Fingerprint anti-counterfeiting detection method, device and electronic equipment

Abstract

The present invention provides a fingerprint anti-counterfeiting detection method, device, and electronic device. The method comprises: obtaining device posture information corresponding to a fingerprint to be tested, the device posture information being used to characterize the posture state of the electronic device during the process of the electronic device acquiring a fingerprint signal from the fingerprint to be tested; performing fingerprint anti-counterfeiting detection based on the device posture information to obtain a detection result; and determining the authenticity of the fingerprint to be tested based on the detection result. By using the device posture information to perform anti-counterfeiting detection on fingerprints, the ability to detect fake fingerprints is enhanced, making it more difficult for attackers to use fake fingerprints to perform operations, and effectively improving the device's security defense capabilities.

Description

Technical Field

[0001] The present invention relates to the field of fingerprint recognition technology, and in particular to a fingerprint anti-counterfeiting detection method, device and electronic equipment. Background Art

[0002] With the widespread use of electronic devices, including smartphones, tablets, laptops, portable gaming consoles, and fingerprint locks, the security requirements for these devices are becoming increasingly stringent. Currently, fingerprint detection technology is widely used to verify the identity of users of electronic devices. This technology utilizes optical, capacitive, or ultrasonic fingerprint sensors installed on the electronic device to collect fingerprint signals and then uses fingerprint recognition algorithms to verify the user's identity.

[0003] With the popularization of fingerprint detection technology, fake fingerprints made of materials such as paper, film, and plastic are becoming increasingly realistic. Existing fingerprint detection technology is difficult to effectively detect new types of fake fingerprints or has a low effective detection rate for fake fingerprints. Summary of the Invention

[0004] In view of this, an object of the present invention is to provide a fingerprint anti-counterfeiting detection method, device and electronic device method, device and electronic device to alleviate the technical problem of limited detection capability of fake fingerprints in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a fingerprint anti-counterfeiting detection method, which is applied to an electronic device. The method includes: obtaining device posture information corresponding to the fingerprint to be tested, wherein the device posture information is used to characterize the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be tested; performing fingerprint anti-counterfeiting detection according to the device posture information to obtain a detection result; and determining the authenticity of the fingerprint to be tested based on the detection result.

[0006] Furthermore, the device posture information includes acceleration information and / or angular velocity information of the electronic device; the step of performing fingerprint anti-counterfeiting detection based on the device posture information and obtaining the detection result includes: performing fingerprint anti-counterfeiting detection based on the acceleration information and / or angular velocity information of the electronic device and obtaining the detection result.

[0007] Furthermore, the step of obtaining device posture information corresponding to the fingerprint to be tested includes at least one of the following: when the electronic device first collects the fingerprint signal of the fingerprint to be tested, obtaining the device posture information corresponding to the moment of first collection; obtaining the device posture information corresponding to each moment from the start to the end of the fingerprint signal collection of the fingerprint to be tested at a first sampling interval, and obtaining a first device posture information sequence; obtaining the device posture information corresponding to each moment within a first time period after the start of fingerprint signal collection of the fingerprint to be tested at a second sampling interval, and obtaining a second device posture information sequence; when the electronic device is in a device posture collection mode, obtaining and storing the device posture information of the electronic device at a third sampling interval, and retaining part or all of the device posture information stored before the start of fingerprint signal collection of the fingerprint to be tested, and obtaining a third device posture information sequence.

[0008] Furthermore, the device posture acquisition mode is a powered-on state, a low-power state, or a state triggered and set by a user of the electronic device.

[0009] Furthermore, the step of performing fingerprint anti-counterfeiting detection according to the device posture information and obtaining a detection result includes: performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information and obtaining a detection result.

[0010] Furthermore, the step of performing fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information to obtain a detection result includes: performing a first fingerprint anti-counterfeiting detection on the fingerprint signal to obtain a first detection result; performing a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result; and the step of determining the authenticity of the fingerprint to be tested based on the detection results includes: determining the authenticity of the fingerprint to be tested based on the first detection result and the second detection result.

[0011] Furthermore, the step of determining the authenticity of the fingerprint to be tested based on the first detection result and the second detection result includes: if the first detection result and / or the second detection result indicates a fake fingerprint, determining that the fingerprint to be tested is a fake fingerprint.

[0012] Furthermore, the step of performing fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information to obtain a detection result includes: performing a first fingerprint anti-counterfeiting detection on the fingerprint signal to obtain a first detection result; if the first detection result is characterized as a true fingerprint or the first detection result is characterized as a pending fingerprint, performing a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result; accordingly, the step of determining the authenticity of the fingerprint to be tested based on the detection result includes: determining the authenticity of the fingerprint to be tested based on the second detection result.

[0013] Furthermore, the step of determining the authenticity of the fingerprint to be tested according to the second detection result includes: if the second detection result indicates a fake fingerprint, determining that the fingerprint to be tested is a fake fingerprint.

[0014] Furthermore, the electronic device includes a first type of application scenario configured with a first fingerprint anti-counterfeiting function and a second type of application scenario configured with a second fingerprint anti-counterfeiting function; wherein, the security level of the first type of application scenario is higher than the security level of the second type of application scenario; the step of performing fingerprint anti-counterfeiting detection according to the device posture information and obtaining the detection result includes: if the electronic device is in the first type of application scenario, performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information, and obtaining the detection result; if the electronic device is in the second type of application scenario, performing fingerprint anti-counterfeiting detection according to the fingerprint signal or the device posture information, and obtaining the detection result.

