Biometric identification method and device

Abstract

The present invention discloses a biometric recognition method and device. The method includes: using a first sensor to acquire biometric registration data and generate a first image; converting the first image into a second image; generating template data based on the first and second images; using the first or second sensor to acquire biometric data to be recognized; and matching the data to be recognized with the template data to obtain a recognition result. This method eliminates the need for multiple registrations for multiple sensors, achieving convenient use.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method and device for biometric recognition. Background Art

[0002] With the continuous development of biometric technology, biometric technology solutions on the market are becoming more and more diversified, which can meet different application scenarios. Given the high reliability and convenience of biometric technology, solutions equipped with this technology have been widely used in electronic devices, especially smart devices.

[0003] To make device use more convenient, the combination of multiple fingerprint sensors will become increasingly common. In 2017, a certain smart device manufacturer launched a foldable device equipped with both front- and rear-mounted fingerprint sensors, bringing significant convenience. However, the device required separate registrations before use. This meant that the same finger had to be registered on both sensors before recognition could be achieved. This caused confusion and inconvenience for users, impacting the user experience.

[0004] Currently, no effective solution has been proposed to address the problem in related technologies that devices containing multiple sensors require multiple registrations, which is inconvenient to use. Summary of the Invention

[0005] The main purpose of the present invention is to provide a biometric identification method and device to solve the problem of inconvenience in using equipment with multiple fingerprint sensors.

[0006] To achieve the above-mentioned purpose, according to one aspect of the present invention, a biometric feature recognition method is provided, which includes: using a first sensor to obtain registration data of a biometric feature and generate a first image; converting the first image into a second image; generating template data based on the first image and the second image; using the first sensor or the second sensor to obtain data to be recognized of the biometric feature; matching the data to be recognized with the template data to obtain a recognition result.

[0007] Furthermore, the method also includes: before converting the first image into the second image, obtaining a first calibration image and a second calibration image of a calibration plate through a first sensor and a second sensor; and obtaining calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image.

[0008] Further, converting the first image into the second image includes: converting the first image into the second image based on the calibration data.

[0009] Furthermore, obtaining calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image includes: extracting first feature data of the first calibration image and second feature data of the second calibration image; calculating a difference value between the first feature data and the second feature data, and obtaining calibration data of the first sensor and the second sensor based on the difference value.

[0010] Furthermore, the method further includes: performing denoising and / or alignment processing on the data to be identified.

[0011] Furthermore, the difference value includes a deformation coefficient, a size variation coefficient, and a feature point variation coefficient.

[0012] Furthermore, the first image is converted into the second image using a trained deep learning model.

[0013] Furthermore, the deep learning model is trained using first training data of the biometric feature acquired by the first sensor and second training data of the biometric feature acquired by the second sensor, respectively, to obtain a trained deep learning model.

[0014] Furthermore, the template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

[0015] Furthermore, the biometric features include fingerprints, palm prints, and faces.

[0016] Furthermore, the first sensor and the second sensor include a sensor located on a side of the electronic device and a sensor under the screen.

[0017] Furthermore, the stitching of the multiple first images or the multiple second images respectively includes: registering the first image or the second image based on the features or pixels of a single first image or a single second image to obtain an overlapping area; and stitching the multiple first images or the multiple second images based on the overlapping area.

[0018] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a biometric feature recognition device is further provided, which includes: an acquisition unit, used to use a first sensor to obtain registration data of a biometric feature and generate a first image; a conversion unit, used to convert the first image into a second image; a generation unit, used to generate template data based on the first image and the second image; an acquisition unit, used to use the first sensor or the second sensor to obtain data to be recognized of the biometric feature; and a matching unit, used to match the data to be recognized with the template data to obtain a recognition result.

[0019] Furthermore, the device also includes: a calibration acquisition unit, used to acquire a first calibration image and a second calibration image of a calibration plate through the first sensor and the second sensor before converting the first image into the second image; and a calibration acquisition unit, used to acquire calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image.

