Fingerprint image generation method, fingerprint identification method, electronic equipment and storage medium

Through image acquisition and style conversion technology, a target fingerprint image matching the image style of the fingerprint mold is generated, which solves the problem of time-consuming and labor-consuming fingerprint input in the prior art, and improves fingerprint input efficiency and unlocking success rate.

CN118968569APending Publication Date: 2024-11-15BEIJING JIIOV TECH CO LTD

Patent Information

Application Number
CN202410916813.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing fingerprint recognition technology requires moving your fingers multiple times during the initial entry, which is time-consuming and labor-intensive and the information is not comprehensive enough, which affects the unlocking success rate.

Method used

The fingerprint image is captured through the image acquisition device, and the image forming style of the fingerprint module is used for style conversion, and a target fingerprint image matching the image style of the fingerprint module is generated, simplifying the entry process and improving efficiency.

Benefits of technology

It reduces user operation complexity, improves fingerprint entry efficiency and unlocking success rate, and can complete fingerprint information entry through a single or a small number of images.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968569A_ABST
    Figure CN118968569A_ABST
Patent Text Reader

Abstract

The invention provides a fingerprint image generation method, a fingerprint identification method, electronic equipment and a storage medium, and relates to the technical field of image processing. In order to complete input of fingerprint information through image shooting, the fingerprint image generation method provided by the invention comprises the following steps: obtaining a to-be-processed fingerprint image according to a shot image acquired by an image acquisition device with a first visual field range; according to the imaging style of the fingerprint module, style conversion is conducted on the fingerprint image to be processed, a target fingerprint image with the style matched with the imaging style of the fingerprint module is obtained, and the fingerprint module has a second view field range smaller than the first view field range. According to the invention, fingerprint information input is completed through image shooting, and the fingerprint input efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing technology, and in particular to a fingerprint image generation method, a fingerprint recognition method, an electronic device and a storage medium. Background Art

[0002] Fingerprint recognition technology for mobile devices is currently divided into three types: capacitive, optical screen, and ultrasonic. These fingerprint recognition technologies require users to enter their fingerprints when using them for the first time, so that the fingerprint information can be stored in the mobile device as a comparison basis for subsequent unlocking. The more comprehensive the fingerprint information entered, the larger the fingerprint area covered, and the higher the success rate of unlocking, thereby reducing the risk of matching failure.

[0003] However, when entering fingerprints for the first time, users usually need to move their fingers multiple times according to the system prompts to ensure that the system captures sufficient fingerprint information from all angles and positions. This process is not only time-consuming and labor-intensive, but may also result in incomplete entered fingerprint information, thus affecting the unlocking success rate during actual use. Summary of the invention

[0004] The embodiments of the present invention provide a fingerprint image generation method, a fingerprint recognition method, an electronic device and a storage medium, so as to complete the entry of fingerprint information by shooting an image, thereby improving the efficiency of fingerprint entry.

[0005] A first aspect of an embodiment of the present invention provides a fingerprint image generation method, the method comprising:

[0006] Obtaining a fingerprint image to be processed according to a captured image acquired by an image acquisition device having a first field of view;

[0007] According to the imaging style of the fingerprint module, the fingerprint image to be processed is style converted to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module, and the second field of view of the fingerprint module is smaller than the first field of view.

[0008] A second aspect of an embodiment of the present invention provides a fingerprint recognition method, the method comprising:

[0009] Obtaining the fingerprint image to be identified collected by the fingerprint module;

[0010] The fingerprint image to be identified is matched with a pre-stored target fingerprint image to obtain a fingerprint identification result, wherein the target fingerprint image is obtained by the fingerprint image generation method described in the first aspect of the present invention.

[0011] A third aspect of an embodiment of the present invention provides a fingerprint image generating device, the device comprising:

[0012] An image capturing module, used to obtain a fingerprint image to be processed based on an image captured by an image capturing device having a first field of view;

[0013] The image generation module is used to perform style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module, and the second field of view of the fingerprint module is smaller than the first field of view.

[0014] A fourth aspect of an embodiment of the present invention provides a fingerprint recognition device, the device comprising:

[0015] An image acquisition module is used to obtain the fingerprint image to be identified collected by the fingerprint module;

[0016] The fingerprint recognition module is used to match the fingerprint image to be recognized with a pre-stored target fingerprint image to obtain a fingerprint recognition result. The target fingerprint image is obtained by the fingerprint image generation method described in the first aspect of the present invention.

[0017] A fifth aspect of an embodiment of the present invention provides an electronic device, including:

[0018] An image acquisition device, used for acquiring and shooting images, wherein the image acquisition device has a first field of view;

[0019] A fingerprint module, used for collecting a fingerprint image to be identified, wherein the fingerprint module has a second field of view, and the first field of view is larger than the second field of view;

[0020] A computer program stored on a memory and executable on a processor;

[0021] The processor, when executing the computer program, implements the fingerprint image generation method described in the first aspect of the present invention to obtain the target fingerprint image; and / or implements the fingerprint recognition method described in the second aspect of the present invention;

[0022] The memory is used to store the target fingerprint image.

[0023] A sixth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in generating a fingerprint image as described in the first aspect of the present invention and / or the steps in the fingerprint recognition method as described in the second aspect of the present invention are implemented.

