Imaging object recognition method, apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application provide an imaging object recognition method, an apparatus, an electronic device, and a storage medium. The method comprises: acquiring a plurality of pieces of echo data separately generated by a fingerprint sensor on the basis of a plurality of preset configurations and corresponding to an imaging object; and recognizing the material of the imaging object on the basis of the plurality of pieces of echo data. In the embodiments of the present application, on the basis of the fact that a same material has different echo signals in different configurations, a plurality of pieces of echo data of an imaging object are acquired on the basis of a plurality of preset configurations, so that the material of the imaging object can be better distinguished on the basis of the plurality of pieces of echo data, thereby achieving a better recognition effect. When the method is used for fingerprint anti‑spoofing, a real finger can be better distinguished from a fake finger. When the method is used for recognizing a protective film of a display screen, the material of the protective film can be recognized.

Description

Imaging target recognition methods, devices, electronic equipment, and storage media

[0001] This application claims priority to Chinese Patent Application No. 202510061164.3, filed on January 14, 2025, entitled “Imaging Target Recognition Method, Apparatus, Electronic Device and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of electronic equipment technology, specifically to an imaging target recognition method, apparatus, electronic device, and storage medium. Background Technology

[0003] Biometric systems are widely used to improve the security of electronic devices. Fingerprint recognition systems, in particular, are widely used in personal electronic devices such as mobile phones, where they can be used for unlocking devices, mobile payments, account logins, and real-name authentication.

[0004] Fingerprint anti-counterfeiting is a critical issue for fingerprint recognition systems, specifically preventing the imitation of live fingerprints. If a live fingerprint is successfully imitated, unauthorized unlocking, payments, and account logins could be mistakenly approved, potentially leading to serious consequences.

[0005] In ultrasonic fingerprint systems, different materials exhibit varying acoustic impedances, resulting in different responses even under the same configuration. Related technologies attempt to distinguish imaging targets with different acoustic impedances by acquiring images of a single configuration. However, because the acoustic impedance of some materials is close to that of a real finger, these materials show low response differentiation under the same configuration and cannot completely distinguish imaging targets with different acoustic impedances. Summary of the Invention

[0006] In view of the above problems, embodiments of this application provide an imaging target recognition method, apparatus, electronic device, and storage medium to solve the above technical problems.

[0007] In a first aspect, embodiments of this application provide an imaging target recognition method, which is applied to an electronic device. The method includes: acquiring multiple echo data corresponding to an imaging target generated by a fingerprint sensor according to multiple preset configurations; and identifying the material of the imaging target based on the multiple echo data.

[0008] In some embodiments, identifying the material of an imaging target based on the plurality of echo data includes: calculating one or more preset joint index values ​​based on the plurality of echo data, wherein at least one joint index value is calculated based on the joint index values ​​of at least two echo data; and identifying the material of the imaging target based on the one or more joint index values ​​and the index value range corresponding to the material.

[0009] In some embodiments, identifying the material of an imaging target based on one or more joint index values ​​includes: determining whether one or more joint index values ​​conform to the index value range of the target material, and determining whether the imaging target is the target material based on the determination result.

[0010] In some embodiments, the echo data is an image, and the indicators of the echo data include at least one of the following: image signal quantity, image signal-to-noise ratio, signal sensitivity, imaging sensitivity, AC signal amplitude in the image, AC signal amplitude in the image after removing the background pattern, image fluctuation information calculated in the spatial domain, and data amplitude of the image. The signal sensitivity is the image signal quantity obtained by one integration, and the imaging sensitivity is the AC signal quantity increased by one integration.

[0011] In some embodiments, identifying the material of an imaging target based on the plurality of echo data includes: inputting the plurality of echo data into an imaging target identification model so that the imaging target identification model outputs a model output indicating the material of the imaging target.

[0012] In some embodiments, the model output is a score indicating that the imaging target is the target material; or the model output is material information of the imaging target.

[0013] In some embodiments, the imaging target recognition model is a neural network model, and the neural network model is trained to extract joint features of multiple echo data generated based on multiple preset configurations to obtain the model output.

[0014] In some embodiments, the acoustic frequencies and / or flight times of any two of the plurality of preset configurations are different.

[0015] In some embodiments, before acquiring multiple echo signals corresponding to the imaging target generated by the fingerprint sensor according to multiple preset configurations, the method further includes: for each of the multiple preset configurations: using the fingerprint sensor to emit an acoustic signal at the acoustic frequency of the preset configuration; using the fingerprint sensor to receive the echo signal reflected by the imaging target from the acoustic signal according to the flight time of the preset configuration and outputting the echo data corresponding to the preset configuration.

[0016] In some embodiments, the method further includes: traversing configurations in a configuration space, and for each configuration: generating echo data of a test imaging target based on the configuration, and calculating multiple indicators of the echo data to obtain multiple evaluation indicators of the configuration; the test imaging target includes fingerprints of a real finger and fingerprints of a fake finger; selecting the multiple preset configurations from the configuration space based on the multiple evaluation indicators of each configuration in the configuration space.

[0017] In some embodiments, the configuration space is defined by a range of acoustic frequencies and a range of flight times, the configuration including acoustic frequencies and flight times.

[0018] In some embodiments, generating echo data of a test imaging target according to a configuration includes: transmitting an acoustic signal at a configured acoustic frequency using a fingerprint sensor; adaptively determining the number of integrations using the fingerprint sensor; receiving the echo signal reflected by the acoustic signal from the test imaging target based on the number of integrations and a configured time of flight; and outputting echo data corresponding to the configuration.

[0019] In some embodiments, selecting the plurality of preset configurations from the configuration space based on multiple evaluation metrics for each configuration includes: for each evaluation metric: obtaining a heatmap of the evaluation metric according to the combination of acoustic frequency and time of flight for each configuration, the heatmap representing the size distribution of the evaluation metric in different configurations; projecting the heatmap onto a three-dimensional space according to the evaluation metric value corresponding to each configuration to obtain a three-dimensional heatmap; determining the average Euclidean distance from each pixel point corresponding to each configuration to other pixels in the three-dimensional heatmap, and determining candidate configurations corresponding to the evaluation metric based on the average Euclidean distance corresponding to each configuration; and selecting the plurality of preset configurations from the plurality of candidate configurations corresponding to the plurality of evaluation metrics.

[0020] In some embodiments, before determining the average Euclidean distance from each pixel point corresponding to each configuration in the three-dimensional heatmap to other pixels, the method further includes: identifying and removing outlier points of the evaluation metrics in the heatmap.

[0021] In some embodiments, identifying the material of an imaging target based on multiple echo data includes: determining whether the imaging target is human epidermal tissue based on the multiple echo data.

[0022] In some embodiments, the fingerprint sensor is located inside or under the display screen, and the method further includes: identifying whether the imaging target is a fingerprint based on multiple echo data; if the imaging target is not a fingerprint and is human epidermal tissue, then determining that the display screen was not accidentally touched by a finger.

[0023] In some embodiments, the above method is applied to fingerprint anti-counterfeiting, and the imaging target is the input fingerprint, which includes fingerprints of real fingers and fingerprints of fake fingers.