[0015] Furthermore, the fingerprint signal is a fingerprint image of the fingerprint to be tested; the step of performing a first fingerprint anti-counterfeiting test on the fingerprint signal to obtain the first test result includes: extracting actual feature parameters of the fingerprint image; wherein the actual feature parameters include at least one of the following: pixel value statistical parameters, texture parameters and brightness parameters; and determining the first test result based on the actual feature parameters.

[0016] Furthermore, the step of performing fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information includes: inputting the fingerprint signal into a first neural network model to perform a first fingerprint anti-counterfeiting detection to obtain a first detection result; inputting the device posture information into a second neural network model to perform a second fingerprint anti-counterfeiting detection to obtain a second detection result; wherein, the first neural network model is trained using real fingerprint samples and forged fingerprint samples; the second neural network model is trained using real posture samples and forged posture samples, the real posture sample is the posture state of the electronic device during the process of collecting the fingerprint signal of the real fingerprint, and the forged posture sample is the posture state of the electronic device during the process of collecting the fingerprint signal of the forged fingerprint.

[0017] Furthermore, the first detection result is a probability value that the fingerprint to be tested is a fake fingerprint; if the probability value is less than a preset first threshold, the first detection result is characterized as a true fingerprint; or; if the probability value is less than a preset second threshold, the first detection result is characterized as a true fingerprint, and, if the probability value is greater than or equal to the second threshold and less than or equal to the first threshold, the first detection result is characterized as a pending fingerprint; wherein, the first threshold is greater than the second threshold.

[0018] In a second aspect, an embodiment of the present invention provides a fingerprint anti-counterfeiting detection device, which is applied to an electronic device, and the device includes: an acquisition module, used to obtain device posture information corresponding to the fingerprint to be tested; wherein the device posture information is used to characterize the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be tested; a detection module, used to perform fingerprint anti-counterfeiting detection based on the device posture information to obtain a detection result; and an anti-counterfeiting determination module, used to determine the authenticity of the fingerprint to be tested based on the detection result.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device comprising an acquisition device, a processing device and a storage device, wherein the acquisition device is used to obtain the fingerprint signal and device posture information of the fingerprint to be tested; the storage device stores a computer program, and the computer program executes the above-mentioned fingerprint anti-counterfeiting detection method when the processed device is running.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned fingerprint anti-counterfeiting detection method.

[0021] The embodiments of the present invention bring the following beneficial effects:

[0022] Embodiments of the present invention provide a fingerprint anti-counterfeiting detection method, device, and electronic device, which perform anti-counterfeiting detection based on device posture information when obtaining a fingerprint signal of a fingerprint to be tested, and determine the authenticity of the fingerprint to be tested based on the detection result obtained by the detection, thereby increasing the difficulty for attackers to use fake fingerprints to operate and effectively improving the security defense capabilities of the device.

[0023] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by practicing the above-mentioned technology of the present disclosure.

[0024] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1A schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0027] Figure 2 A flowchart of a fingerprint anti-counterfeiting detection method provided by an embodiment of the present invention;

[0028] Figure 3 A flowchart of another fingerprint anti-counterfeiting detection method provided by an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of a scenario application of a fingerprint anti-counterfeiting detection method provided by an embodiment of the present invention;

[0030] Figure 5 A schematic diagram of a fingerprint anti-counterfeiting detection device provided by an embodiment of the present invention;

[0031] Figure 6 A schematic structural diagram of another electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0033] With the development of intelligent technologies such as the Internet of Things (IoT), artificial intelligence (AI), and big data, the demand for transforming and upgrading the traditional logistics industry through these technologies is growing stronger. Intelligent logistics (Intelligent Logistics System) has become a research hotspot in the logistics field. Intelligent logistics utilizes AI, big data, and IoT devices and technologies such as information sensors, radio frequency identification (RFID), and the Global Positioning System (GPS). These technologies are widely applied to fundamental activities such as material transportation, warehousing, distribution, packaging, loading and unloading, and information services. This enables intelligent analysis and decision-making, automated operations, and efficient optimization of material management processes. IoT technologies include sensing devices, RFID, laser infrared scanning, and infrared sensor recognition. The IoT effectively connects materials in logistics to the network, enabling real-time monitoring of materials. It also senses environmental data such as humidity and temperature in warehouses to ensure a safe and secure storage environment. Big data technologies can sense and collect all logistics data, upload it to the data layer of an information platform, and filter, mine, and analyze the data. Ultimately, this data provides accurate data support for business processes such as transportation, warehousing, storage and retrieval, picking, packaging, sorting, outbound delivery, inventory, and distribution. The application of artificial intelligence in logistics can be broadly categorized into two main areas: 1) AI-enabled intelligent devices such as unmanned trucks, AGVs, AMRs, forklifts, shuttle trucks, stackers, unmanned delivery vehicles, drones, service robots, robotic arms, and smart terminals are replacing some manual labor; 2) software systems such as transportation equipment management systems, warehouse management systems, equipment scheduling systems, and order distribution systems are driven by technologies or algorithms like computer vision, machine learning, and operations optimization to improve human efficiency. With the research and advancement of smart logistics, this technology has been applied in numerous fields, including retail and e-commerce, electronics, tobacco, pharmaceuticals, industrial manufacturing, footwear and apparel, textiles, and food.