[0024] In the embodiment of the present invention, the first field of view of the image acquisition device is larger than the second field of view of the fingerprint module, so the fingerprint information contained in the captured image captured by the image acquisition device is more comprehensive and larger than the fingerprint information in the image captured by the fingerprint module. Based on this, the captured image captured by the image acquisition device is processed to obtain a fingerprint image to be processed, and then the fingerprint image to be processed is converted into a target fingerprint image that matches the imaging style of the fingerprint module, so that the target fingerprint image can be used for fingerprint recognition, thereby completing the entry of fingerprint information. In this way, the embodiment of the present invention simplifies the fingerprint entry process, and can complete the entry of fingerprint information through a small number or a single captured image, greatly reducing the complexity of user operations. Compared with traditional fingerprint entry, the multiple finger movements required for fingerprint entry are reduced to one or two photo shootings, greatly improving the efficiency of fingerprint entry, and based on the target fingerprint image with more fingerprint information, the unlocking success rate during actual use by the user is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0026] Figure 1 is a flow chart of a fingerprint image generation method according to an embodiment of the present invention;

[0027] Figure 2 It is a flow chart of a fingerprint image entry method according to an embodiment of the present invention;

[0028] Figure 3 is a flow chart of a fingerprint recognition method according to an embodiment of the present invention;

[0029] Figure 4 is a schematic diagram of a fingerprint image generating device provided by an embodiment of the present invention;

[0030] Figure 5 Schematic diagram of a fingerprint recognition device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Figure 1 , shows a flow chart of a fingerprint image generation method according to an embodiment of the present invention. The fingerprint image generation method provided by the embodiment of the present invention may include the following steps:

[0033] S101, obtaining a fingerprint image to be processed according to an image captured by an image acquisition device having a first field of view.

[0034] In the embodiment of the present invention, when fingerprint is recorded, the image of the finger can be photographed by an image acquisition device to obtain a photographed image; image processing is performed based on the photographed image to obtain a fingerprint image to be processed. The image acquisition device has a first field of view, which is the field of view (FOV) of the image acquisition device; the fingerprint image to be processed is an image containing fingerprint information obtained based on the photographed image.

[0035] S102, performing style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module, wherein the second field of view of the fingerprint module is smaller than the first field of view.

[0036] In the embodiment of the present invention, the fingerprint module is a device specially used for fingerprint collection, which has a unique imaging style due to the fingerprint characteristics. For example, the imaging style of the optical fingerprint module is that the clarity and brightness gradually decrease from the center to the edge; for another example, the imaging style of the capacitive fingerprint module is that different areas have different noises; etc. Moreover, the second field of view of the fingerprint module is smaller than the first field of view of the image acquisition device; wherein the second field of view is the field of view of the fingerprint module.

[0037] Based on this, the embodiment of the present invention needs to perform style conversion on the obtained fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image, and the imaging style of the target fingerprint image matches the imaging style of the fingerprint module. Among them, the target fingerprint image is a fingerprint image that conforms to the imaging style of the fingerprint module obtained based on the captured image processing, and the target fingerprint image can be used for fingerprint recognition.

[0038] In one embodiment, for fingerprint entry, the above fingerprint image generation method can be executed for a single or multiple captured images captured by the image acquisition device to generate a single or multiple target fingerprint images; for the case of generating multiple target fingerprint images, a target final fingerprint image can be generated based on the fusion of multiple target fingerprint images, and the target final fingerprint image can be used for fingerprint recognition. Among them, the number of captured images required for fingerprint entry is less than the average number of presses required for fingerprint entry through the traditional fingerprint module, for example, the number of captured images required can be 1 or 2.

[0039] In view of the fact that the entry process of the current fingerprint system is limited by the field of view of the fingerprint module, the user is usually required to press and move the finger multiple times, which results in the defect that the entire entry process is both time-consuming and cumbersome, the embodiment of the present invention processes the captured image captured by the image acquisition device to obtain a fingerprint image to be processed, and then converts the fingerprint image to be processed into a target fingerprint image that matches the imaging style of the fingerprint module. Since the first field of view of the image acquisition device is larger than the second field of view of the fingerprint module, the fingerprint information contained in the captured image captured by the image acquisition device is more comprehensive and larger than the fingerprint information in the image captured by the fingerprint module. Generally speaking, the fingerprint information contained in the captured image is 10-20 times the fingerprint information in the image captured by the fingerprint module, so that the average number of presses required for traditional fingerprint entry can be reduced from 25 to completing the entry of fingerprint information by taking pictures 1 to 2 times. In this way, the embodiment of the present invention simplifies the fingerprint entry process, greatly reduces the complexity of user operations, greatly improves the efficiency of fingerprint entry, and based on the target fingerprint image with more fingerprint information, improves the unlocking success rate when the user actually uses it.

[0040] In combination with the above embodiments, in one implementation, an embodiment of the present invention further provides a fingerprint image generation method. In this method, the above step S102 of "performing style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module" may specifically include the following sub-steps:

[0041] S1021: Inputting the fingerprint image to be processed and the randomly sampled noise image into the trained control network to obtain the intermediate features output by the trained control network.

[0042] In an embodiment of the present invention, a fingerprint image generation network and a trained control network matching the fingerprint image generation network are configured. The trained control network is used to generate intermediate features based on the fingerprint image to be processed to guide the fingerprint image generation network to generate a target fingerprint image based on the fingerprint image to be processed; the fingerprint image generation network is used to convert the fingerprint image to be processed into a target fingerprint image that conforms to the imaging style of the fingerprint module. In one embodiment, the configured fingerprint image generation network can be a pre-trained fingerprint image generation network.

[0043] In the embodiment of the present invention, the fingerprint image to be processed and a randomly sampled noise image can be input into the trained control network, and the feature extraction of the fingerprint image to be processed and the noise image can be performed to obtain the intermediate features output by the trained control network; wherein the intermediate features are used to guide the fingerprint image generation network to generate the fingerprint image according to the imaging style of the fingerprint module. The noise image in the embodiment of the present invention is generated by random sampling and conforms to the Gaussian distribution.

[0044] S1022: Input the randomly sampled noise image and the intermediate features into the fingerprint image generation network to obtain the target fingerprint image.