[0024] In some embodiments, the electronic device includes a display screen, and the method is applied to identify the material of a protective film, with the imaging target being the protective film affixed to the surface of the display screen.

[0025] Secondly, embodiments of this application provide a fingerprint processing apparatus, which includes: a fingerprint sensor for generating multiple echo data corresponding to an imaging target according to multiple configurations; and a processing unit for executing the above-described imaging target recognition method.

[0026] Thirdly, embodiments of this application provide an electronic device, including: the fingerprint processing device described above.

[0027] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the above-described imaging target recognition method.

[0028] The imaging target recognition method, apparatus, electronic device, and storage medium provided in this application, based on the fact that the same material has different echo signals in different configurations, obtains multiple echo data corresponding to the imaging target through multiple preset configurations, and combines the multiple echo data to better identify the material of the imaging target, achieving a better recognition effect. In fingerprint anti-counterfeiting applications, it can better distinguish between genuine and fake fingers. In display screen protector recognition applications, it can identify the material of the protective film.

[0029] These or other aspects of this application will become more apparent from the description of the following embodiments. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1A shows a schematic diagram of an electronic device that may be applied according to an exemplary embodiment of this application.

[0032] Figure 1B shows a schematic diagram of another applicable electronic device according to an exemplary embodiment of this application.

[0033] Figure 1C shows a system block diagram of an electronic device to which an exemplary embodiment of this application may be applied.

[0034] Figure 2 shows a flowchart of an imaging target recognition method according to an exemplary embodiment of this application.

[0035] Figure 3 shows a schematic diagram of an acoustic imaging model to which an exemplary embodiment of this application may be applied.

[0036] Figure 4 shows a flowchart of a method for determining multiple preset configurations according to an exemplary embodiment of this application.

[0037] Figure 5 shows a flowchart of a method for selecting multiple preset configurations from a configuration space according to an exemplary embodiment of this application.

[0038] Figure 6A shows a heatmap of exemplary evaluation metrics from an embodiment of this application.

[0039] Figure 6B shows a three-dimensional heatmap of exemplary evaluation metrics from an embodiment of this application.

[0040] Figure 7 shows a flowchart of identifying imaging targets according to predefined rules.

[0041] Figure 8 shows a flowchart of a typical fingerprint anti-counterfeiting method according to an exemplary embodiment of this application.

[0042] Figure 9 shows a flowchart of another typical fingerprint anti-counterfeiting method according to an exemplary embodiment of this application.

[0043] Figure 10 shows a flowchart of a typical protective film identification method according to an exemplary embodiment of this application.

[0044] Figure 11 shows a structural block diagram of a fingerprint processing apparatus according to an exemplary embodiment of this application. Detailed Implementation

[0045] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0046] To enable those skilled in the art to better understand the solutions of this application, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0047] In the embodiments of this application, it should be noted that, in this document, relational terms such as first and second are used only 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.

[0048] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0049] In the description of the embodiments of this application, the words "example" or "for example" are used to indicate exemplification, illustration, or description. Any embodiment or design described as "example" or "for example" in the embodiments of this application is not to be construed as being more preferred or having more advantages than another embodiment or design. The use of the words "example" or "for example" is intended to present relative concepts in a clear manner.

[0050] Furthermore, in the embodiments of this application, "multiple" refers to two or more. Therefore, in the embodiments of this application, "multiple" can also be understood as "at least two". "At least one" can be understood as one or more, such as one, two, or more. For example, including at least one means including one, two, or more, and is not limited to which ones are included. For example, including at least one of A, B, and C, then it could include A, B, C, A and B, A and C, B and C, or A and B and C.

[0051] It should be noted that in the embodiments of this application, "and / or" describes the relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. In addition, the character " / ", unless otherwise specified, generally indicates that the associated objects before and after it are in an "or" relationship.

[0052] It should be noted that in the embodiments of this application, "connection" can be understood as electrical connection. The connection between two electrical components can be a direct or indirect connection between the two electrical components. For example, the connection between A and B can be a direct connection between A and B, or an indirect connection between A and B through one or more other electrical components.

[0053] Figures 1A and 1B illustrate schematic diagrams of electronic devices in which various solutions described herein can be implemented according to exemplary embodiments of this application. As shown in Figures 1A and 1B, the electronic device 100 may include a device body 101 and a fingerprint sensor 102. The fingerprint sensor 102 can acquire fingerprint images for fingerprint recognition. The fingerprint sensor 102 may include an ultrasonic fingerprint sensor, which can emit ultrasonic waves toward an imaging target and receive the echoes, generating an image of the imaging target based on the echoes. The specific location of the fingerprint sensor 102 in the electronic device 100 may be located on the side, back, front, or below the front display screen of the device body 101, depending on the actual product design requirements.

[0054] In some embodiments, the electronic device 100 may be a portable electronic device, such as a smartphone, tablet, laptop, personal digital assistant, etc. In other embodiments, the electronic device 100 may also be a smart wearable device, such as a smartwatch, virtual reality headset, augmented reality headset, etc. This application does not limit the type of electronic device 100.

[0055] In some embodiments, the fingerprint sensor 102 may be specifically disposed on the side of the device body 101 of the electronic device 100; as smartphones or other portable electronic devices develop towards thinner or foldable designs, the thickness of the electronic device 100 becomes smaller and smaller, resulting in the fingerprint sensor 102 disposed on the side of the device body 101 becoming narrower and narrower.

[0056] Referring to Figure 1A, as a typical embodiment, the device body 101 includes a display screen 10 and a mid-frame 20. The display screen 10 is located on the front of the device body 101, used to display images and provide a human-computer interaction interface for the user. The mid-frame 20 is generally located between the display screen 10 and the rear shell of the electronic device, used to support the display screen 10 and to carry various functional components inside the device body 101, such as the motherboard, battery, camera, speaker, microphone, various sensing units, etc. In a specific embodiment, the mid-frame 20 includes a border surrounding the device body 101. The border may include multiple sides and carry a power button, volume buttons, or other function buttons. A fingerprint sensor 102 may be disposed on one side of the border and has a sensing area 108. In a specific embodiment, the fingerprint sensor 102 may be a fingerprint recognition chip or a fingerprint module with a fingerprint recognition chip. It may be integrated above the power button or volume buttons on the side of the border, embedded in a predetermined area on the side of the border, or attached to the inner surface of the side of the border, to allow the user to input their fingerprint to realize the side fingerprint function of the electronic device 100.

[0057] In some embodiments, the fingerprint sensor 102 may be disposed in a partial or complete area beneath the display screen 10, thereby forming an under-display fingerprint system. Alternatively, the fingerprint sensor 102 may be partially or completely integrated into the display screen 10 of the electronic device, thereby forming an in-display fingerprint system. Compared to the fingerprint sensor 102 being disposed in an area outside the display screen on the front of the device, the fingerprint sensor 102 being disposed beneath the display screen of the electronic device 100 or integrated into the display screen 10 can improve the screen-to-body ratio of the electronic device.