[0034] Currently, fake fingerprints made of materials such as paper, film, and plastic are becoming increasingly realistic. Existing methods that rely solely on fingerprint signals are prone to low detection rates for fake fingerprints. Therefore, embodiments of the present invention provide a fingerprint anti-counterfeiting detection method, device, and electronic device. The method provided by embodiments of the present invention can effectively improve the detection capabilities of electronic devices for fake fingerprints.

[0035] Figure 1 FIG1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention, which is used for fingerprint anti-counterfeiting detection. Figure 1In the embodiment, the electronic device includes an acquisition device for acquiring the fingerprint signal and device posture information of the fingerprint to be tested. The acquisition device may specifically include a fingerprint module and a device posture information collector, wherein the fingerprint module is used to acquire the user's fingerprint signal. In addition to the fingerprint sensor fingerprint, the fingerprint module may also include related circuits and optical components. The device posture information collector is used to acquire the device posture information of the electronic device during the process of the fingerprint module acquiring the fingerprint signal. The above-mentioned electronic device also includes a processing device connected to the acquisition device, and a storage device connected to the processing device, the storage device is used to store information and data used in the detection process, such as the above-mentioned fingerprint signal and device posture information, as well as computer programs. The computer program executes the following fingerprint anti-counterfeiting detection method when the processed device is running.

[0036] For ease of understanding, before describing specific embodiments, the definitions of true fingerprints and false fingerprints involved in the present invention are explained as follows:

[0037] The difference between a real fingerprint and a fake fingerprint in the embodiments of the present invention lies in the fact that when collecting fingerprints, the fingerprint to be tested pressing the fingerprint recognition area in the electronic device is a real finger or an attack material. The real finger includes real fingers in various states, including but not limited to:

[0038] 1) Clean fingers: Wash your hands and dry your fingers with a tissue.

[0039] 2) Oily fingers: Fingers coated with oily skin care products.

[0040] 3) Wet fingers: After washing your hands, wipe your fingers with a wet towel.

[0041] 4) Fingers at room temperature: Fingers used for fingerprint recognition at room temperature of 20-30 degrees.

[0042] 5) Fingers in a dry and cold state: Fingers in an environment with a temperature below zero degrees, such as -5 degrees.

[0043] 6) Finger in strong light: The image is collected under sunlight. The angle of sunlight hitting the screen can be divided into multiple angles, such as 10 degrees, 45 degrees, and 90 degrees.

[0044] In actual applications, the finger state during fingerprint detection can be any of the above states, or a combination of the above states, such as a wet finger at room temperature, or a clean finger under strong light. It should be understood that the above situations are only examples of finger conditions in actual fingerprint recognition, and the genuine fingerprints in the fingerprint anti-counterfeiting detection method of the embodiments of the present invention are not limited to the above situations.

[0045] In contrast to the above-mentioned real fingerprints, fake fingerprints are fingerprints that are identified using attack materials. Attack materials include various forged fingerprint samples, including but not limited to:

[0046] 1) Colored paper 2D sample: Use a black and white printer to print the fingerprint pattern on various colored printing papers. The printing paper colors include white, red, yellow, blue, green, etc.

[0047] 2) Color printed 2D sample: Use a color printer to print the fingerprint pattern on white printing paper. The fingerprint colors include red, yellow, blue, green, etc.

[0048] 3) 2.5D Sample: Using the fingerprint image, a fingerprint mold with concave and convex surfaces is made using a printed circuit board (PCB). This mold is then used to create a silicone fingerprint sample. The silicone color includes transparent, black, light yellow, white, etc.

[0049] 4) 3D Sample: Using a real fingerprint, we create a reversed fingerprint structure on the modeling gel, including complete depth information. This 3D mold is then used to create a silicone fingerprint sample. Silicone colors include transparent, black, light yellow, and white.

[0050] It is understandable that the above situations are only examples of situations in which attack materials are actually used for fingerprint identification, and the fake fingerprints in the fingerprint anti-counterfeiting detection method of the present invention are not limited to the above situations.

[0051] Figure 2 This is a flow chart of a fingerprint anti-counterfeiting detection method provided by an embodiment of the present invention. The method is applied to an electronic device and specifically includes steps S201-S203:

[0052] S201: Acquire device posture information corresponding to the fingerprint to be measured, where the device posture information is used to represent the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be measured.

[0053] The fingerprint to be tested in this step refers to the fingerprint of the user who wants to pass the verification of the electronic device and then operate the electronic device. When the user presses a specific area on the electronic device, the electronic device starts to perform fingerprint anti-counterfeiting detection. The embodiment of the present invention uses the posture information of the electronic device to perform anti-counterfeiting detection, so it is necessary to obtain the device posture information corresponding to the fingerprint signal of the fingerprint to be tested. In some embodiments, the screen touch component or the fingerprint module can detect whether there is a touch signal. Once the touch signal is detected, the SoC (System on aChip) of the device is notified by an interrupt to execute the fingerprint signal and device posture information collection process.