[0045] In an embodiment of the present invention, after obtaining the intermediate features, the intermediate features and the randomly sampled noise image used to generate the intermediate features can be input into a fingerprint image generation network, and the noise image and the intermediate features can be fused to obtain a target fingerprint image output by the fingerprint image generation network.

[0046] In an optional embodiment, the control network of the embodiment of the present invention can be a convolutional neural network (CNN), and the feature extraction of the fingerprint image and the noise image to be processed can be performed through the deep learning algorithm and the convolutional neural network to obtain the intermediate features. The fingerprint image generation network of the embodiment of the present invention can be a plug-in of the diffusion model, thereby combining the diffusion model (fingerprint image generation network) and the convolutional neural network (control network), fusing the noise image with the intermediate features, and gradually converting it into the desired target fingerprint image through the diffusion model generation algorithm.

[0047] In combination with the above embodiments, in one implementation, an embodiment of the present invention further provides a fingerprint image generation method. In this method, the above step S102 of "performing style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module" may specifically include the following sub-steps:

[0048] S102-1: obtaining a plurality of intermediate fingerprint images according to the fingerprint image to be processed and a plurality of noise images randomly sampled multiple times.

[0049] In an embodiment of the present invention, in order to improve image quality and ridge consistency, noise images can be randomly sampled multiple times to obtain multiple noise images. Each of the multiple noise images can be processed with the same fingerprint image to be processed to obtain multiple intermediate fingerprint images.

[0050] Specifically, the i-th intermediate fingerprint image among the multiple intermediate fingerprint images of this embodiment can be obtained according to step S102-11 and step S102-12:

[0051] Step S102-11: Input the fingerprint image to be processed and the i-th randomly sampled noise image into the trained control network to obtain the i-th intermediate feature output by the trained control network, and the i-th intermediate feature is used to guide the fingerprint image generation network to generate the fingerprint image according to the imaging style of the fingerprint module.

[0052] Step S102-12: inputting the i-th randomly sampled noise image and the i-th intermediate feature into the fingerprint image generation network to obtain the i-th intermediate fingerprint image.

[0053] Wherein, i is a natural number greater than 0, and the above steps S102-11 and S102-12 are the same as or similar to the above steps S1021 and S1022.

[0054] S102-2: Fusing the multiple intermediate fingerprint images to obtain the target fingerprint image.

[0055] In the embodiment of the present invention, the obtained multiple intermediate fingerprint images can be fused to obtain a high-quality target fingerprint image that is consistent with the fingerprint lines of the fingerprint image to be processed and conforms to the fingerprint module imaging style.

[0056] The embodiment of the present invention ensures that the detail information in the original fingerprint image taken by the image acquisition device (such as the front camera and / or rear camera of a mobile phone) is highly consistent with the converted image (target fingerprint image) by integrating control network technology, such as ControlNet. This integration not only improves the accuracy of fingerprint information, but also enhances the stability and reliability of the fingerprint recognition system.

[0057] In combination with the above embodiments, in one implementation, the embodiment of the present invention further provides a fingerprint image generation method. In this method, the type of the fingerprint module is any one of the following: capacitive fingerprint module, optical fingerprint module and ultrasonic fingerprint module; in addition to the above steps, step S1023 or step S1024 may also be included:

[0058] S1023, based on the real fingerprint images collected by the different types of fingerprint modules, training is performed to obtain a trained control network suitable for the different types of fingerprint modules.

[0059] In the embodiment of the present invention, different types of fingerprint modules correspond to corresponding trained control networks; for different types of fingerprint modules, based on the real fingerprint images collected by different types of fingerprint modules, trained control networks suitable for different types of fingerprint modules can be trained respectively. The trained control networks of different types of fingerprint modules can correspond to the same pre-trained fingerprint image generation network or to different pre-trained fingerprint image generation networks. In other words, the pre-trained fingerprint image generation networks corresponding to different types of fingerprint modules can be the same or different.

[0060] For example, when the type of fingerprint module is a capacitive fingerprint module, a control network that can guide the generation of intermediate features that conform to the imaging style of the capacitive fingerprint module can be obtained based on the real fingerprint image (i.e., the capacitive fingerprint image) collected by the capacitive fingerprint module, thereby obtaining a fingerprint image generation network that performs image conversion consistent with the imaging style of the capacitive fingerprint module.

[0061] S1024, based on the real fingerprint image collected by any type of fingerprint module, training a trained control network shared by different types of fingerprint modules.

[0062] In an embodiment of the present invention, different types of fingerprint modules may correspond to a common trained control network; for different types of fingerprint modules, real fingerprint images collected by any type of fingerprint module may be used to train a common trained control network suitable for different types of fingerprint modules.

[0063] In addition, in an optional embodiment, a trained control network shared by different types of fingerprint modules can be trained based on real fingerprint images collected by multiple types of fingerprint modules. For example, a control network that can guide the generation of intermediate features that conform to the imaging styles of various fingerprint modules can be obtained based on real fingerprint images collected by a capacitive fingerprint module (i.e., capacitive fingerprint image), real fingerprint images collected by an optical fingerprint module (i.e., optical fingerprint image), and real fingerprint images collected by an ultrasonic fingerprint module (i.e., ultrasonic fingerprint image), thereby obtaining a fingerprint image generation network that performs image conversion consistent with the imaging styles of various fingerprint modules.

[0064] In combination with the above embodiments, in an embodiment of the present invention, the training process of the trained control network includes the following steps:

[0065] S201, obtaining the fingerprint image generation network, wherein the fingerprint image generation network is used to generate a fingerprint image according to a noise image.

[0066] In an embodiment of the present invention, during the training process of the control network, a fingerprint image generation network may be first obtained, where the fingerprint image generation network is a trained fingerprint image generation network with fixed network parameters, and is used to generate a fingerprint image based on a noise image.

[0067] S202, obtaining a real fingerprint ridge image corresponding to the real fingerprint image collected by the fingerprint module.