[0058] Referring to Figure 1B, as another typical embodiment, the difference from the embodiment in Figure 1A is that the fingerprint sensor 102 is located below the display screen 10, i.e., inside the display screen 10. The display screen 10 consists of a cover glass 11, a touchpad 12, and a display panel 13 from top to bottom. The fingerprint sensor 102 can be located below the display panel 13. The fingerprint sensor 102 has a sensing area 108, and the area on the display screen 10 corresponding to the sensing area 108 is the fingerprint collection area. Typically, a visual prompt can be displayed on the display screen 10 regarding the fingerprint collection area to inform the user of its location.

[0059] The fingerprint sensor 102 can emit acoustic signals and receive echo signals reflected from a finger, generating a fingerprint image based on the echo signals. Specifically, referring to Figure 1B, the fingerprint sensor 102 can emit acoustic signals to the display screen 10, allowing the acoustic signals to penetrate the cover glass 11, touchpad 12, and display panel 13, etc. The signal can be reflected by a finger located on the outer surface of the cover glass 11 to form an echo signal. The echo signal penetrates the cover glass 11, touchpad 12, and display panel 13, etc., and reaches the sensing area 108 of the fingerprint sensor 102. The fingerprint sensor 102 generates a fingerprint image based on the echo signal. Figure 1A is similar to Figure 1B and will not be described again here.

[0060] Referring to Figure 1C, the fingerprint sensor 102 includes a sensing array 103, an output module 104, an interface module 105, and a driving module 106. The sensing array 103 is used to couple with the user's finger when the user presses the fingerprint sensor 102 to input a fingerprint, thereby acquiring the user's fingerprint information. Specifically, it includes multiple sensing units arranged in an array. The area where the sensing array 103 is located, or its effective fingerprint acquisition area, is the sensing area 108 of the fingerprint sensor 102. The sensing array 103 is also called a pixel array, and the sensing units are also called pixel units. The driving module 106 and the output module 104 are connected to the sensing array 103 and the interface module 105, respectively. The driving module 106 drives the sensing array 103 to perform fingerprint scanning to acquire the user's fingerprint information. The output module 104 generates corresponding fingerprint data based on the fingerprint information acquired by the sensing array 103 and outputs the fingerprint data to the control system 120 through the interface module 105. The interface module 105 can specifically be a Serial Peripheral Interface (SPI).

[0061] Referring again to Figure 1C, the control system 120 may include one or more general-purpose single-chip or multi-chip processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or combinations thereof. According to some examples, the control system 120 may include dedicated components for controlling the fingerprint sensor 102. In some implementations, the functionality of the control system 120 may be partitioned between one or more controllers or processors, such as between a dedicated sensor controller and an application processor of the electronic device. Referring to Figure 1C, the control system 120 may include an application processor 121 of the electronic device. The application processor 121 can be a central processing unit (CPU) or other processing unit or control unit with processing capabilities inside the electronic device 100, such as a microcontroller (MCU). It is connected to the interface module 105 and includes a fingerprint processing unit. It is mainly used to control the working state of the fingerprint sensor 102, process the fingerprint data output by the fingerprint sensor 102, and perform fingerprint template registration and fingerprint matching verification to determine whether the currently collected fingerprint image is a legitimate fingerprint. Based on the judgment result, it unlocks the electronic device 100 or performs other functions related to fingerprint recognition.

[0062] This application provides an imaging target recognition method, which can be applied to the electronic device 100 shown in Figures 1A, 1B, and 1C. Figure 2 shows a flowchart of an imaging target recognition method provided by this application. This method identifies the material of the imaging target based on multiple echo data corresponding to the imaging target generated by a fingerprint sensor according to multiple preset configurations. This method can be applied to fingerprint anti-counterfeiting to better distinguish between genuine and fake fingers, improving the anti-counterfeiting effect. This method can also be used for protective film recognition to identify the material of the protective film applied to the display screen. As shown in Figure 2, it specifically includes the following steps.

[0063] Step S201: Obtain multiple echo data corresponding to the imaging target generated by the fingerprint sensor according to multiple preset configurations.

[0064] In the embodiments of this application, the imaging target in the fingerprint anti-counterfeiting application is the input fingerprint, which may be a genuine fingerprint or a fake fingerprint. Fake fingerprints can be forged from materials such as resin and gelatin. Different materials have different acoustic impedances. Referring to the imaging model in Figure 3, the acoustic impedance of air is relatively small, approximately 0.004 MRayls, much smaller than the acoustic impedance of the display screen (screen cover) of 14 MRayls, and ultrasonic waves undergo total internal reflection at the fingerprint ridges. The measured acoustic impedance of fake fingerprint materials and genuine fingerprints is on the same order of magnitude as that of the display screen (screen cover), approximately 1–3 MRayls. Specifically, the acoustic impedance of the skin surface is approximately 1.68 MRayls, the acoustic impedance of resin is approximately 2.86 MRayls, and the typical acoustic impedance of gelatin is approximately 2.07 MRayls. There is partial reflection and partial transmission at the ridges of genuine and fake fingerprints. Assuming the ridge-valley duty cycle in the image is 50%, ideally, the difference in image data exchange and / or signal quantity mainly originates from the ridges and is only related to the material's acoustic impedance. The actual imaging model is related not only to acoustic impedance, but also to good contact, fingerprint edge shape, material sound velocity, etc., and cannot be decoupled.

[0065] In the embodiments of this application, in order to better distinguish between genuine and fake fingers and improve the fingerprint anti-counterfeiting effect, the characteristic of the same material having different echo signals in different configurations is utilized. In the electronic device 100, the fingerprint sensor 102 can generate multiple echo data corresponding to the input fingerprint according to multiple preset configurations. Furthermore, it is possible to determine whether the input fingerprint is a genuine fingerprint based on the multiple echo data corresponding to the input fingerprint. Possible implementation methods will be described later in this specification.

[0066] On the one hand, the same material produces different echo signals under acoustic signals of different frequencies, and there is no direct or inverse proportional relationship between the acoustic impedance and the echo signals. In other words, materials with different acoustic impedances do not exhibit a direct or inverse proportional relationship between their echo signals and acoustic signals of different frequencies. In some implementations, any two preset configurations may have different acoustic frequencies. The acoustic frequency refers to the frequency of the acoustic signal emitted by the fingerprint sensor. On the other hand, different Time of Flight (TOF) values ​​result in different received echo signals; specifically, the amplitude of the echo signals received in different time windows varies. Different echo data can be generated by controlling the TOF, i.e., receiving echo signals and outputting corresponding echo data in different time windows. In some implementations, the TOF can be different for different configurations.

[0067] In some possible implementations, in the electronic device 100, the application processor 121 can control the fingerprint sensor 102 to generate multiple echo data corresponding to the input fingerprint according to multiple preset configurations. Among these, any two preset configurations have different acoustic frequencies, and at least two configurations have different flight times. Specifically, for each preset configuration: the application processor 121 controls the fingerprint sensor 102 to emit an acoustic signal at the acoustic frequency of that preset configuration, and controls the fingerprint sensor 102 to receive the echo signal reflected by the input fingerprint according to the flight time of that preset configuration, and output the echo data corresponding to that preset configuration. The echo data can be a fingerprint image. The fingerprint sensor 102 can output the echo data corresponding to the preset configuration through the output module 105, and send the echo data to the application processor 121 through the interface module 105. The application processor 121 includes a fingerprint processing unit, which can process the echo data.

