​the first non-public image region is smaller than the area of ​​the second non-public image region, the region image of the public image region corresponding to the second processed image is used as a reference image. Then, for the same fingerprint feature point, the vertical and horizontal distortion values ​​of the pixel position of the region image of the public image region corresponding to the first processed image are calculated relative to the pixel position of the region image of the public image region corresponding to the second processed image. Then, based on the vertical and horizontal distortion values ​​corresponding to each fingerprint feature point, a first tensor set is generated. Further, based on the changing trend of each distortion coefficient in the first tensor set, a first prediction tensor set corresponding to the first non-public image region is generated. Then, based on the first prediction tensor set, the pixel position in the region image corresponding to the first non-public image region is corrected to generate a first corrected image.

[0089] Step S208: If the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, then the area image corresponding to the second non-public image region is corrected based on the area image of the public image region corresponding to the first processed image and the area image of the public image region corresponding to the second processed image, to generate a second corrected image.

[0090] Step S209: Based on the second corrected image and the first processed image, obtain the processed original fingerprint image.

[0091] For example, if the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, then the first processed image is used as the reference image, that is, the area image of the public image region corresponding to the first processed image is used as the reference image. Then, based on the degree of distortion of the area image of the public image region corresponding to the second processed image relative to the area image of the public image region corresponding to the first processed image, the area image corresponding to the second non-public image region is corrected to generate a second corrected image. Further, the second corrected image and the first processed image are fused and stitched together to obtain the processed original fingerprint image.

[0092] In one possible implementation, step S208 is specifically implemented as follows:

[0093] Step S2081: Generate a second tensor group based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image.

[0094] Step S2082: Based on the second tensor group, correct the region image corresponding to the second non-common image region to generate a second corrected image.

[0095] For example, based on the fact that the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, the region image of the public image region corresponding to the first processed image is used as a reference image. Then, for the same fingerprint feature point, the vertical and horizontal distortion values ​​of the pixel position of the region image of the public image region corresponding to the second processed image are calculated relative to the pixel position of the region image of the public image region corresponding to the first processed image. Then, based on the vertical and horizontal distortion values ​​corresponding to each fingerprint feature point, a second tensor set is generated. Further, based on the changing trend of each distortion coefficient in the second tensor set, a second prediction tensor set corresponding to the second non-public image region is generated. Then, based on the second prediction tensor set, the pixel position in the region image corresponding to the second non-public image region is corrected to generate a second corrected image.

[0096] In this embodiment, two fingerprint images of the target object at different locations within the same time interval are distorted and stitched together to obtain a fused fingerprint image, which is the processed original fingerprint image. By distorting and stitching the images together, the image information of the fingerprint image is expanded, providing rich data for the subsequent steps to generate a predicted fingerprint image, and improving the prediction accuracy of the generated predicted fingerprint image.

[0097] Step S210: Obtain the original fingerprint vector from the processed original fingerprint image.

[0098] Step S211: Obtain the fingerprint prediction model corresponding to the target object.

[0099] Step S212: Input the original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient into the fingerprint prediction model to output the predicted fingerprint vector.

[0100] Step S213: Generate a predicted fingerprint image based on the predicted fingerprint vector.

[0101] In this embodiment, the implementation of steps S210-S213 is the same as that in this application. Figure 2 The implementation methods of steps S103-S106 in the illustrated embodiment are the same, and will not be described in detail here.

[0102] Figure 4 This is a schematic diagram of the structure of a predictive fingerprint image generation apparatus provided in one embodiment of this application, as shown below. Figure 4 As shown, the predictive fingerprint image generation device 3 provided in this embodiment includes:

[0103] The acquisition module 31 is used to acquire the original fingerprint image of any target object;

[0104] Processing module 32 is used to preprocess the original fingerprint image to obtain the processed original fingerprint image; obtain the original fingerprint vector from the processed original fingerprint image; obtain the fingerprint prediction model corresponding to the target object; and input the original fingerprint vector, the preset time interval and the pre-generated target fingerprint change coefficient into the fingerprint prediction model to output the predicted fingerprint vector.

[0105] The generation module 33 is used to generate a predicted fingerprint image based on the predicted fingerprint vector.

[0106] In one possible implementation, the fingerprint image generation device 3, in the process of pre-generating the target fingerprint variation coefficient, is specifically used to: determine one or more occupational information of the target object according to a preset time interval; and obtain the target fingerprint variation coefficient based on the one or more occupational information.

[0107] In one possible implementation, when the fingerprint image generation device 3 obtains the target fingerprint change coefficient based on one or more occupational information, it is specifically used to: obtain the corresponding occupational duration and the corresponding fingerprint change coefficient based on one or more occupational information; generate the actual fingerprint change coefficient for each occupational information based on the corresponding occupational duration and the corresponding fingerprint change coefficient; and obtain the target fingerprint change coefficient based on the actual fingerprint change coefficient corresponding to each occupational information.

[0108] In one possible implementation, when the processing module 32 acquires the fingerprint prediction model corresponding to the target object, it is specifically used to: determine the target age of the target object based on the acquisition time of the original fingerprint image; and determine the fingerprint prediction model from multiple candidate fingerprint prediction models based on the age range corresponding to the target age.