[0068] In the process of training the control network in the embodiment of the present invention, the training samples used are: a real fingerprint line image corresponding to the real fingerprint image collected by the fingerprint module. The real fingerprint image is a fingerprint image collected by the fingerprint module. The fingerprint lines of the real fingerprint image can be extracted to obtain the real fingerprint line image corresponding to the real fingerprint image.

[0069] S203, inputting the real fingerprint image and the sample noise image into the control network to be trained, and obtaining intermediate sample features output by the control network to be trained.

[0070] In the embodiment of the present invention, in each round of model training, a real fingerprint line image corresponding to a real fingerprint image and a sample noise image can be input into the control network to be trained to obtain the intermediate sample features output by the control network to be trained. The sample noise image is a randomly generated noise image used for model training, and the intermediate sample features are the intermediate features output by the control network in model training.

[0071] S204, inputting the sample noise image and the intermediate sample features into the fingerprint image generation network to obtain a sample fingerprint image output by the fingerprint image generation network.

[0072] In an embodiment of the present invention, after obtaining the intermediate sample feature, the intermediate sample feature and the sample noise image used to generate the intermediate sample feature can be input into a fingerprint image generation network to obtain a sample fingerprint image output by the fingerprint image generation network.

[0073] S205: Based on the sample fingerprint image and the real fingerprint image, the control network to be trained is trained to obtain the trained control network.

[0074] In the embodiment of the present invention, the control network to be trained can be trained based on the sample fingerprint image and the corresponding real fingerprint image to obtain a trained control network.

[0075] For example, in each round of model training, the loss value is calculated for the sample fingerprint image generated in the model training and the real fingerprint image used, and the network parameters of the control network to be trained are adjusted based on the loss value, and the control network to be trained with updated network parameters is used for the next round of model training. Then, in the next round of model training, the model is trained using the real fingerprint line image and the sample noise image corresponding to a new real fingerprint image to obtain the loss value corresponding to the next round of model training, until the loss value converges, and the network parameters of the control network to be trained are fixed to obtain the trained control network.

[0076] In combination with the above embodiments, in one implementation, after obtaining the target fingerprint image, the target fingerprint image can be stored, such as storing the target fingerprint image in a base database as an entry base database image for a fingerprint recognition system. The large size and comprehensive information of the target fingerprint image help to improve the unlocking rate of the first fingerprint recognition use and the overall user experience.

[0077] In combination with the above embodiments, in one implementation, the present invention also provides a fingerprint image generation method. In this method, in addition to the above steps, the following steps may also be included:

[0078] S301, in response to a fingerprint entry operation, controlling the image acquisition device to acquire an image to obtain the captured image.

[0079] The fingerprint image generation method of this embodiment can be applied to electronic devices, such as mobile phones, tablets, smart watches, door locks, etc. In response to the user's fingerprint entry operation, the electronic device controls the image acquisition device of the electronic device to acquire an image and obtain a captured image.

[0080] In one embodiment, the image acquisition device may be a rear camera and / or a front camera of the electronic device, and the captured image is obtained based on the image acquired by the front camera and / or the rear camera of the electronic device.

[0081] S302: Detect whether the captured image contains a finger.

[0082] In the embodiment of the present invention, after obtaining the captured image, firstly, it is possible to detect whether the captured image contains a finger by using a relevant target detection algorithm.

[0083] Furthermore, in the embodiment of the present invention, the above S101 may include sub-step S1011:

[0084] S1011: When the captured image contains a finger, extract fingerprint lines from the captured image to obtain the fingerprint image to be processed.

[0085] In the embodiment of the present invention, when it is determined that the captured image contains a finger, fingerprint lines are extracted from the captured image to obtain a fingerprint image to be processed. When it is determined that the captured image does not contain a finger, a result indicating that the finger was not detected can be returned, and a prompt message can be generated to prompt the user to retake the photo.

[0086] In combination with the above embodiments, in one implementation, the present invention also provides a fingerprint image generation method. In this method, in addition to the above steps, the following steps may also be included:

[0087] S401, in response to a fingerprint entry operation, controlling the image acquisition device to acquire an image to obtain the captured image.

[0088] S402: Detect whether the captured image contains a finger.

[0089] In the embodiment of the present invention, steps S401 and S402 are the same as or similar to the above steps S301 and S302, and are not described in detail.

[0090] S403: When the captured image contains a finger, detect whether the clarity of the fingerprint of the finger in the captured image is greater than a clarity threshold.

[0091] In the case where it is determined that the captured image contains a finger, the embodiment of the present invention needs to further detect whether the finger fingerprint in the captured image is clear enough. Specifically, it can detect whether the clarity of the finger fingerprint in the captured image is greater than a clarity threshold. In this embodiment, a clarity threshold is pre-configured, and the clarity threshold is the minimum clarity that characterizes the clarity of the finger fingerprint. It can be freely set according to needs, and there is no limit on this value.

[0092] Furthermore, in the embodiment of the present invention, the above S101 may include sub-step S101-1:

[0093] S101-1: When the clarity of the fingerprint in the captured image is greater than the clarity threshold, fingerprint ridges are extracted from the captured image to obtain the fingerprint image to be processed.

[0094] In the embodiment of the present invention, when it is determined that the clarity of the fingerprint of the finger in the captured image is greater than the clarity threshold, fingerprint lines are extracted from the captured image to obtain a fingerprint image to be processed.

[0095] In another optional embodiment, when it is determined that the captured image contains the finger, it is determined whether the captured image contains the finger fingerprint. When it is determined that the captured image contains the finger fingerprint, it is further determined whether the finger fingerprint is clear. For example, it can be processed by a pre-trained fingerprint recognition model. The fingerprint recognition model outputs 0 for unclear finger fingerprints and outputs 1 for clear finger fingerprints. For example, it can be processed by a pre-trained fingerprint key point extraction model. Whether the finger fingerprint is clear is determined based on the number of key points output by the fingerprint key point extraction model. This embodiment does not limit this.