[0068] Typically, when the fingerprint sensor 102 receives echo signals and outputs echo data, the configuration also includes the number of integrations. In some implementations, the number of integrations can be adaptively determined. Specifically, for each of multiple preset configurations: the application processor 121 controls the fingerprint sensor 102 to emit an acoustic signal at the acoustic frequency of that preset configuration, controls the fingerprint sensor 102 to adaptively determine the number of integrations, and, based on the number of integrations and the flight time of the preset configuration, receives the echo signal reflected by the input fingerprint and outputs the echo data corresponding to that preset configuration. In some implementations, the number of integrations is defined in the preset configuration. By pre-defining the number of integrations in the preset configuration, differences in echo data caused by variations in the number of integrations can be largely avoided. Specifically, for each of multiple preset configurations: the application processor 121 controls the fingerprint sensor 102 to emit an acoustic signal at the acoustic frequency of that preset configuration, controls the fingerprint sensor 102 to receive the echo signal reflected by the input fingerprint and output the echo data corresponding to that preset configuration based on the number of integrations and the flight time of the preset configuration.

[0069] Furthermore, in some implementations, the application processor 121 can control the fingerprint sensor 102 to generate the aforementioned multiple echo data in parallel. For example, the fingerprint sensor 102 can generate echo data corresponding to configuration 0 and configuration 1 respectively, substantially simultaneously. In some implementations, the application processor 121 can control the fingerprint sensor 102 to generate the aforementioned multiple echo data serially. For example, the fingerprint sensor 102 generates echo data corresponding to configuration 0 according to configuration 0, and then generates echo data corresponding to configuration 1 according to configuration 1. In some implementations, the application processor 121 can control the fingerprint sensor 102 to generate the aforementioned multiple echo data in part-parallel and part-serial. For example, the fingerprint sensor 102 can generate echo data corresponding to configuration 0 and configuration 1 respectively, substantially simultaneously, and then generate echo data corresponding to configuration 2 according to configuration 2. In specific implementations, the serial, parallel, or combined serial and parallel methods can be selected to generate multiple echo data according to multiple configurations, depending on the processing speed requirements.

[0070] In embodiments of this application, multiple preset configurations can be predetermined and stored in the electronic device 100, for example, in the memory of the electronic device 100. In embodiments of this application, in the electronic device 100, the fingerprint sensor 102 can activate the fingerprint acquisition function upon detecting user finger contact or according to the instructions of the application processor 121 of the electronic device 100, and generate echo data corresponding to the input fingerprint according to the multiple predetermined configurations stored in the memory.

[0071] In some possible implementations, as shown in FIG4, the method for determining the above-mentioned multiple preset configurations may include the following steps.

[0072] Step S401: Traverse the configurations in the configuration space. For each configuration: generate echo data of the test imaging target based on the configuration, and calculate multiple indicators of the echo data to obtain multiple evaluation indicators for the configuration. The test imaging target can include fingerprints of real fingers and fake fingers made of various materials.

[0073] The configuration space can be a three-dimensional space consisting of sound wave frequency, flight time, and number of integrations, where all points in this three-dimensional space are possible configurations. In a specific implementation, the sound wave frequency range can be divided into multiple sound wave frequency points according to a certain step size; similarly, the flight time range can be divided into multiple flight time points. Multiple configurations are formed by combining multiple sound wave frequency points, multiple flight time points, and multiple number of integrations. Each configuration consists of sound wave frequency, flight time, and number of integrations. Specifically, the sound wave frequency range can be between 5 MHz and 25 MHz, the flight time range can be between 200 ns and 2500 ns, and the number of integrations is not less than 1.

[0074] In some possible implementations, the configuration includes the acoustic frequency and time-of-flight. The fingerprint sensor adaptively determines the number of integration iterations. By adaptively determining the number of integration iterations, the integrated voltage under different configurations can be adjusted to the same level, thereby ensuring that the dynamic range of the fingerprint sensor is maximized and does not saturate. In this case, the configuration space is defined by the acoustic frequency range and the time-of-flight range. In a specific implementation, the acoustic frequency range can be divided into multiple acoustic frequency points according to a certain step size. Similarly, the time-of-flight range can be divided into multiple time-of-flight points. Multiple configurations are formed by combining multiple acoustic frequency points and multiple time-of-flight points, and each configuration consists of an acoustic frequency and a time-of-flight.

[0075] Specifically, for each configuration: generating echo data corresponding to the test imaging target according to the configuration may include: using a fingerprint sensor to emit an acoustic signal at a configured acoustic frequency, using the fingerprint sensor to adaptively determine the number of integrations, and based on the number of integrations and the configured flight time, receiving the echo signal reflected by the acoustic signal from the test imaging target and outputting the echo data corresponding to the configuration.

[0076] Furthermore, in embodiments of this application, the echo data can be an image, and the indicators of the echo signal can include, but are not limited to, at least one of the following: image signal quantity, image signal-to-noise ratio, signal sensitivity, imaging sensitivity, AC signal amplitude in the image, AC signal amplitude in the image after removing the background pattern, image fluctuation information (i.e., spatial noise) calculated in the spatial domain, and image data amplitude. Signal sensitivity is the image signal quantity obtained by one integration, and imaging sensitivity is the AC signal quantity increased by one integration.

[0077] Step S402: Select the multiple preset configurations from the configuration space based on the multiple evaluation indicators of each configuration in the configuration space.

[0078] In some possible implementations, as shown in Figure 5, selecting the multiple preset configurations from the configuration space based on multiple evaluation metrics of each configuration in the configuration space may include the following steps.

[0079] For each evaluation indicator, steps S501 and S504 are performed to determine the candidate configuration corresponding to each evaluation indicator.

[0080] Step S501: A heat map of the evaluation index is obtained according to the combination of sound wave frequency and flight time for each configuration. The heat map represents the size distribution of the evaluation index in different configurations.

[0081] Please refer to Figure 6A. In this exemplary heatmap, the horizontal direction represents time of flight, and the vertical direction represents sound frequency. The time of flight can range from 200 ns to 2500 ns, and the sound frequency can range from 5 MHz to 25 MHz. Each pixel in the heatmap represents a configuration composed of time of flight and sound frequency. The value of each pixel is the value of the evaluation metric. This heatmap represents the distribution of the evaluation metric across different configurations. In the heatmap, darker colors correspond to larger (or smaller) evaluation metrics. Specifically, if a larger evaluation metric is better, then a darker color corresponds to a larger evaluation metric; if a smaller evaluation metric is better, then a darker color corresponds to a smaller evaluation metric. Furthermore, in Figure 6A, "#" indicates points with missing data or values ​​that are too large or too small.

[0082] Step S502: Project the heat map onto a three-dimensional space according to the evaluation index value corresponding to each configuration to obtain a three-dimensional heat map.

[0083] Step S503: Determine the average Euclidean distance from each pixel in the three-dimensional heat map to other pixels.