[0020] Furthermore, the conversion unit is configured to convert the first image into the second image based on the calibration data.

[0021] Furthermore, the calibration acquisition unit includes: an extraction module for extracting first feature data of the first calibration image and second feature data of the second calibration image; a calculation module for calculating a difference value between the first feature data and the second feature data, and acquiring calibration data of the first sensor and the second sensor based on the difference value.

[0022] Furthermore, the conversion unit converts the first image into the second image using a trained deep learning model.

[0023] Furthermore, the template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

[0024] In order to achieve the above-mentioned object, according to another aspect of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the biometric feature recognition method of the present invention is executed.

[0025] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a device is also provided, comprising at least one processor, and at least one memory and bus connected to the processor, wherein the processor and the memory communicate with each other via the bus, and the processor is used to call program instructions in the memory to execute the biometric recognition method described in the present invention.

[0026] The present invention obtains registration data of biometrics by using a first sensor and generates a first image; converts the first image into a second image; generates template data based on the first image and the second image; uses the first sensor or the second sensor to obtain data to be identified of the biometrics; matches the data to be identified with the template data to obtain an identification result, thereby solving the problem that devices with multiple sensors require multiple registrations and are inconvenient to use, thereby achieving the effect of convenient use without having to register multiple sensors multiple times. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0028] Figure 1 is a flow chart of a biometric feature recognition method according to an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of the sensor setting area of ​​this embodiment;

[0030] Figure 3 is a schematic diagram of the calibration process of this embodiment;

[0031] Figure 4 Schematic diagram of a portion of the calibration plate of this embodiment;

[0032] Figure 5 is a flow chart of the fingerprint recognition method of this embodiment;

[0033] Figure 6 FIG. 1 is a schematic diagram of a biometric feature recognition device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0035] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] For ease of description, several terms involved in the embodiments of this application are explained below:

[0038] Fingerprint sensor: A sensor used to detect fingerprints. Currently, the more common ones are sensors based on capacitance principles, sensors based on optical principles, and sensors based on acoustic principles.

[0039] Under-screen fingerprint sensor: A fingerprint sensor that can be used under the device screen. The more common ones are sensors based on optical principles and sensors based on acoustic principles.

[0040] Side fingerprint sensor: A screen sensor that can be used in the device's mid-frame. This sensor is usually narrow and can be reused with the device's power button, volume button, or other buttons.

[0041] Rear-mounted fingerprint sensor: A fingerprint sensor that can be applied on the back of the device.

[0042] Front-mounted fingerprint sensor: A fingerprint sensor that can be used on the front of a device. Similar to the under-screen fingerprint sensor, both are used by users from the front of the device; the difference is that the front-mounted fingerprint sensor is not located under the screen.

[0043] Foldable device: A device with a screen that folds up to make the device more portable and unfolds to provide a larger screen.

[0044] An embodiment of the present invention provides a biometric feature recognition method.

[0045] Figure 1 is a flow chart of a biometric feature recognition method according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0046] Step S102: using a first sensor to obtain registration data of a biometric feature and generate a first image;

[0047] Step S104: converting the first image into a second image;

[0048] Step S106: generating template data based on the first image and the second image;

[0049] Step S108: using the first sensor or the second sensor to obtain the biometric data to be identified;

[0050] Step S110: Match the data to be identified with the template data to obtain the identification result.

[0051] This embodiment uses a first sensor to obtain biometric registration data and generate a first image; converts the first image into a second image; generates template data based on the first and second images; uses the first or second sensor to obtain biometric data to be recognized; and matches the data to be recognized with the template data to obtain a recognition result. This solves the inconvenience of requiring multiple registrations for devices with multiple sensors, thereby achieving the effect of eliminating the need for multiple sensor registrations and facilitating use. Biometrics include, but are not limited to, fingerprints, palm prints, and faces.