[0096] If the fingerprint is clear, the fingerprint lines can be extracted from the captured image to obtain the fingerprint image to be processed. If the fingerprint is unclear, the fingerprint lines can be clearly visible through the image quality enhancement algorithm, so that the fingerprint is clear, and then the fingerprint lines can be extracted from the captured image to obtain the fingerprint image to be processed.

[0097] In an embodiment of the present invention, when it is determined that the captured image does not contain a finger, or when it is determined that the clarity of the finger fingerprint in the captured image is less than a clarity threshold, a result of no finger detected or a clear finger fingerprint can be returned, and a prompt message can be generated to prompt the user to retake the photo.

[0098] In combination with the above embodiments, in one implementation, the present invention also provides a fingerprint image generation method. In this method, the above step S1011 of "extracting fingerprint lines from the captured image to obtain the fingerprint image to be processed" may specifically include the following sub-steps:

[0099] S10111, cropping the captured image with the finger as the center to obtain a cropped image.

[0100] In the embodiment of the present invention, an object detection algorithm may be used to obtain a boundary frame of a finger, locate the position of the finger, and then crop the captured image with the finger as the center to obtain a cropped image.

[0101] In an optional embodiment, the captured image may be cropped with the finger as the center to obtain an intermediate cropped image, and then the intermediate cropped image may be processed based on the scale coefficient of the image captured by the fingerprint module to obtain a cropped image, so that the cropped image and the image captured by the fingerprint module are within a proportional range, which can improve the subsequent fingerprint recognition accuracy based on the target fingerprint image.

[0102] S10112: Extract fingerprint lines from the cropped image to obtain the fingerprint image to be processed.

[0103] In the embodiment of the present invention, after the cropped image is obtained, fingerprint ridges may be extracted from the cropped image to obtain a fingerprint image to be processed.

[0104] In an optional implementation manner, the above step S10112 may include the following sub-steps:

[0105] S10112-1, obtaining a mask of the fingerprint image area in the cropped image.

[0106] In the embodiment of the present invention, when fingerprint ridge extraction is performed, a mask of the fingerprint image area in the cropped image may be obtained through an image segmentation algorithm.

[0107] S10112-2, performing fingerprint key point detection based on the cropped image and the mask to obtain a fingerprint key point feature map, and performing fingerprint ridge estimation based on the cropped image and the mask to obtain a fingerprint ridge direction feature map.

[0108] In the embodiment of the present invention, fingerprint key point detection can be performed by a fingerprint key point detection algorithm based on the cropped image and the mask of the fingerprint image area in the cropped image to obtain a fingerprint key point feature map. For example, the cropped image and the mask of the fingerprint image area in the cropped image can be input into a pre-trained fingerprint key point detection model to obtain a fingerprint key point feature map.

[0109] Furthermore, the fingerprint ridges can be estimated by a fingerprint ridge estimation algorithm according to the cropped image and the mask of the fingerprint image area in the cropped image to obtain a fingerprint ridge direction feature map. For example, the fingerprint ridge direction feature map can be obtained by inputting the cropped image and the mask of the fingerprint image area in the cropped image into a pre-trained fingerprint ridge estimation model. The fingerprint ridge direction is the direction carried by the fingerprint ridges.

[0110] It should be noted that the fingerprint key point detection and fingerprint ridge line estimation in the embodiment of the present invention can be performed simultaneously or sequentially, and there is no limitation on this.

[0111] S10112-3, obtaining the fingerprint image to be processed according to the fingerprint key point feature map and the fingerprint ridge direction feature map.

[0112] In the embodiment of the present invention, after the fingerprint key point feature map and the fingerprint ridge direction feature map are obtained, the fingerprint image to be processed can be obtained according to the fingerprint key point feature map and the fingerprint ridge direction feature map.

[0113] Furthermore, in a preferred embodiment, the fingerprint key point feature map and the fingerprint ridge direction feature map carry corresponding confidences. Since the number of fingerprint key point feature maps and fingerprint ridge direction feature maps obtained is huge, in order to save computing resources, a non-maximum suppression algorithm (NMS) can be applied to obtain high-confidence fingerprint key point feature maps and fingerprint ridge direction feature maps, and then by optimizing the high-confidence fingerprint key point feature maps and fingerprint ridge direction feature maps, a binary fingerprint ridge image (binarized fingerprint valley and ridge image) is generated as the fingerprint image to be processed.

[0114] like Figure 2 As shown, Figure 2 FIG. 1 is a flow chart of a fingerprint image entry method according to an embodiment of the present invention. Figure 2In the method, first, a photographed image is taken by an image acquisition device; secondly, a finger and a fingerprint of the finger are detected in the photographed image by a finger detection module (used to detect whether there is a finger in the photographed image and confirm whether the fingerprint is clear and discernible), and when it is determined that there is a finger in the photographed image and the fingerprint of the finger is clear, the photographed image is enlarged and cropped with the finger as the center to obtain a cropped image; then, a fingerprint ridge extraction module (used to detect the key points and ridges of the fingerprint and generate a binary fingerprint valley and ridge image) is used to obtain a mask of the fingerprint area of ​​the cropped image by an image segmentation algorithm, and then fingerprint key point detection and fingerprint ridge estimation are performed based on the cropped image and the mask to obtain a fingerprint. The key point feature map and the fingerprint ridge direction feature map are finally generated into a binary fingerprint ridge image; then, the fingerprint ridge image and the randomly generated noise image are input into a pre-trained control network module (used to output intermediate features for guiding fingerprint generation based on the binary fingerprint ridge image and the sampled noise image) to obtain intermediate features; finally, the intermediate features and the randomly generated noise image are input into the fingerprint generation module (used to output a fingerprint base library image consistent with the binary fingerprint image ridges based on the sampled noise image and the guiding features output by the control network module) to obtain a generated image output by the fingerprint generation module, which is a fingerprint image consistent with the imaging style of the fingerprint module.