[0084] Please refer to Figure 6B. The three dimensions of the 3D heatmap are sound frequency, flight time, and evaluation index value, respectively. Each configuration's sound frequency, flight time, and evaluation index value correspond to a pixel in the 3D heatmap. The pixel corresponding to the i-th configuration can be represented as (F... i T i S i ), where Fi represents the i-th configured sound wave frequency, T i S represents the flight time of the i-th configuration. i This represents the evaluation index value for the i-th configuration of this evaluation index. i The Euclidean distance L between the pixel corresponding to the j-th configuration and the pixel corresponding to the j-th configuration is... ij The calculation method is as follows:

[0085] In the formula, (F i T i S i ) represents the pixel point corresponding to the i-th configuration, (F j T j S j The pixel corresponding to the j-th configuration.

[0086] Step S504: Determine the candidate configurations corresponding to the evaluation indicators based on the average Euclidean distance for each configuration.

[0087] In the embodiments of this application, considering that the actual sound wave frequency and flight time may deviate from the configured sound wave frequency and flight time when generating echo data according to the configuration, in order to avoid such deviation from causing abnormal echo data, through steps S501 to S504, the configurations adjacent to the candidate configuration also have evaluation index sizes similar to those of the candidate configuration.

[0088] In some embodiments, before determining the average Euclidean distance from each pixel in the 3D heatmap to other pixels, the method further includes: identifying and removing outliers in the heatmap for evaluation metrics. Specifically, a window of a preset size is used to define the neighborhood of each pixel in the heatmap. For each pixel, the number of pixels in its neighborhood is checked. If a pixel has fewer than a preset number of pixels in its neighborhood, it is considered an outlier. In a specific implementation, the window size can be set to 3.3, and the preset number can be set to 3. That is, a 3.3 window is used to define the neighborhood of each pixel in the heatmap. For each pixel, the number of pixels in its neighborhood is checked. If a pixel has fewer than 3 pixels in its neighborhood, it is considered an outlier.

[0089] Step S505: Select the multiple preset configurations from the multiple candidate configurations corresponding to multiple evaluation indicators.

[0090] In the embodiments of this application, the results of different evaluation indicators are compared, and multiple preset configurations are selected according to project requirements. For example, configuration 0 selects the configuration with the highest image signal-to-noise ratio, configuration 1 selects the configuration with the highest signal sensitivity, and configuration 2 selects the configuration with the lowest spatial noise.

[0091] Step S202: Identify the material of the imaging target based on the multiple echo data.

[0092] In the embodiments of this application, the material of the imaging target can be identified according to predefined rules, or an imaging target identification model can be used to identify the material of the imaging target. These two implementation methods are described below.

[0093] Method 1

[0094] Figure 7 shows a flowchart of identifying the material of the imaging target according to predefined rules. As shown in Figure 7, it may specifically include the following steps.

[0095] Step S701: Calculate one or more preset joint index values ​​based on multiple echo data, wherein at least one joint index value is calculated based on the joint index of at least two echo data.

[0096] Specifically, the echo data can be a fingerprint image, and the indicators of the echo data can include at least one of the following: image signal quantity, image signal-to-noise ratio, signal sensitivity, imaging sensitivity, AC signal amplitude in the image, AC signal amplitude after removing the background pattern in the image, image fluctuation information calculated in the spatial domain, and image data amplitude. The signal sensitivity is the image signal quantity obtained by one integration, and the imaging sensitivity is the AC signal quantity increased by one integration.

[0097] For ease of understanding, the joint indicators are illustrated by example.

[0098] In some implementations, the metrics for the echo data may include the amplitude of the AC signal in the image. Table 1 shows the AC signal amplitudes of materials 1, 2, 3, and 4 in images from configurations 0 and 1. Configuration 0 uses an 11.5 MHz ultrasonic transmission frequency, a 1300 ns flight time, and 20 integrations, while configuration 1 uses a 14.5 MHz ultrasonic transmission frequency, a 1400 ns flight time, and 30 integrations. Configurations 0 and 1 differ in both the acoustic frequency, flight time, and number of integrations.

[0099] Table 1

[0100] As shown in Table 1, the AC signal amplitude in the images corresponding to configurations 0 and 1 is not significantly different between materials 1, 2, 3, and 4, indicating that the index differences of the echo data for a single configuration are not significant. Subtracting the result corresponding to configuration 0 from the result corresponding to configuration 1, i.e., the joint index is the difference in AC signal amplitude in the images under the two configurations, results in a negative value for material 3, while the others are all positive values ​​greater than 10. It is evident that the joint index based on the difference in AC signal amplitude in the images under the two configurations can effectively distinguish material 3 from materials 1, 2, and 4.

[0101] In some implementations, the metrics for echo data may include signal sensitivity. Table 2 shows the signal sensitivity of materials 1, 2, 3, and 4 in configurations 0, 1, and 2.

[0102] Table 2

[0103] As shown in Table 2, the signal sensitivity of materials 1, 2, 3, and 4 under configurations 0, 1, and 1 is not significantly different, meaning the differences in the echo data of individual configurations are not obvious. The formula for calculating the joint index value is: (Configuration 2 · Configuration 0) / Configuration 1. The calculated result for material 3 differs significantly from that of materials 1, 2, and 4, and can effectively distinguish material 3 from materials 1, 2, and 4.

[0104] Step S702: Identify the material of the imaging target based on the one or more joint index values ​​and the index value range corresponding to the material.

[0105] In possible embodiments of this application, the index value ranges of multiple materials can be predetermined, and the index value range of any one material may include the range of one or more joint index values. The joint indexes of different materials may be different. For example, the index value range of a first material may include a first joint index value range and a second joint index value range, and the index value range of a second material may include a third joint index value range. The first material is different from the second material. If the joint index value of the imaging target conforms to the index value range corresponding to the material, then the imaging target is that material. This embodiment can identify which material the imaging target belongs to among multiple materials.

[0106] In a possible embodiment of this application, the index value range of the target material can be predetermined. If the joint index value of the imaging target matches the index value range of the target material, then the imaging target is the target material. This embodiment is capable of identifying whether the imaging target is the target material.

[0107] In some possible implementations, this method can be applied to accidental touch recognition. Specifically, it determines whether the imaging target is human skin tissue based on multiple echo data. If the imaging target is not human skin tissue, it can be determined that it is non-human contact. In some implementations, referring to Figure 1B, the fingerprint sensor is located inside or below the display screen, forming an under-screen or in-screen fingerprint recognition system. The fingerprint sensor detects the object in contact with the display screen and generates multiple echo data corresponding to the contact object according to multiple preset configurations. Based on the multiple echo data, it determines whether the contact object is human skin tissue. If the contact object is not human skin tissue, it can be determined that it is non-human contact with the display screen; if the contact object is human skin tissue, it can be determined that it is human contact with the display screen. Further, it can be determined whether the contact object is a fingerprint based on the echo data. If it is human skin tissue and not a fingerprint, it can be determined that it is a non-finger accidental touch; if it is human skin tissue and is a fingerprint, it can be determined that it is finger contact.