[0052] The technical solution of this embodiment can be used as a fingerprint recognition method. There are multiple sensors in the smart terminal device that can collect fingerprints. Due to the slight differences between each sensor, the related technology requires that each sensor be registered separately before it can be used for subsequent fingerprint recognition. The technical solution of this embodiment uses the first sensor to collect the registration data of the fingerprint to generate a first image, and converts the first image into a second image based on the difference between the two sensors. The second image can be used as the image obtained by collecting the same fingerprint by the second sensor. Template data of the two sensors is generated based on the two images for subsequent comparison. Since the first image can be directly converted into the second image, there is no need to collect registration data through the second sensor again. The effect of one registration can be achieved for multiple sensors, which is convenient for users.

[0053] Optionally, before converting the first image into the second image, the first and second calibration images of the calibration plate are acquired through the first and second sensors; and calibration data of the first and second sensors are acquired based on the first and second calibration images. The two sensors respectively acquire images of the same calibration plate to obtain the first and second calibration images. Based on these two calibration images, the feature differences between the two sensors can be determined, and the calibration data of the two sensors can be acquired. In this way, the template image acquired by one sensor can be converted into the template image of the other sensor based on the calibration data. The fingerprint can be matched with the second sensor to unlock the device without being registered on the second sensor. It should be noted that after the feature match is successful, a variety of operations can be performed, not limited to unlocking, and can also include payment, ringing, screen lighting, and other types of results.

[0054] The pattern on the calibration plate may include one or more different patterns, such as checkerboard, stripes, dots, etc. In actual use, it can be selected according to different algorithms to achieve better calibration and contrast effects.

[0055] This method can be used to register multiple sensors at once. The principle is the same when used on more sensors, so I will not go into details.

[0056] Optionally, obtaining calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image includes: extracting first feature data of the first calibration image and second feature data of the second calibration image; calculating a difference value between the first feature data and the second feature data, and obtaining calibration data of the first sensor and the second sensor based on the difference value.

[0057] Optionally, the difference value includes a deformation coefficient, a size variation coefficient, and a feature point variation coefficient.

[0058] Optionally, the biometric feature recognition method further includes performing denoising and / or alignment processing on the data to be recognized.

[0059] For example, in one embodiment, denoising and / or aligning the data to be identified includes: denoising the data to be identified to obtain denoised data; aligning the denoised data to obtain aligned data, and then performing feature extraction on the aligned data to match it with the template data.

[0060] When converting two images, a trained deep learning model can be used to convert the first image into the second image, which can improve the efficiency and accuracy of each image conversion.

[0061] Before image conversion, the deep learning model can be trained using first training data of the biometric features acquired by the first sensor and second training data of the biometric features acquired by the second sensor, respectively, to obtain a trained deep learning model.

[0062] Optionally, the template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

[0063] Optionally, stitching the multiple first images or the multiple second images separately includes: registering the first image or the second image based on the features or pixels of a single first image or a single second image to obtain an overlapping area; and stitching the multiple first images or the multiple second images based on the overlapping area.

[0064] If the biometric feature is a fingerprint, the fingerprint area that can be collected each time is limited due to the position of the sensor. In this case, multiple collections are required and the multiple first images or multiple second images collected are spliced ​​to obtain a template image.

[0065] Optionally, the first sensor and the second sensor include a sensor located on the side of the electronic device and a sensor under the screen. Setting them at these two locations can facilitate users to unlock the electronic device by collecting fingerprints.

[0066] The embodiment of the present invention also provides a specific implementation method.

[0067] Taking foldable smart devices as an example, Figure 2 This is a schematic diagram of the sensor setting area of ​​​​this embodiment. The device is equipped with both a side fingerprint sensor and an under-screen fingerprint sensor. Users can choose to register and recognize fingerprints through the side fingerprint sensor or the under-screen fingerprint sensor.