[0115] Through the method of the embodiment of the present invention, innovative image generation technology and image editing means are adopted, and through a deep learning algorithm, the fingerprint image captured by the image acquisition device (such as a mobile phone camera) is accurately converted into a target fingerprint image that conforms to the fingerprint module imaging style, thereby completing the fingerprint information entry process. By utilizing the larger field of view of the image acquisition device, the complete fingerprint information of the finger can be obtained in a single or a few images; then, through the image generation technology combined with the control network (ControlNet) and other spatial structure control modules, the fingerprint pattern information is controlled for consistency, and finally a target fingerprint image that is consistent with the fingerprint pattern of the recorded finger and conforms to the fingerprint module imaging style is generated as the entry base image. This conversion process ensures that the fingerprint image can meet the specific requirements of the fingerprint recognition system, thereby improving the accuracy and efficiency of recognition.

[0116] Based on the same inventive concept, Figure 3 , shows a flow chart of a fingerprint recognition method according to an embodiment of the present invention. The fingerprint recognition method provided by the embodiment of the present invention may include the following steps:

[0117] S601, obtaining a fingerprint image to be identified collected by a fingerprint module.

[0118] The fingerprint recognition method of the embodiment of the present invention can be applied to electronic devices, such as mobile phones, tablets, smart watches, door locks, etc. In response to the user's fingerprint unlocking / recognition operation, the electronic device controls the fingerprint module of the electronic device to collect fingerprint images and obtains the fingerprint image to be recognized collected by the fingerprint module.

[0119] S602, matching the fingerprint image to be identified with a pre-stored target fingerprint image to obtain a fingerprint identification result, wherein the target fingerprint image is obtained by the fingerprint image generation method described in any of the above embodiments.

[0120] In an embodiment of the present invention, a target fingerprint image is pre-stored in the electronic device, and the target fingerprint image is obtained by the fingerprint image generation method proposed in any of the above embodiments. Then, in the process of fingerprint recognition, the fingerprint image to be recognized is matched with the target fingerprint image to obtain a fingerprint recognition result. If the fingerprint recognition result is a successful match, relevant control operations such as unlocking, payment, login, etc. are performed without restriction; if the fingerprint recognition result is a failed match, a fingerprint mismatch result notification is generated and displayed to prompt the user to re-recognize the fingerprint.

[0121] In order to solve the problem that during the fingerprint recognition process, if the fingerprint information recorded in the fingerprint is insufficient, when the recorded finger is used to unlock the phone at a relatively biased angle, the fingerprint may not match the stored fingerprint information when unlocking, thereby reducing the initial unlocking rate (i.e. the probability of successful fingerprint unlocking for the first time), affecting the user experience, in an embodiment of the present invention, by combining multimodality and image generation technology, a fingerprint image captured in a different modality from the fingerprint module is used to complete the fingerprint system's registration and unlocking process. The use of this multimodal image makes fingerprint recognition more comprehensive and accurate, which not only simplifies the fingerprint system's registration process, allowing users to complete the fingerprint information registration through a small amount or a single image; at the same time, it can provide a larger fingerprint information base area after the registration is completed, effectively improving the success rate of fingerprint unlocking and the user's overall experience.

[0122] The embodiment of the present invention converts the finger image taken by the image acquisition device into an image of fingerprint model imaging style by combining image generation technology and image editing technology to optimize the entry and unlocking process of the fingerprint recognition system. In other words, this sending embodiment not only significantly optimizes the fingerprint entry process through innovative image processing technology, greatly reduces the user's operation complexity, and greatly improves user convenience; it also provides a more efficient, accurate and convenient fingerprint recognition solution to improve the unlocking rate and accuracy of the fingerprint recognition system, especially when using it for the first time, making it easier for users and enhancing the user experience.

[0123] Based on the same inventive concept, an embodiment of the present invention provides a fingerprint image generating device 400. Figure 4 , Figure 4 4 is a schematic diagram of a fingerprint image generating device provided by an embodiment of the present invention, wherein the device 400 comprises:

[0124] An image capturing module 401 is used to obtain a fingerprint image to be processed based on an image captured by an image capturing device having a first field of view;

[0125] The image generation module 402 is used to perform style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module, and the second field of view of the fingerprint module is smaller than the first field of view.

[0126] Optionally, the device 400 further includes:

[0127] A first input module, configured to control the image acquisition device to acquire an image in response to a fingerprint input operation, so as to obtain the captured image;

[0128] A first detection module, used to detect whether the captured image contains a finger;

[0129] The image capturing module 401 includes:

[0130] The first extraction module is used to extract fingerprint lines from the captured image to obtain the fingerprint image to be processed when the captured image contains a finger.

[0131] Optionally, the device 400 further includes:

[0132] A second input module, configured to control the image acquisition device to acquire an image in response to a fingerprint input operation, so as to obtain the captured image;

[0133] A second detection module, used to detect whether the captured image contains a finger;

[0134] A third detection module, configured to detect whether the clarity of the fingerprint of the finger in the captured image is greater than a clarity threshold when the captured image contains the finger;

[0135] The image capturing module 401 includes:

[0136] The second extraction module is used to extract fingerprint lines from the captured image to obtain the fingerprint image to be processed when the clarity of the fingerprint in the captured image is greater than the clarity threshold.

[0137] Optionally, the first extraction module or the second extraction module includes:

[0138] A cropping module, used for cropping the captured image with the finger as the center to obtain a cropped image;

[0139] The fingerprint ridge extraction module is used to extract fingerprint ridges from the cropped image to obtain the fingerprint image to be processed.