[0054] The above-mentioned fingerprint signal and device posture information can be obtained by a corresponding detection device set in the electronic device. It is understandable that the detection device can be a detection device provided by the electronic device itself, or a detection device provided separately for fingerprint anti-counterfeiting detection. For example, the fingerprint signal can be obtained by a fingerprint module provided separately for fingerprint anti-counterfeiting detection, and the device posture information can be obtained by a sensor such as an IMU (Inertial Measurement Unit) or a gyroscope provided by the electronic device itself. Since the devices provided by the electronic device itself are reused, the fingerprint anti-counterfeiting detection capability is enhanced without increasing the hardware cost.

[0055] S202: Perform fingerprint anti-counterfeiting detection based on the device posture information to obtain a detection result.

[0056] In the process of using the device posture information for anti-counterfeiting detection, fingerprint anti-counterfeiting detection can be performed solely based on the device posture information. When a genuine fingerprint is detected, the fingerprint signal can be used for subsequent processing such as fingerprint identification. Alternatively, in the process of performing anti-counterfeiting detection, the device posture information can be combined with the fingerprint signal to perform fingerprint anti-counterfeiting detection. For example, fingerprint anti-counterfeiting detection of the fingerprint signal and the device posture information can be started simultaneously. Alternatively, a sequential order can be adopted, where the fingerprint signal anti-counterfeiting detection is performed first, and then the device posture information anti-counterfeiting detection is performed. Alternatively, the device posture information anti-counterfeiting detection is performed first, and then the fingerprint signal anti-counterfeiting detection is performed. The embodiments of the present invention do not limit this.

[0057] S203: Determine the authenticity of the fingerprint to be tested based on the detection result.

[0058] In this step, the result of the fingerprint anti-counterfeiting detection may be a probability indicating whether the fingerprint to be tested is a genuine fingerprint or a fake fingerprint, or may be a binary value indicating whether the fingerprint to be tested is genuine or fake.

[0059] The fingerprint anti-counterfeiting detection method provided in the above embodiment obtains the device posture information of the fingerprint to be tested. The device posture information is used to characterize the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be tested. Fingerprint anti-counterfeiting detection is performed based on the device posture information, and then the authenticity of the fingerprint to be tested is determined based on the detection result. Since the attacker may put the device in different postures when using a fake fingerprint for detection so that the fake fingerprint can be closer to the real fingerprint at various angles, such as causing the device posture to change continuously in a short period of time, causing the device to rotate beyond a certain angle, and causing the device to have an acceleration or angular velocity exceeding a certain limit, etc. Based on this, in the fingerprint anti-counterfeiting detection process, the device posture information is taken into consideration, and fake fingerprints can be detected more effectively, thereby enhancing the detection capability of fake fingerprints, increasing the difficulty for attackers to use fake fingerprints to operate, and effectively improving the device security defense capability.

[0060] In some embodiments, the step of performing fingerprint anti-counterfeiting detection based on the device posture information may include: performing fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information to obtain a detection result. Based on this, the step may specifically include:

[0061] 1) Performing a first fingerprint anti-counterfeiting detection on the fingerprint signal to obtain a first detection result.

[0062] 2) Perform a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result.

[0063] 3) Determine the authenticity of the fingerprint to be tested based on the first detection result and the second detection result.

[0064] The above two detection processes can be carried out simultaneously, and the first detection result and the second detection result can be obtained at the same time. The method of using the above fingerprint signal and device posture information to simultaneously perform fingerprint anti-counterfeiting detection can ensure the accuracy of detection compared to the anti-counterfeiting method that only uses the fingerprint signal. At the same time, it can also flexibly use the detection results corresponding to the above fingerprint signal or device posture information based on actual application scenarios, thereby broadening the application scenarios of the technology. Based on this, in some embodiments, the step of determining the authenticity of the fingerprint to be tested based on the detection results includes: determining the authenticity of the fingerprint to be tested based on the first detection result and the second detection result. For example, if the first detection result and / or the second detection result is characterized as a fake fingerprint, the fingerprint to be tested is determined to be a fake fingerprint.

[0065] The following describes how to determine the authenticity of a fingerprint to be tested based on the first detection result and / or the second detection result in conjunction with actual application scenarios. Considering that there may be many scenarios for fingerprint detection during the use of an electronic device, some scenarios have higher security requirements, while some scenarios have lower security requirements. In order to improve the rationality of fingerprint detection, the electronic device may include a first type of application scenario configured with a first fingerprint anti-counterfeiting function and a second type of application scenario configured with a second fingerprint anti-counterfeiting function, wherein the security level of the first type of application scenario is higher than the security level of the second type of application scenario (for example, the first type of application scenario is a payment application scenario, and the second type of application scenario is an unlocking electronic device).