[0108] In some possible implementations, this method can be applied to the identification of protective films on displays to identify the material of the protective film applied to the display screen. Specifically, in the protective film identification application, the imaging target is the protective film applied to the display screen. Multiple index value ranges for different film materials are preset, and the method can determine which range the combined index values ​​of the protective film meet, thus identifying the protective film as the corresponding film material. In practical applications, the materials of the protective film may include: polypropylene (PP), polyvinyl chloride (PVC), polyethylene terephthalate (PET), and thermoplastic polyurethane (TPU). If the combined index values ​​of the protective film meet the index value range of polypropylene, then the material of the protective film is determined to be polypropylene; if the combined index values ​​of the protective film meet the index value range of polyvinyl chloride, then the material of the protective film is determined to be polyvinyl chloride; if the combined index values ​​of the protective film meet the index value range of polyethylene terephthalate, then the material of the protective film is determined to be polyethylene terephthalate; and so on, the material of the protective film can be determined to be thermoplastic polyurethane.

[0109] In some possible implementations, this method can be applied to fingerprint anti-counterfeiting to determine whether an input fingerprint is from a genuine finger. Specifically, in fingerprint anti-counterfeiting applications, the imaging target is the input fingerprint. One or more joint indicator values ​​can be determined to be within the range of indicator values ​​for a genuine finger. Based on the determination result, it is determined whether the input fingerprint is from a genuine finger. If a single joint indicator value is used, the input fingerprint is determined to be from a genuine finger if the joint indicator value is within the range of indicator values ​​for a genuine finger; otherwise, it is determined to be from a fake finger. If multiple joint indicator values ​​are used, the input fingerprint can be determined to be from a genuine finger if any joint indicator value is within the range of indicator values ​​for a genuine finger; otherwise, it is determined to be from a fake finger. Alternatively, the input fingerprint can be determined to be from a genuine finger if all multiple joint indicator values ​​are within the range of indicator values ​​for a genuine finger. In specific implementations, the judgment rules can be set as needed.

[0110] In practical implementation, multiple echo data points from genuine fingers and prosthetic fingers made of various materials under different configurations can be analyzed. Based on actual needs, the indicators from these multiple echo data points are jointly calculated to select a joint indicator value that can distinguish between genuine and prosthetic fingers. A range of genuine finger indicator values ​​is defined, forming a predefined rule composed of the joint indicator value and the genuine finger indicator value range. During fingerprint anti-counterfeiting, the joint indicator value corresponding to the input fingerprint is determined, and based on whether the joint indicator value of the input fingerprint conforms to the corresponding genuine finger indicator value range, it is determined whether the input fingerprint is a genuine fingerprint.

[0111] The typical process of the above-described imaging target recognition method in fingerprint anti-counterfeiting applications can be summarized by the flowchart shown in Figure 8. Figure 8 shows a flowchart of a fingerprint anti-counterfeiting method according to an exemplary embodiment of the present disclosure. As shown in Figure 8, the fingerprint anti-counterfeiting method of the present disclosure embodiment may include steps S801 to S805.

[0112] Step S801: Obtain multiple pre-stored preset configurations.

[0113] In the embodiments of this application, in the electronic device 100, the fingerprint sensor 102 can activate the fingerprint acquisition function upon detecting a user's finger contact or according to the instruction of the application processor 121 of the electronic device 100, and read a plurality of predetermined preset configurations stored in the memory. Any two preset configurations have different acoustic frequencies, and optionally, at least two preset configurations have different flight times. Optionally, the plurality of preset configurations also include integration counts. In some implementations, the preset configurations do not include integration counts, which are adaptively determined by the fingerprint sensor. The following description assumes that the preset configurations include integration counts.

[0114] The fingerprint sensor can generate echo data corresponding to the input fingerprint according to multiple preset configurations. In the electronic device 100, the application processor 121 can control the fingerprint sensor 102 to generate echo data corresponding to the input fingerprint according to multiple preset configurations. Specifically, steps S802 to S803 are executed for each of the multiple preset configurations.

[0115] In step S802, the fingerprint sensor emits an acoustic signal at a preset acoustic frequency.

[0116] In step S803, the fingerprint sensor receives the echo signal reflected by the input fingerprint from the acoustic signal according to the preset flight time and number of integrations, and outputs the echo data corresponding to the preset configuration.

[0117] In the embodiments of this application, if the preset configuration does not include the number of integrations, the fingerprint sensor can adaptively determine the number of integrations, and based on the determined number of integrations and the preset flight time, receive the echo signal reflected by the input fingerprint from the acoustic signal and output the echo data corresponding to the preset configuration.

[0118] Step S804: Calculate one or more preset joint index values ​​based on multiple echo data generated by multiple preset configurations, wherein at least one joint index value is calculated based on the joint index of at least two echo data.

[0119] In the embodiments of this application, the echo data is a fingerprint image, and the indicators of the echo data may include, but are not limited to, at least one of the following: image signal quantity, image signal-to-noise ratio, signal sensitivity, imaging sensitivity, AC signal amplitude in the image, AC signal amplitude after removing the background pattern in the image, image fluctuation information calculated in the spatial domain, and image data amplitude.

[0120] Step S805: Determine whether the one or more combined index values ​​meet the index value range of a real finger, and determine whether the input fingerprint is a real finger fingerprint based on the determination result.

[0121] Specifically, if a single joint indicator value is used, the input fingerprint is determined to be a genuine fingerprint if the joint indicator value falls within the corresponding genuine fingerprint indicator value range. If multiple joint indicator values ​​are used, the input fingerprint can be determined to be a genuine fingerprint if any single joint indicator value falls within the corresponding genuine fingerprint indicator value range; alternatively, the input fingerprint can be determined to be a genuine fingerprint if all multiple joint indicator values ​​fall within the corresponding genuine fingerprint indicator value range. In the specific implementation, the judgment rules can be set as needed.

[0122] Method 2

[0123] In Method Two, multiple echo data are input into the imaging target recognition model, causing the model to output a model output indicating the material of the imaging target. One implementation is that the model output is a score indicating whether the imaging target is the target material, used to identify whether the material of the imaging target is the target material. Another implementation is that the model output is the material information of the imaging target. Specifically, the model output can be a probability distribution for multiple materials: for each material, the model output is a value between 0 and 1, summing to 1, representing the probability that the model considers the input data to belong to that material. In some cases, the model output can be the label of the most likely material, i.e., the material with the highest probability.

[0124] In some possible implementations, the imaging target recognition model is a neural network model, and this neural network model is trained to extract joint features from multiple echo data generated based on multiple preset configurations to obtain the model output. The neural network model may include a convolutional neural network model, which may include convolutional layers that perform convolution operations on multiple echo data to extract joint features from the multiple echo data.

[0125] In protective film recognition applications, the model output can be the material information of the protective film. Specifically, multiple echo data of various film materials under multiple configurations can be collected, and their material information can be labeled as the corresponding materials. The collected data is used to train the network parameters of a neural network so that the neural network can distinguish different materials. Specifically, the materials of the protective film can include: polypropylene (PP), polyvinyl chloride (PVC), polyethylene terephthalate (PET), thermoplastic polyurethane (TPU), etc.

[0126] In fingerprint anti-counterfeiting applications, one implementation is that the model outputs a score indicating that the input fingerprint is from a genuine finger. Another implementation is that the model outputs material information of the input fingerprint; if the material information indicates that the input fingerprint is finger epidermal tissue, then the input fingerprint can be determined to be from a genuine finger; otherwise, the input fingerprint is determined to be a fake fingerprint.