[0068] Figure 3 Schematic diagram of the calibration process of this embodiment. The calibration method includes:

[0069] S301: Acquire a first calibration image of a calibration plate through the under-screen fingerprint sensor;

[0070] S302: Acquire a second calibration image of the calibration plate through the side fingerprint sensor;

[0071] S303: Extracting first feature data of the first calibration image;

[0072] S304: extracting second feature data of the second calibration image;

[0073] S305: Calculating the difference between the first feature data and the second feature data;

[0074] S306: Obtain calibration data of the under-screen fingerprint sensor and the side fingerprint sensor based on the difference value.

[0075] Since the input source is the same, that is, the same calibration plate, but the output source is inconsistent, that is, the first calibration image and the second calibration image collected will be different. Based on the characteristics of the output sources of the two, such as deformation coefficient, size change coefficient, feature point change and other characteristics, the calibration data of the under-screen fingerprint sensor and the side fingerprint sensor can be obtained to realize subsequent image conversion.

[0076] There is no restriction on the order in which the under-screen fingerprint sensor and the side fingerprint sensor obtain the calibration plate image. That is, the under-screen fingerprint sensor and the side fingerprint sensor can obtain the calibration plate image at the same time or at different times. Figure 4 Schematic diagram of a portion of the calibration plate of this embodiment.

[0077] Figure 5 This is a flow chart of the fingerprint recognition method of this embodiment, which takes the registration of fingerprint information on the under-screen fingerprint sensor as an example. Specifically, it includes:

[0078] S501: Using the under-screen fingerprint sensor to obtain fingerprint registration data and generate a first image;

[0079] S502: Converting the first image into a second image based on calibration data of the under-screen fingerprint sensor and the side fingerprint sensor, i.e., generating a second image corresponding to the side fingerprint sensor;

[0080] In one embodiment, a trained deep learning model can be used to convert a first image into a second image, such as a CycleGAN network model, which mainly learns the quality changes between the two images, including line thickness, blur, noise, etc. The CycleGAN network model may include a generation network, a discrimination network, a feature extraction network, etc. The generated image and the groundtruth image should be able to extract enough identical (or similar) features in the overlapping area. When training the deep learning model, the input samples can include images captured by the side fingerprint sensor and the under-screen fingerprint sensor. Based on the calibration data of the under-screen fingerprint sensor and the side fingerprint sensor, the image generated by the deep learning model is transformed in position to generate a second image corresponding to the side fingerprint sensor.

[0081] S503: Generate template data based on the first image and the second image;

[0082] When obtaining fingerprint registration data through the under-screen fingerprint sensor, the template data can be the first image captured during a single registration or the first image saved by stitching fingerprint images captured during multiple registrations;

[0083] If the registration data of the fingerprint is obtained through the side fingerprint sensor, due to the size and position limitations of the side fingerprint sensor, usually only a partial fingerprint image can be collected during registration. Therefore, the template data can be the first image saved after stitching together the fingerprint images collected through multiple registrations.

[0084] Generally, stitching methods include direct and indirect methods. Among them, the indirect method: first extract the features of the first image or the second image, then align multiple first images or multiple second images based on the features to obtain overlapping areas; stitch multiple first images or multiple second images based on the overlapping areas, and the features include but are not limited to detail points, ridges, local texture features, etc. The direct method: directly align the pixels of a single first image or a single second image to obtain overlapping areas; stitch multiple first images or multiple second images based on the overlapping areas. Direct methods include gradient descent method, phase correlation method, etc.

[0085] The first image generated by direct registration and the first image obtained by splicing, as well as the second image obtained by conversion, are all saved in the template library as fingerprint templates.

[0086] S504: Obtain the fingerprint data to be identified through the under-screen fingerprint sensor or the side fingerprint sensor.

[0087] S505: Preprocess the data to be recognized. The preprocessing includes but is not limited to at least one of the following: image denoising, image alignment, feature extraction, image conversion, etc.