[0140] Optionally, the grain extraction module includes:

[0141] A mask determination module, used to obtain a mask of a fingerprint image region in the cropped image;

[0142] A feature map acquisition module, used to perform fingerprint key point detection according to the cropped image and the mask to obtain a fingerprint key point feature map, and to perform fingerprint ridge estimation according to the cropped image and the mask to obtain a fingerprint ridge direction feature map;

[0143] The fingerprint image determination module is used to obtain the fingerprint image to be processed according to the fingerprint key point feature map and the fingerprint ridge direction feature map.

[0144] Optionally, the image generation module 402 includes:

[0145] A guide feature generation module, used to input the fingerprint image to be processed and the randomly sampled noise image into the trained control network, and obtain the intermediate features output by the trained control network, wherein the intermediate features are used to guide the fingerprint image generation network to generate the fingerprint image according to the imaging style of the fingerprint module;

[0146] The target image generation module is used to input the randomly sampled noise image and the intermediate features into the fingerprint image generation network to obtain the target fingerprint image.

[0147] Optionally, the image generation module 402 includes:

[0148] A sampling module, used for obtaining a plurality of intermediate fingerprint images according to the fingerprint image to be processed and a plurality of noise images randomly sampled for multiple times;

[0149] An image fusion module, used for fusing the multiple intermediate fingerprint images to obtain the target fingerprint image;

[0150] The adopting module includes: an intermediate image processing module, which is used to obtain the i-th intermediate fingerprint image among the multiple intermediate fingerprint images; the intermediate image processing module includes:

[0151] The i-th intermediate feature determination module is used to input the fingerprint image to be processed and the i-th randomly sampled noise image into the trained control network to obtain the i-th intermediate feature output by the trained control network, and the i-th intermediate feature is used to guide the fingerprint image generation network to generate the fingerprint image according to the imaging style of the fingerprint module;

[0152] The i-th fingerprint image generation module is used to input the i-th randomly sampled noise image and the i-th intermediate feature into the fingerprint image generation network to obtain the i-th intermediate fingerprint image.

[0153] Optionally, the type of the fingerprint module is any one of the following: a capacitive fingerprint module, an optical fingerprint module, and an ultrasonic fingerprint module; the device 400 further includes:

[0154] The first training module is used to train a trained control network suitable for different types of fingerprint modules based on real fingerprint images collected by different types of fingerprint modules;

[0155] The second training module is used to train a trained control network shared by different types of fingerprint modules based on a real fingerprint image collected by any type of fingerprint module.

[0156] Optionally, the device 400 further includes: a network training module, used to train the trained control network, the network training module including:

[0157] A network acquisition module, used to acquire the fingerprint image generation network, wherein the fingerprint image generation network is used to generate a fingerprint image according to a noise image;

[0158] A real fingerprint acquisition module, used to acquire a real fingerprint line image corresponding to the real fingerprint image collected by the fingerprint module;

[0159] An intermediate feature acquisition module, used for inputting the real fingerprint ridge image and the sample noise image into the control network to be trained, and obtaining the intermediate sample features output by the control network to be trained;

[0160] A sample fingerprint generation module, used for inputting the sample noise image and the intermediate sample features into the fingerprint image generation network to obtain a sample fingerprint image output by the fingerprint image generation network;

[0161] The network parameter adjustment module is used to train the control network to be trained based on the sample fingerprint image and the real fingerprint image to obtain the trained control network.

[0162] Optionally, the captured image is obtained based on an image captured by a front camera and / or a rear camera of the electronic device.

[0163] Based on the same inventive concept, an embodiment of the present invention provides a fingerprint recognition device 500. Figure 5 , Figure 5 is a schematic diagram of a fingerprint recognition device provided by an embodiment of the present invention, wherein the device 500 comprises:

[0164] The image acquisition module 501 is used to obtain the fingerprint image to be identified collected by the fingerprint module;

[0165] The fingerprint recognition module 502 is used to match the fingerprint image to be recognized with a pre-stored target fingerprint image to obtain a fingerprint recognition result. The target fingerprint image is obtained by the fingerprint image generation method described in any of the above embodiments.

[0166] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0167] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, including:

[0168] An image acquisition device, used for acquiring and shooting images, wherein the image acquisition device has a first field of view;

[0169] A fingerprint module, used for collecting a fingerprint image to be identified, wherein the fingerprint module has a second field of view, and the first field of view is larger than the second field of view;

[0170] A computer program stored on a memory and executable on a processor;

[0171] The processor, when executing the computer program, implements the steps of the fingerprint image generation method described in any of the above embodiments to obtain the target fingerprint image; and / or implements the steps of the fingerprint recognition method described in the above embodiments;

[0172] The memory is used to store the target fingerprint image.

[0173] Optionally, the image acquisition device is a front camera and / or a rear camera of the electronic device.

[0174] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the fingerprint image generation method described in any of the above embodiments and / or the steps of the fingerprint recognition method described in the above embodiments are implemented.

[0175] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0176] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0177] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable image processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable image processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable image processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable image processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0181] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0182] The above is a detailed introduction to a fingerprint image generation method, a fingerprint recognition method, an electronic device and a storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A fingerprint image generation method, characterized in that: The method comprises: Obtaining a fingerprint image to be processed according to a captured image acquired by an image acquisition device having a first field of view; According to the imaging style of the fingerprint module, the fingerprint image to be processed is style converted to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module, and the second field of view of the fingerprint module is smaller than the first field of view.

2. The method according to claim 1, characterized in that The method further comprises: In response to the fingerprint entry operation, controlling the image acquisition device to acquire an image to obtain the captured image; Detecting whether the captured image contains a finger; The method of obtaining a fingerprint image to be processed based on the captured image acquired by the image acquisition device having the first field of view includes: In the case that the captured image contains a finger, fingerprint lines are extracted from the captured image to obtain the fingerprint image to be processed.