[0127] As one implementation, the neural network model is trained to receive multiple echo data corresponding to an input fingerprint, process these multiple echo data, and output a score indicating that the input fingerprint is a genuine finger. Specifically, multiple echo data of a genuine finger in multiple configurations can be collected and labeled as a genuine finger; multiple echo data of fake fingers made of various materials in multiple configurations can be collected and labeled as fake fingers. The network parameters of the neural network are trained using the aforementioned collected data so that the neural network can distinguish between genuine and fake fingers.

[0128] As another implementation, the neural network model is trained to receive multiple echo data corresponding to the input fingerprint, process these multiple echo data, and output the material information of the input fingerprint. Specifically, multiple echo data of a real finger in multiple configurations can be collected, and its material information can be labeled as skin; multiple echo data of a prosthetic finger made of various materials in multiple configurations can be collected, and its material information can be labeled as the corresponding material. The network parameters of the neural network are trained using the aforementioned collected data so that the neural network can distinguish between different materials.

[0129] The typical process of the above-described imaging target recognition method in fingerprint anti-counterfeiting applications can be summarized by the flowchart shown in Figure 9. Figure 9 shows a flowchart of a fingerprint anti-counterfeiting method according to an exemplary embodiment of the present disclosure. As shown in Figure 9, the fingerprint anti-counterfeiting method of the present disclosure embodiment includes steps S901 to S905.

[0130] Step S901: Obtain multiple pre-stored preset configurations.

[0131] In the embodiments of this application, in the electronic device 100, the fingerprint sensor 102 can activate the fingerprint acquisition function upon detecting a user's finger contact or according to the instruction of the application processor 121 of the electronic device 100, and read a plurality of predetermined preset configurations stored in the memory. Any two preset configurations have different acoustic frequencies, and optionally, at least two preset configurations have different flight times. Optionally, the plurality of preset configurations also include integration counts. In some implementations, the preset configurations do not include integration counts, which are adaptively determined by the fingerprint sensor. The following description uses an example where the preset configurations do not include integration counts.

[0132] The fingerprint sensor can generate echo data corresponding to the input fingerprint according to multiple preset configurations. In the electronic device 100, the application processor 121 can control the fingerprint sensor 102 to generate echo data corresponding to the input fingerprint according to multiple preset configurations. Specifically, steps S902 to S903 are executed for each of the multiple preset configurations.

[0133] In step S902, the fingerprint sensor emits an acoustic signal at a preset acoustic frequency.

[0134] In step S903, the fingerprint sensor adaptively determines the number of integrations, and based on the number of integrations and the preset flight time, receives the echo signal reflected by the input fingerprint from the acoustic signal and outputs the echo data corresponding to the preset configuration.

[0135] Step S904: Input multiple echo data into the fingerprint anti-counterfeiting model so that the fingerprint anti-counterfeiting model outputs a model output indicating whether the input fingerprint is a genuine finger.

[0136] Step S905: Determine whether the input fingerprint is a genuine finger fingerprint based on the model output.

[0137] If the model output is a score indicating that the input fingerprint is a genuine fingerprint, the score can be compared with a preset threshold. If the score is greater than the preset threshold, the input fingerprint is a genuine fingerprint; otherwise, the input fingerprint is not a genuine fingerprint, that is, the input fingerprint is a fake fingerprint.

[0138] If the model output is the material information of the input fingerprint, it determines whether the material of the input fingerprint is skin. If the material information indicates that the input fingerprint is skin, then the input fingerprint is a real finger fingerprint; otherwise, it is determined that the input fingerprint is a fake fingerprint.

[0139] The typical process of the above-described imaging target recognition method in the application of protective film recognition can be summarized by the flowchart shown in FIG10. FIG10 shows a flowchart of a protective film recognition method according to an exemplary embodiment of the present disclosure. As shown in FIG10, the protective film recognition method of the present disclosure embodiment includes steps S1001 to S1004.

[0140] Step S1001: Obtain multiple pre-stored preset configurations.

[0141] In the embodiments of this application, in the electronic device 100, the fingerprint sensor 102 can activate the fingerprint acquisition function according to the instructions of the application processor 121 of the electronic device 100, and read a plurality of predetermined preset configurations stored in the memory. Any two preset configurations have different acoustic frequencies, and optionally, at least two preset configurations have different flight times. Optionally, the plurality of preset configurations also include integration counts. In some implementations, the preset configurations do not include integration counts, and the integration counts are adaptively determined by the fingerprint sensor. The following description uses an example where the preset configurations do not include integration counts.

[0142] The fingerprint sensor can generate echo data corresponding to the imaging target according to multiple preset configurations. In the embodiments of this application, in the electronic device 100, referring to FIG1B, a protective film is pasted on the surface of the display screen 10. The fingerprint sensor 102 sends an acoustic wave signal, which is reflected by the protective film to form an echo signal. The fingerprint sensor 102 receives the echo data and outputs the echo data. In the electronic device 100, the application processor 121 can control the fingerprint sensor 102 to generate echo data corresponding to the protective film according to multiple preset configurations. Specifically, steps S1002 to S1003 are executed for each of the multiple preset configurations.

[0143] In step S1002, the fingerprint sensor emits an acoustic signal at a preset acoustic frequency.

[0144] In step S1003, the fingerprint sensor adaptively determines the number of integrations, and based on the number of integrations and the preset flight time, receives the echo signal reflected by the protective film of the acoustic signal and outputs the echo data corresponding to the preset configuration.

[0145] Step S1004: Input multiple echo data into the imaging target recognition model so that the imaging target recognition model outputs a model output indicating the material of the protective film.

[0146] The specific model output can be a probability distribution for various materials: for each material, the model output is a value between 0 and 1, and the sum of these values ​​is 1. This value represents the probability that the model considers the input data to belong to that material. In some cases, the model output can be the label of the most likely material, that is, the material with the highest probability.

[0147] In another embodiment, multiple index value ranges for membrane materials can be preset. During protective film identification, one or more preset joint index values ​​are calculated based on multiple echo data. The range of index values ​​that the joint index values ​​of the protective film conform to is determined, and the protective film is identified as the corresponding membrane material. In practical applications, the materials of the protective film may include: polypropylene (PP), polyvinyl chloride (PVC), polyethylene terephthalate (PET), and thermoplastic polyurethane (TPU). If the joint index values ​​of the protective film conform to the index value range of polypropylene, the material of the protective film is determined to be polypropylene; if the joint index values ​​of the protective film conform to the index value range of polyvinyl chloride, the material of the protective film is determined to be polyvinyl chloride; if the joint index values ​​of the protective film conform to the index value range of polyethylene terephthalate, the material of the protective film is determined to be polyethylene terephthalate; and so on, the material of the protective film can be determined to be thermoplastic polyurethane.