[0088] S506: Match the pre-processed data to be identified with the template data to obtain a fingerprint identification result.

[0089] In one embodiment, during recognition, the pre-processed data to be recognized is matched with the stored fingerprint template data after feature value extraction. If the match is successful, the recognition is successful.

[0090] In another embodiment, when one of the sensors receives a fingerprint image, it is matched with the fingerprint template data stored in the template library to determine whether it is a registered fingerprint.

[0091] It should be noted that you can also use the side fingerprint sensor to obtain fingerprint registration information and then generate an image corresponding to the under-screen fingerprint sensor.

[0092] The technical solution of this embodiment can be applied to devices equipped with multiple fingerprint sensors. Users only need to perform a single registration on one of the side or under-screen fingerprint sensors to be recognized on both sensors.

[0093] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0094] An embodiment of the present invention provides a biometric feature recognition device, which can be used to perform the biometric feature recognition method of the embodiment of the present invention.

[0095] Figure 6 is a schematic diagram of a biometric identification device according to an embodiment of the present invention. Figure 6 As shown, the device includes:

[0096] The acquisition unit 10 is configured to acquire biometric registration data using a first sensor and generate a first image;

[0097] a conversion unit 20, configured to convert the first image into a second image;

[0098] A generating unit 30, configured to generate template data based on the first image and the second image;

[0099] an acquiring unit 40, configured to acquire the biometric data to be identified using the first sensor or the second sensor;

[0100] The matching unit 50 is configured to match the data to be identified with the template data to obtain an identification result.

[0101] This embodiment includes an acquisition unit 10, which is used to use a first sensor to obtain registration data of a biometric feature and generate a first image; a conversion unit 20, which is used to convert the first image into a second image; a generation unit 30, which is used to generate template data based on the first image and the second image; an acquisition unit 40, which is used to use the first sensor or the second sensor to obtain data to be identified of the biometric feature; and a matching unit 50, which is used to match the data to be identified with the template data to obtain an identification result, thereby solving the problem that a device with multiple sensors needs to be registered multiple times and is inconvenient to use, thereby achieving an effect of not needing to register multiple sensors multiple times and being convenient to use.

[0102] Optionally, the device further includes: a calibration acquisition unit, used to acquire a first calibration image and a second calibration image of the calibration plate through the first sensor and the second sensor before converting the first image into the second image; and a calibration acquisition unit, used to acquire calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image.

[0103] Optionally, the conversion unit 20 is configured to convert the first image into the second image based on the calibration data.

[0104] Optionally, the calibration acquisition unit includes: an extraction module for extracting first feature data of the first calibration image and second feature data of the second calibration image; a calculation module for calculating a difference value between the first feature data and the second feature data, and acquiring calibration data of the first sensor and the second sensor based on the difference value.

[0105] Optionally, the conversion unit 20 converts the first image into the second image using a trained deep learning model.

[0106] Optionally, the template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

[0107] The biometric recognition device includes a processor and a memory. The above-mentioned collection unit, conversion unit, generation unit, acquisition unit, matching unit, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0108] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and by adjusting the kernel parameters, multiple sensors do not need to be registered multiple times for convenient use.

[0109] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0110] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the biometric feature recognition method of the present invention is executed.

[0111] An embodiment of the present invention provides a processor, which is used to run a program, wherein the biometric feature recognition method is executed when the program is run.

[0112] An embodiment of the present invention provides a device comprising at least one processor, at least one memory device connected to the processor, and a bus. The processor and the memory device communicate with each other via the bus. The processor is configured to invoke program instructions stored in the memory device to execute the biometric recognition method described above. The device herein may be a server, a PC, a PAD, a mobile phone, or the like.

[0113] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: using a first sensor to obtain registration data of a biometric feature and generate a first image; converting the first image into a second image; generating template data based on the first image and the second image; using the first sensor or the second sensor to obtain data to be identified of the biometric feature; matching the data to be identified with the template data to obtain an identification result.