[0066] In the first type of application scenario (i.e., high security level), in order to reduce the situation where a fake fingerprint is identified as a real fingerprint, it is necessary to consider the above-mentioned first detection result and the second detection result at the same time, that is, perform fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information. Specifically, only when the first detection result and the second detection result are both characterized as real fingerprints, can the fingerprint to be tested be determined to be a real fingerprint and pass the fingerprint anti-counterfeiting detection. As long as one result is characterized as a fake fingerprint, the fingerprint anti-counterfeiting detection cannot be passed. Correspondingly, in the second type of application scenario (i.e., low security level), since the security requirements are not high, for example, more emphasis may be placed on the efficiency of fingerprint recognition. At this time, the authenticity of the fingerprint to be tested is determined based on the above-mentioned first detection result or the second detection result, that is, fingerprint anti-counterfeiting detection is performed based on the fingerprint signal or the device posture information. For example, as long as one of the first detection result and the second detection result is characterized as a real fingerprint, the fingerprint to be tested is determined to be a real fingerprint. Only when both results are characterized as fake fingerprints, can the fingerprint to be tested be determined to be a fake fingerprint. Therefore, the efficiency of fingerprint detection can be effectively improved and time can be saved.

[0067] In the above two detection processes, a first fingerprint anti-counterfeiting detection process can also be performed first to obtain a first detection result. If the first detection result indicates that the fingerprint to be tested is a fake fingerprint, the fingerprint to be tested is determined to be a fake fingerprint. There is no need to further perform the second fingerprint anti-counterfeiting detection process. If the first detection result indicates that the fingerprint to be tested is a genuine fingerprint or the first detection result indicates that the fingerprint to be tested is a pending fingerprint, in order to improve the accuracy of the detection, a second fingerprint anti-counterfeiting detection process is further performed to determine the authenticity of the fingerprint to be tested based on the second detection result obtained by the second fingerprint anti-counterfeiting detection. Specifically, if the second detection result indicates that the fingerprint to be tested is a genuine fingerprint, the fingerprint to be tested is determined to be a genuine fingerprint. Conversely, if the second detection result indicates that the fingerprint to be tested is a fake fingerprint, the fingerprint to be tested is determined to be a fake fingerprint.

[0068] See also Figure 3 The flowchart of another fingerprint anti-counterfeiting method provided by an embodiment of the present invention is shown, and the method specifically includes the following steps:

[0069] S301: Obtain device posture information corresponding to the fingerprint to be tested.

[0070] Step S301 can refer to the method of the above embodiment and will not be described again here.

[0071] S302: Perform a first fingerprint anti-counterfeiting detection on the fingerprint signal to obtain a first detection result.

[0072] S303: Determine whether the first detection result represents a true fingerprint or a pending fingerprint. If so, execute step S304; if not, execute step S306 to determine whether the pending fingerprint is a false fingerprint.

[0073] S304: Perform a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result.

[0074] S305: Determine the authenticity of the fingerprint to be tested according to the second detection result.

[0075] In an embodiment of the present invention, a first fingerprint anti-counterfeiting test is first performed to obtain a first test result. If the first test result indicates a genuine fingerprint or a pending fingerprint, a second fingerprint anti-counterfeiting test is performed on the device posture information to obtain a second test result. Based on the second test result, the authenticity of the fingerprint to be tested is determined.

[0076] It is understood that in the above process, after obtaining the first test result, if the first test result indicates that the fingerprint is a fake, there is no need to perform the second fingerprint anti-counterfeiting test, that is, the fingerprint to be tested is directly determined to be a fake. There is no need to further perform the second fingerprint anti-counterfeiting test process. If the first test result indicates that the fingerprint to be tested is a genuine fingerprint or a pending fingerprint, in order to improve the accuracy of the test, a second fingerprint anti-counterfeiting test process is further performed to determine whether the fingerprint to be tested is a fake based on the second test result obtained by the second fingerprint anti-counterfeiting test. Specifically, if the second result indicates that the fingerprint to be tested is a genuine fingerprint, the fingerprint to be tested is determined to be a genuine fingerprint. Conversely, if the second result indicates that the fingerprint to be tested is a fake, the fingerprint to be tested is determined to be a fake.

[0077] In some possible implementations, a first fingerprint anti-counterfeiting test may be performed on the device posture information to obtain a first test result. If the first test result indicates a true fingerprint or a pending fingerprint, a second fingerprint anti-counterfeiting test may be performed on the fingerprint signal to obtain a second test result, and the authenticity of the fingerprint to be tested may be determined based on the second test result.

[0078] In some possible implementations, the first detection result may be a probability value indicating that the fingerprint being tested is a fake fingerprint, or a probability value indicating that the fingerprint being tested is a genuine fingerprint. This embodiment uses the probability value indicating that the first detection result is a fake fingerprint as an example for illustration. Specifically, the probability value indicating that the fingerprint being tested is a fake fingerprint can be represented by a floating-point number between 0 and 1. Ideally, a probability value of 0 indicates that the fingerprint being tested is a genuine fingerprint, and a probability value of 1 indicates that the fingerprint being tested is a fake fingerprint. In other words, a larger probability value indicates a greater likelihood that the fingerprint being tested is a fake fingerprint, and conversely, a smaller probability value indicates a greater likelihood that the fingerprint being tested is a genuine fingerprint.