3. The method according to claim 1, characterized in that The method further comprises: In response to the fingerprint entry operation, controlling the image acquisition device to acquire an image to obtain the captured image; Detecting whether the captured image contains a finger; In the case where the captured image contains a finger, detecting whether the clarity of the fingerprint of the finger in the captured image is greater than a clarity threshold; The method of obtaining a fingerprint image to be processed based on the captured image acquired by the image acquisition device having the first field of view includes: When the clarity of the fingerprint of the finger in the captured image is greater than the clarity threshold, fingerprint ridges are extracted from the captured image to obtain the fingerprint image to be processed.

4. The method according to claim 2 or 3, characterized in that: The step of extracting fingerprint lines from the captured image to obtain the fingerprint image to be processed includes: Cropping the captured image with the finger as the center to obtain a cropped image; The fingerprint lines are extracted from the cropped image to obtain the fingerprint image to be processed.

5. The method according to claim 4, characterized in that The step of extracting fingerprint lines from the cropped image to obtain the fingerprint image to be processed includes: Obtaining a mask of a fingerprint image region in the cropped image; Performing fingerprint key point detection according to the cropped image and the mask to obtain a fingerprint key point feature map, and performing fingerprint ridge estimation according to the cropped image and the mask to obtain a fingerprint ridge direction feature map; The fingerprint image to be processed is obtained according to the fingerprint key point feature map and the fingerprint ridge direction feature map.

6. The method according to claim 1, characterized in that The method of performing style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module includes: Inputting the fingerprint image to be processed and the randomly sampled noise image into a trained control network to obtain intermediate features output by the trained control network, wherein the intermediate features are used to guide the fingerprint image generation network to generate fingerprint images according to the imaging style of the fingerprint module; The randomly sampled noise image and the intermediate features are input into the fingerprint image generation network to obtain the target fingerprint image.

7. The method according to claim 1, characterized in that The method of performing style conversion on the fingerprint image to be processed according to the imaging style of the fingerprint module to obtain a target fingerprint image whose style matches the imaging style of the fingerprint module includes: Obtaining multiple intermediate fingerprint images according to the fingerprint image to be processed and multiple noise images randomly sampled multiple times; fusing the multiple intermediate fingerprint images to obtain the target fingerprint image; The i-th intermediate fingerprint image among the plurality of intermediate fingerprint images is obtained according to the following steps: Input the fingerprint image to be processed and the i-th randomly sampled noise image into the trained control network to obtain the i-th intermediate feature output by the trained control network, wherein the i-th intermediate feature is used to guide the fingerprint image generation network to generate the fingerprint image according to the imaging style of the fingerprint module; The i-th randomly sampled noise image and the i-th intermediate feature are input into the fingerprint image generation network to obtain the i-th intermediate fingerprint image.

8. The method according to claim 6 or 7, characterized in that: The type of the fingerprint module is any one of the following: a capacitive fingerprint module, an optical fingerprint module, and an ultrasonic fingerprint module; the method further includes: Based on real fingerprint images collected by different types of fingerprint modules, training a trained control network suitable for different types of fingerprint modules; or Based on the real fingerprint image collected by any type of fingerprint module, a trained control network shared by different types of fingerprint modules is obtained through training.

9. The method according to claim 6 or 7, characterized in that: The training process of the trained control network comprises the following steps: Acquire the fingerprint image generation network, wherein the fingerprint image generation network is used to generate a fingerprint image according to the noise image; Acquire a real fingerprint ridge image corresponding to the real fingerprint image collected by the fingerprint module; Inputting the real fingerprint ridge image and the sample noise image into the control network to be trained, and obtaining the intermediate sample features output by the control network to be trained; Inputting the sample noise image and the intermediate sample features into the fingerprint image generation network to obtain a sample fingerprint image output by the fingerprint image generation network; Based on the sample fingerprint image and the real fingerprint image, the control network to be trained is trained to obtain the trained control network.

10. The method according to any one of claims 1 to 9, characterized in that: The captured image is obtained based on an image captured by a front camera and / or a rear camera of the electronic device.

11. A fingerprint recognition method, characterized in that: The method comprises: Obtaining the fingerprint image to be identified collected by the fingerprint module; The fingerprint image to be identified is matched with a pre-stored target fingerprint image to obtain a fingerprint identification result, wherein the target fingerprint image is obtained by the fingerprint image generation method according to any one of claims 1 to 10.

12. An electronic device, characterized in that: include: An image acquisition device, used for acquiring and shooting images, wherein the image acquisition device has a first field of view; A fingerprint module, used for collecting a fingerprint image to be identified, wherein the fingerprint module has a second field of view, and the first field of view is larger than the second field of view; A computer program stored on a memory and executable on a processor; The processor, when executing the computer program, implements the fingerprint image generation method according to any one of claims 1 to 10 to obtain the target fingerprint image; And / or, implementing the fingerprint recognition method according to claim 11; The memory is used to store the target fingerprint image.

13. The electronic device according to claim 12, characterized in that: The image acquisition device is a front camera or a rear camera of the electronic device.

14. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the fingerprint image generation method according to any one of claims 1 to 10 and / or the steps of the fingerprint recognition method according to claim 11 are implemented.

Citation Information

Patent Citations

  • Fingerprint image processing method and device, storage medium and electronic equipment

    CN110363121A

  • Fingerprint synthesis method and device, electronic equipment and computer readable storage medium

    CN111639521A

  • Under-screen fingerprint image generation method and device

    CN112183324A

  • Fingerprint input method and electronic equipment

    CN113766050A

  • Image shooting method and device, attribute information determination method and device and electronic equipment

    CN116261039A

Cited By

  • Fingerprint identification method and device, electronic equipment, storage medium and program product

    CN121259881A