[0114] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. 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.

[0116] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0119] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0120] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0122] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A biometric identification method, characterized in that: include: Acquire biometric registration data using a first sensor and generate a first image; converting the first image into a second image; generating template data based on the first image and the second image; Acquiring the biometric data to be identified using the first sensor or the second sensor; Matching the data to be identified with the template data to obtain an identification result; Before converting the first image into a second image, the method further includes: Acquire a first calibration image and a second calibration image of a calibration plate using a first sensor and a second sensor, wherein a feature difference between the first sensor and the second sensor is determined based on the first calibration image and the second calibration image; acquiring calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image, wherein the calibration data is obtained by the feature difference; Converting the first image into the second image includes converting the first image into the second image based on the calibration data.

2. The method according to claim 1, characterized in that The acquiring calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image includes: extracting first feature data of the first calibration image and second feature data of the second calibration image; A difference value between the first feature data and the second feature data is calculated, and calibration data of the first sensor and the second sensor are acquired based on the difference value.

3. The method according to claim 2, characterized in that The difference values ​​include deformation coefficient, size variation coefficient, and feature point variation coefficient.

4. The method according to claim 1, wherein The method further comprises: Performing denoising and / or alignment processing on the data to be identified.

5. The method according to claim 1, wherein The first image is converted into the second image using a trained deep learning model.

6. The method according to claim 5, characterized in that The deep learning model is trained using first training data of the biometric feature acquired by the first sensor and second training data of the biometric feature acquired by the second sensor, respectively, to obtain a trained deep learning model.

7. The method according to claim 1, characterized in that The template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

8. The method according to claim 7, characterized in that The stitching of the plurality of first images or the plurality of second images comprises: Registering the first image or the second image based on features or pixels of a single first image or a single second image to obtain an overlapping area; The plurality of first images or the plurality of second images are stitched together based on the overlapping area.

9. The method according to claim 1, characterized in that The biometric features include fingerprints, palm prints, and faces.

10. The method according to claim 1, characterized in that The first sensor and the second sensor include a sensor located on a side of the electronic device and a sensor under the screen.

11. A biometric identification device, characterized in that: include: an acquisition unit, configured to acquire registration data of a biometric feature using a first sensor and generate a first image; a conversion unit, configured to convert the first image into a second image; a generating unit, configured to generate template data based on the first image and the second image; an acquiring unit, configured to acquire the biometric data to be identified using the first sensor or the second sensor; A matching unit, configured to match the data to be identified with the template data to obtain an identification result; a calibration acquisition unit, configured to acquire, by means of a first sensor and a second sensor, a first calibration image and a second calibration image of a calibration plate before converting the first image into a second image, wherein a feature difference between the first sensor and the second sensor is determined based on the first calibration image and the second calibration image; a calibration acquisition unit, configured to acquire calibration data of the first sensor and the second sensor based on the first calibration image and the second calibration image, wherein the calibration data is obtained by the feature difference; The conversion unit is configured to convert the first image into the second image based on the calibration data.

12. The device according to claim 11, characterized in that The calibration acquisition unit includes: an extraction module, configured to extract first feature data of the first calibration image and second feature data of the second calibration image; A calculation module is configured to calculate a difference value between the first feature data and the second feature data, and obtain calibration data of the first sensor and the second sensor based on the difference value.

13. The device according to claim 11, characterized in that The conversion unit converts the first image into the second image using a trained deep learning model.

14. The device according to claim 11, characterized in that The template data includes single template data directly extracted from the first image and the second image, and / or synthetic template data obtained by splicing multiple first images or multiple second images.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the biometric recognition method according to any one of claims 1 to 10 is performed.

16. A device, characterized in that The device includes at least one processor, and at least one memory and bus connected to the processor, wherein the processor and the memory communicate with each other through the bus, and the processor is used to call program instructions in the memory to execute the biometric recognition method described in any one of claims 1 to 10.

Images