[0079] Continuing with the above-mentioned first and second application scenarios as examples, we will introduce how to determine the authenticity of the fingerprint to be tested in actual application scenarios. If the electronic device is in the first application scenario (a scenario with a higher security level), a first fingerprint anti-counterfeiting test is performed on the fingerprint signal to obtain a first test result, and a second fingerprint anti-counterfeiting test is performed on the device posture information to obtain a second test result. If the electronic device is in the second application scenario, a first fingerprint anti-counterfeiting test is performed on the fingerprint signal to obtain a first test result. Based on the first test result, it is determined whether to perform a second fingerprint anti-counterfeiting test on the device posture. If the first test result indicates a fake fingerprint, there is no need to perform the second fingerprint anti-counterfeiting test. In this way, for the first application scenario with a higher security level requirement, two detection mechanisms are adopted, performing both the first fingerprint anti-counterfeiting test corresponding to the fingerprint signal and the second fingerprint anti-counterfeiting test corresponding to the device posture information, thereby enhancing the accuracy of fingerprint anti-counterfeiting detection. For the second application scenario with a relatively low security level requirement, only the first fingerprint anti-counterfeiting test corresponding to the fingerprint signal can be used to improve fingerprint detection efficiency while ensuring basic security. At the same time, the accuracy of fingerprint anti-counterfeiting detection can be further enhanced through the above-mentioned first threshold and second threshold. For example, for the first type of application scenarios with a relatively high security level, the first threshold in the first fingerprint anti-counterfeiting function can be set to be greater than the first threshold in the second fingerprint anti-counterfeiting function. In this way, the probability values ​​corresponding to more fingerprints to be detected in the first fingerprint anti-counterfeiting detection process can be lower than the first threshold, and then the second fingerprint anti-counterfeiting detection process will be executed, effectively ensuring that both fingerprint detection processes are used, thereby improving the detection accuracy of the first type of application scenarios.

[0080] In some possible implementations, after obtaining the first detection result, the authenticity of the fingerprint to be tested can be determined by any one of the following methods:

[0081] (1) Pre-set a threshold value, compare the first detection result with the threshold value, and determine the authenticity of the fingerprint to be tested. Specifically: the first threshold value can be pre-set, for example, the first threshold value is set to 0.8, and the first detection result is compared with the first threshold value. If the probability value is less than the first threshold value, the first detection result is determined to be a true fingerprint. If the probability value is greater than the first threshold value, the first detection result is determined to be a false fingerprint. Or,

[0082] (2) Two thresholds are set, a first threshold and a second threshold, the first threshold being greater than the second threshold, and the first result is compared with the two thresholds respectively to determine the detection result. Specifically: if the probability value is less than the preset second threshold, the first detection result is determined to be a true fingerprint, and if the probability value is greater than or equal to the second threshold and less than or equal to the first threshold, the first detection result is determined to be a pending fingerprint; if the probability value is greater than the first threshold, the first detection result is determined to be a false fingerprint. For example, the first threshold can be set to 0.8 and the second threshold can be set to 0.4. If the probability value is 0.2, the first detection result is determined to be a true fingerprint, if the probability value is 0.6, the first detection result is determined to be a pending fingerprint, and if the probability value is 0.9, the first detection result is determined to be a false fingerprint.

[0083] In practice, the collected fingerprint signal can be an image of the fingerprint to be tested. For example, with an optical fingerprint module, when a user's finger presses a specific area of ​​the screen, the screen illuminates the finger. The light then reflects off the fingerprint and is received by the fingerprint sensor under the screen. The fingerprint sensor then outputs an image containing the fingerprint's features.

[0084] In this case, step S202 can extract actual feature parameters of the fingerprint based on the fingerprint image and determine the first detection result based on the actual feature parameters. The feature parameters can be extracted using a traditional feature extraction algorithm or a neural network model, which is not limited in this embodiment of the present invention.

[0085] The actual characteristic parameters include at least one of the following:

[0086] 1) Pixel value statistical parameters.

[0087] The pixel value statistical parameters may include but are not limited to statistical features such as the mean and variance of the fingerprint image.

[0088] 2) Texture parameters.

[0089] Texture parameters may include but are not limited to fingerprint texture minutiae, texture edge contrast, etc.

[0090] 3) Brightness parameter.

[0091] Brightness parameters may include but are not limited to brightness distribution, local brightness variation, etc.

[0092] In some embodiments, the above-mentioned device attitude information may include acceleration information and / or angular velocity information of the electronic device. The acceleration information and angular velocity information of the electronic device can be obtained by calling the software interface of the IMU of the electronic device. Specifically, the measurement values ​​of the three-axis gyroscope and the three-axis accelerometer in the IMU are read, and these measurement values ​​represent the attitude of the device. The acceleration information includes: the acceleration measured along the x-axis, the acceleration measured along the y-axis, and the acceleration measured along the z-axis; the angular velocity information includes: the rotation vector component along the x-axis, the rotation vector component along the y-axis, and the rotation vector component along the z-axis.