[0109] In one possible implementation, the original fingerprint image includes a first original fingerprint image and a second original fingerprint image, which are two fingerprint images of the target object at different locations within the same time interval. When the processing module 32 preprocesses the original fingerprint image to obtain a processed original fingerprint image, it specifically performs the following: noise reduction processing on the first original fingerprint image to generate a first processed image; noise reduction processing on the second original fingerprint image to generate a second processed image; and, based on the image regions of the first and second processed images, obtains a common image region, a first non-common image region corresponding to the first processed image, and a second non-common image region corresponding to the second processed image. If the area of ​​the first non-common image region is small... For the area of ​​the second non-public image region, the region image corresponding to the first non-public image region is corrected based on the region images of the public image regions corresponding to the first processed image and the second processed image to generate a first corrected image; the original fingerprint image is obtained based on the first corrected image and the second processed image; if the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, the region image corresponding to the second non-public image region is corrected based on the region images of the public image regions corresponding to the first processed image and the second processed image to generate a second corrected image; the original fingerprint image is obtained based on the second corrected image and the first processed image.

[0110] In one possible implementation, when processing module 32 corrects the region image corresponding to the first non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a first corrected image, it is specifically used to: generate a first tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correct the region image corresponding to the first non-public image region based on the first tensor group to generate the first corrected image. When processing module 32 corrects the region image corresponding to the second non-public image region based on the region images of the common image regions corresponding to the first processed image and the second processed image to generate a second corrected image, it is specifically used to: generate a second tensor group based on the region images of the common image regions corresponding to the first processed image and the second processed image; and correct the region image corresponding to the second non-public image region based on the second tensor group to generate the second corrected image.

[0111] The acquisition module 31, processing module 32, and generation module 33 are connected sequentially. The predictive fingerprint image generation device 3 provided in this embodiment can perform the following... Figures 2-3 The technical solutions of any of the method embodiments shown are similar in implementation principle and technical effect, and will not be described again here.

[0112] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0113] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0114] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0115] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0116] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0117] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0118] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0119] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0120] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0121] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0122] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0123] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0125] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0127] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for predicting fingerprint images, characterized in that, include: Obtain the raw fingerprint image of any target object; The original fingerprint image is preprocessed to obtain the processed original fingerprint image; The original fingerprint vector is obtained from the processed original fingerprint image; Obtain the fingerprint prediction model corresponding to the target object; The original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient are input into the fingerprint prediction model to output the predicted fingerprint vector. Based on the predicted fingerprint vector, a predicted fingerprint image is generated; The pre-generation process of the target fingerprint variation coefficient includes: Based on the preset time interval, determine one or more pieces of occupational information of the target object; The target fingerprint variation coefficient is obtained based on the one or more occupational information.

2. The method according to claim 1, characterized in that, The step of obtaining the target fingerprint variation coefficient based on the one or more occupational information includes: Based on the one or more occupational information, the corresponding occupational duration and the corresponding fingerprint change coefficient are obtained; For each occupational information, the actual fingerprint change coefficient is generated based on the corresponding occupational duration and the corresponding fingerprint change coefficient. The target fingerprint change coefficient is obtained based on the actual fingerprint change coefficient corresponding to each occupational information.

3. The method according to claim 1, characterized in that, The step of obtaining the fingerprint prediction model corresponding to the target object includes: The target age of the target object is determined based on the acquisition time of the original fingerprint image; Based on the age range corresponding to the target age, the fingerprint prediction model is determined from multiple candidate fingerprint prediction models.

4. The method according to any one of claims 1-3, characterized in that, The original fingerprint image includes a first original fingerprint image and a second original fingerprint image, wherein the first original fingerprint image and the second original fingerprint image are two fingerprint images of the target object at different locations within the same time interval; The preprocessing of the original fingerprint image to obtain the processed original fingerprint image includes: The first original fingerprint image is subjected to noise reduction processing to generate a first processed image; The second original fingerprint image is subjected to noise reduction processing to generate a second processed image; Based on the image regions of the first processed image and the image regions of the second processed image, a common image region, a first non-common image region corresponding to the first processed image, and a second non-common image region corresponding to the second processed image are obtained. If the area of ​​the first non-public image region is smaller than the area of ​​the second non-public image region, then the area image corresponding to the first non-public image region is corrected based on the area image of the public image region corresponding to the first processed image and the area image of the public image region corresponding to the second processed image to generate a first corrected image. The processed original fingerprint image is obtained based on the first corrected image and the second processed image; If the area of ​​the first non-public image region is greater than or equal to the area of ​​the second non-public image region, then the area image corresponding to the second non-public image region is corrected based on the area image of the public image region corresponding to the first processed image and the area image of the public image region corresponding to the second processed image to generate a second corrected image. The processed original fingerprint image is obtained based on the second corrected image and the first processed image.

5. The method according to claim 4, characterized in that, The step of correcting the region image corresponding to the first non-common image region based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image to generate a first corrected image includes: A first tensor group is generated based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image. Based on the first tensor group, the region image corresponding to the first non-common image region is corrected to generate the first corrected image. The step of correcting the region image corresponding to the second non-common image region based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image to generate a second corrected image includes: A second tensor group is generated based on the region image of the common image region corresponding to the first processed image and the region image of the common image region corresponding to the second processed image. Based on the second tensor set, the region image corresponding to the second non-common image region is corrected to generate the second corrected image.

6. A predictive fingerprint image generation apparatus, characterized in that, include: The acquisition module is used to acquire the original fingerprint image of any target object; The processing module is used to preprocess the original fingerprint image to obtain a processed original fingerprint image; The original fingerprint vector is obtained from the processed original fingerprint image; Obtain the fingerprint prediction model corresponding to the target object; input the original fingerprint vector, the preset time interval, and the pre-generated target fingerprint change coefficient into the fingerprint prediction model to output the predicted fingerprint vector; the target fingerprint change coefficient is obtained based on one or more occupational information of the target object determined according to the preset time interval; The generation module is used to generate a predicted fingerprint image based on the predicted fingerprint vector.

7. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images