[0148] This application also provides a fingerprint processing device, as shown in FIG11. The device includes a fingerprint sensor 1110 and a processing unit 1120. The fingerprint sensor 1110 is used to generate multiple echo data corresponding to the input fingerprint according to multiple configurations. The processing unit 1120 is used to execute the imaging target recognition method of this application embodiment. The fingerprint processing device may specifically be the electronic device 100 shown in FIG1C. Specifically, the fingerprint sensor 1110 may specifically be the fingerprint sensor 102 shown in FIG1C, and the processing unit 1120 may specifically be the application processor 121 (e.g., a central processing unit CPU) shown in FIG1C, used to execute the main steps of the methods of the above embodiments. In other alternative embodiments, the processing unit 1120 may also be implemented using other processing units or control units with image processing capabilities (e.g., microcontrollers MCUs).

[0149] This application also provides an electronic device 100, which may further include: an application processor 121; and a memory storing a program, wherein the program includes instructions that, when executed by the application processor 121, cause the application processor 121 to perform the methods of the above embodiments, such as the methods shown in FIG2, FIG4, FIG5, and FIG7 to FIG10.

[0150] This application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the application processor 121 of the electronic device 100 to execute the methods of the above embodiments, such as the methods shown in FIG2, FIG4, FIG5, and FIG7 to FIG10.

[0151] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Although this application has disclosed preferred embodiments as above, it is not intended to limit this application. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the technical solution of this application. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. An imaging target recognition method, the method being applied to an electronic device, characterized in that, The method includes: Acquire multiple echo data corresponding to the imaging target generated by the fingerprint sensor according to multiple preset configurations; The material of the imaging target is identified based on the multiple echo data.

2. The imaging target recognition method as described in claim 1, characterized in that, The material used to identify the imaging target based on the plurality of echo data includes: One or more preset joint index values ​​are calculated based on the plurality of echo data, wherein at least one of the joint index values ​​is calculated based on the joint indexes of at least two of the echo data; The material of the imaging target is identified based on one or more joint index values ​​and the range of index values ​​corresponding to the material.

3. The imaging target recognition method as described in claim 2, characterized in that, Identifying the material of the imaging target based on one or more joint index values ​​includes: Determine whether the one or more joint index values ​​meet the index value range of the target material, and determine whether the material of the imaging target is the target material based on the determination result.

4. The imaging target recognition method as described in claim 2, characterized in that, The echo data is an image, and the indicators include at least one of the following: image signal quantity, image signal-to-noise ratio, signal sensitivity, imaging sensitivity, AC signal amplitude in the image, AC signal amplitude in the image after removing the background pattern, image fluctuation information calculated in the spatial domain, and image data amplitude. The signal sensitivity is the amount of image signal obtained by one integration, and the imaging sensitivity is the amount of AC signal increased by one integration.

5. The imaging target recognition method as described in claim 1, characterized in that, The material used to identify the imaging target based on the plurality of echo data includes: The multiple echo data are input into the imaging target recognition model so that the imaging target recognition model outputs a model output indicating the material of the imaging target.

6. The imaging target recognition method as described in claim 5, characterized in that, The model output is a score indicating whether the imaging target is the target material; or The model outputs material information of the imaging target.

7. The imaging target recognition method as described in claim 5, characterized in that, The imaging target recognition model is a neural network model, and the neural network model is trained to extract joint features of multiple echo data generated based on the multiple preset configurations to obtain the model output.

8. The imaging target recognition method according to any one of claims 1 to 7, characterized in that, The sound wave frequency and / or flight time are different for any two of the plurality of preset configurations.

9. The imaging target recognition method according to any one of claims 1 to 7, characterized in that, Before acquiring multiple echo signals corresponding to the imaging target generated by the fingerprint sensor according to multiple preset configurations, the method further includes: For each of the multiple preset configurations: The fingerprint sensor is used to emit a sound wave signal at the preset configured sound wave frequency; Using the fingerprint sensor, based on the preset time of flight, the echo signal reflected by the imaging target from the acoustic wave signal is received and the echo data corresponding to the preset configuration is output.

10. The imaging target recognition method according to any one of claims 1 to 7, characterized in that, Also includes: Traverse the configurations in the configuration space, and for each configuration: generate echo data of the test imaging target according to the configuration, and calculate multiple indicators of the echo data to obtain multiple evaluation indicators of the configuration; Based on the multiple evaluation indicators of each configuration in the configuration space, the multiple preset configurations are selected from the configuration space.

11. The imaging target recognition method as described in claim 10, characterized in that, The configuration space is defined by the range of sound wave frequency and the range of flight time, and the configuration includes the sound wave frequency and the flight time.

12. The imaging target recognition method as described in claim 11, characterized in that, The step of generating echo data of the test imaging target according to the configuration includes: The fingerprint sensor is used to emit an acoustic signal at the configured acoustic frequency. The fingerprint sensor is used to adaptively determine the number of integrations. Based on the number of integrations and the configured flight time, the echo signal reflected by the acoustic signal through the test imaging target is received and the corresponding echo data is output.

13. The imaging target recognition method as described in claim 11, characterized in that, The plurality of preset configurations are selected from the configuration space according to the evaluation indicators of each configuration in the configuration space, including: For each evaluation metric: a heatmap of the evaluation metric is obtained according to the combination of sound wave frequency and flight time for each configuration. The heatmap represents the size distribution of the evaluation metric in different configurations. The heatmap is projected onto three-dimensional space according to the evaluation metric value corresponding to each configuration to obtain a three-dimensional heatmap. The average Euclidean distance from each pixel point corresponding to each configuration to other pixels in the three-dimensional heatmap is determined. Based on the average Euclidean distance corresponding to each configuration, candidate configurations corresponding to the evaluation metric are determined. The multiple preset configurations are selected from the multiple candidate configurations corresponding to the multiple evaluation indicators.

14. The imaging target recognition method as described in claim 13, characterized in that, Before determining the average Euclidean distance from each pixel in the three-dimensional heatmap to other pixels, the method further includes: Identify and remove outlier points of the evaluation index in the heatmap.

15. The imaging target recognition method according to any one of claims 1 to 14, characterized in that, The step of identifying the material of the imaging target based on the plurality of echo data includes: determining whether the imaging target is human epidermal tissue based on the plurality of echo data.

16. The imaging target recognition method as described in claim 15, characterized in that, The electronic device includes a display screen, and the fingerprint sensor is located inside or below the display screen. The method further includes: identifying whether the imaging target is a fingerprint based on the plurality of echo data; if the imaging target is not a fingerprint and is human epidermal tissue, then determining that the touch on the display screen was not accidental by a finger.

17. The imaging target recognition method according to any one of claims 1 to 14, characterized in that, The method is applied to fingerprint anti-counterfeiting, and the imaging target is the input fingerprint, which includes fingerprints from real fingers and fingerprints from fake fingers.

18. The imaging target recognition method according to any one of claims 1 to 14, characterized in that, The electronic device includes a display screen, and the method is applied to identify the material of a protective film, wherein the imaging target is the protective film attached to the surface of the display screen.

19. A fingerprint processing device, characterized in that, The device includes: A fingerprint sensor is used to generate multiple echo data corresponding to the imaging target according to multiple configurations; The processing unit is used to execute the imaging target recognition method described in any one of 1-18.

20. An electronic device, characterized in that, The electronic device includes: the fingerprint processing device according to claim 19.

21. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-18.

Images