[0093] In some embodiments, based on the acceleration and / or angular velocity information obtained above, the above step S202 is performed, i.e., fingerprint anti-counterfeiting detection is performed according to the device posture information. The step of obtaining the detection result may include: performing fingerprint anti-counterfeiting detection according to the acceleration information and / or angular velocity information of the electronic device to obtain the detection result. Specifically, the second detection result can be determined based on the acceleration information and / or angular velocity information of the electronic device. In this process, the posture parameters corresponding to the fake fingerprint can be referred to. The obtained acceleration information and / or angular velocity information of the electronic device are similar to the posture parameters corresponding to the fake fingerprint to obtain the similarity, and the similarity is used as the detection result. Among them, the posture parameters corresponding to the pre-stored fake fingerprint can be a series of posture parameter thresholds set based on experience, or the posture parameters of the fake fingerprint calculated by an algorithm, or the posture parameters of the fake fingerprint obtained by training using a neural network model. The embodiment of the present invention does not limit this. Alternatively, the neural network model is pre-trained with sample data. After the model is trained, it is only necessary to input the above-mentioned acceleration and / or angular velocity information into the model to obtain the second detection result output by the model. The sample data includes positive sample data of acceleration information and / or angular velocity information corresponding to a real fingerprint, and negative sample data of acceleration information and / or angular velocity information corresponding to a fake fingerprint.

[0094] In some embodiments, obtaining the device posture information corresponding to the fingerprint to be measured can be determined by at least one of the following methods:

[0095] 1) When the electronic device first collects the fingerprint signal of the fingerprint to be tested, the device posture information corresponding to the moment of the first collection is obtained;

[0096] 2) acquiring, at a first sampling interval, device posture information corresponding to each moment from the start to the end of fingerprint signal acquisition of the fingerprint to be measured, to obtain a first device posture information sequence;

[0097] 3) At a second sampling interval, obtaining device posture information corresponding to each moment within a preset first time period after the start of fingerprint signal acquisition of the fingerprint to be tested, to obtain a second device posture information sequence;

[0098] 4) When the electronic device is in the device posture acquisition mode, the device posture information of the electronic device is acquired and stored at a third sampling interval, and part or all of the device posture information stored before the fingerprint signal acquisition of the fingerprint to be measured is retained to obtain a third device posture information sequence.

[0099] The above-mentioned device posture collection mode is the electronic device's on state, low power consumption state, or a state triggered by the user.

[0100] In specific applications, any one of the above methods can be used to sample the device posture, or a combination of the above methods can be used to collect the device posture. The device posture time series obtained by the above method can be in the form of a vector composed of the values ​​of a single component at different times, or a matrix composed of the values ​​of multiple components at different times. In an example, the device posture information is collected at three time points t1, t2 and t3, and the angular velocity information of the x-axis and z-axis is collected at each time point. The angular velocity of the x-axis at time t1 is represented by x1, and the angular velocity of the z-axis is represented by z1. The angular velocity of the x-axis at time t2 is represented by x2, and the angular velocity of the z-axis is represented by z2. The angular velocity of the x-axis at time t3 is represented by x3, and the angular velocity of the z-axis is represented by z3. Then the device posture information matrix of this example is expressed as:

[0101]

[0102] The device posture information at the three time points t1, t2 and t3 listed above only lists two posture information components (angular velocity components corresponding to the x-direction and z-direction respectively). In some embodiments, the posture information component in the y-direction can also be collected on this basis, which is not limited in this embodiment of the present invention.

[0103] In another example, the x-axis acceleration and the z-axis acceleration at time t are collected, and the device posture information matrix of this embodiment can be expressed as:

[0104]

[0105] In another example, the above two solutions can be combined, and the obtained device posture information matrix can be expressed as:

[0106]

[0107] The obtained device posture information may be pre-processed before the second anti-counterfeiting detection, such as smoothing filtering, normalization operation, etc., to reduce data noise and improve detection accuracy.

[0108] In some possible implementations, the anti-counterfeiting detection process for the fingerprint signal and device posture information can be implemented using a neural network model. For example, after obtaining the fingerprint signal and device posture information, the authenticity of the fingerprint to be tested can be determined by the following methods:

[0109] (1) Inputting the fingerprint signal into the first neural network model to perform a first fingerprint anti-counterfeiting detection to obtain a first detection result.

[0110] (2) Inputting the device posture information into the second neural network model to perform a second fingerprint anti-counterfeiting detection to obtain a second detection result.

[0111] (3) Determine the authenticity of the fingerprint to be tested based on the above test results (the test results include the above first test results and the above second test results).

[0112] In this embodiment, before performing fingerprint anti-counterfeiting detection, the first neural network model and the second neural network model are pre-trained. The training process of the network model can be performed in the electronic device or in other devices, and the trained models are stored in the electronic device.

[0113] In some embodiments, the first neural network model is trained using real fingerprint samples and forged fingerprint samples; the second neural network model is trained using real posture samples and forged posture samples. The training process of the first neural network model and the second neural network model is described in detail below:

[0114] The above-mentioned first neural network model is obtained by training with labeled sample data, and the sample data includes real fingerprint samples and forged samples, wherein the real fingerprint samples include real fingerprint signals and label data corresponding to the real fingerprint, and the label data corresponding to the real fingerprint is 0; the forged fingerprint samples include fake fingerprint signals and label data corresponding to the fake fingerprint, and the label data corresponding to the fake fingerprint is 1.

[0115] Before the training begins, the network structure and initial parameters of the first neural network model are determined. In this embodiment, the first neural network model can be a neural network model including a convolutional layer, such as a lightweight network model ShuffleNet model, MobileNet model, GhostNet model, etc. optimized for electronic devices, or a combination and deformation of the above models, or other types of neural network models, which are not limited in the present invention. The above sample data is input into the first neural network model, and the model parameters are iteratively trained according to the output results and the label data corresponding to the sample data. Specifically, the training can be performed according to the value of the loss function until the loss function is reduced to a stable state, the model converges, and the training of the first neural network model is completed. Furthermore, during the training process, the ADAM optimizer can be used to adjust the network model parameters to speed up the convergence speed.

[0116] The second neural network model is trained using labeled sample data. The sample data may include real pose samples and forged pose samples. The real pose samples include the device pose information and corresponding label data when collecting genuine fingerprints, with the label data corresponding to the real pose samples being 0. The forged pose samples include the device pose information and corresponding label data when collecting fake fingerprints, with the label data corresponding to the forged pose samples being 1.

[0117] Before training begins, the network structure and initial parameters of the second neural network model are determined. In this embodiment, the second neural network model can be a general convolutional neural network, or an LSTM (Long Short-Term Memory) neural network, or a ConvLSTM network model that combines a general convolutional neural network and LSTM. Furthermore, the above-mentioned sample data is input into the second neural network model, and the model parameters are iteratively trained based on the output results and the label data corresponding to the sample data. Specifically, the training can be performed according to the value of the loss function until the loss function is reduced to a stable state, the model converges, and the training of the second neural network model is completed.

[0118] To explain this embodiment more clearly, see Figure 4 The following is a schematic diagram of a fingerprint anti-counterfeiting detection method according to an embodiment of the present invention. Figure 4 Take the fingerprint anti-counterfeiting detection process as an example to explain in detail:

[0119] S401: The user inputs a fingerprint, and the electronic device obtains the user's fingerprint signal.

[0120] When the user presses the fingerprint recognition area in the electronic device, the screen touch component in the electronic device detects the touch signal and notifies the device's on-chip system through an interrupt to execute the fingerprint anti-counterfeiting detection process.

[0121] S402: Obtain device posture information corresponding to the moment when the user inputs the fingerprint.

[0122] Specifically, the device posture information can be obtained through the IMU of the electronic device. In this embodiment, taking the acquisition of instantaneous device posture information as an example, the device posture information at the moment when the user inputs the fingerprint is acquired.

[0123] S403: Extracting anti-counterfeiting features of the fingerprint signal, and obtaining a first probability value of a fake fingerprint (equivalent to the first detection result) according to the anti-counterfeiting features.

[0124] In this embodiment, the fingerprint signal is a fingerprint image obtained by a fingerprint sensor, and texture features in the fingerprint image are extracted as anti-counterfeiting features. Specifically, the extraction of anti-counterfeiting features from the image is achieved through a convolutional neural network. The extracted anti-counterfeiting features are compared with pre-stored anti-counterfeiting features of authentic fingerprints to obtain a first detection result.

[0125] S404: Determine whether the first probability value is greater than or equal to a preset threshold value A; if so, execute step S408; otherwise, execute step S405.

[0126] The above-mentioned first detection result includes the probability value of the fingerprint signal being a fake fingerprint. If the above-mentioned probability value is greater than or equal to the preset threshold value A (equivalent to the above-mentioned first threshold value), it means that it can be determined that the fingerprint to be detected is a fake fingerprint only through the fingerprint signal, and it is determined that the fingerprint input by the user is a fake fingerprint, and the fingerprint anti-counterfeiting detection is completed.

[0127] If the probability value is less than the preset threshold A, it means that the fingerprint input by the user may be a real fingerprint or a fake fingerprint, and further testing of the fingerprint input by the user is required to determine the authenticity of the fingerprint.

[0128] S405: Extracting anti-counterfeiting features from the device posture information, performing a second anti-counterfeiting test, and obtaining a second probability value of a fake fingerprint (equivalent to a second test result).

[0129] In this embodiment, the three-axis acceleration and three-axis angular velocity of the device at the time of fingerprint recognition by the user are extracted as anti-counterfeiting features through a neural network model, and compared with the three-axis acceleration and three-axis angular velocity within the normal range to obtain a second detection result.

[0130] S406: Determine whether the second probability value is greater than or equal to a preset threshold value B (equivalent to the above-mentioned second threshold value). If so, execute step S408; otherwise, execute step S407.

[0131] S407: Determine whether the fingerprint input by the user is a genuine fingerprint.

[0132] S408: Determine whether the fingerprint input by the user is a fake fingerprint.

[0133] The above-mentioned preset threshold value A and preset threshold value B may be the same or different.

[0134] Based on the above method embodiment, the present invention also provides a fingerprint anti-counterfeiting detection device, see Figure 5 As shown, the above device includes:

[0135] The acquisition module 501 is used to acquire device posture information corresponding to the fingerprint to be measured. The device posture information is used to represent the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be measured.

[0136] The detection module 502 is used to perform fingerprint anti-counterfeiting detection according to the device posture information and obtain a detection result.

[0137] The anti-counterfeiting determination module 503 is used to determine the authenticity of the fingerprint to be tested based on the detection result.

[0138] In the above device, by using the device posture information to perform anti-counterfeiting identification on the fingerprint, the detection capability of fake fingerprints is enhanced, the difficulty for attackers to use fake fingerprints to operate is increased, and the device security defense capability is effectively improved.

[0139] The detection module 502 in the above-mentioned device is further configured to perform fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information to obtain a detection result. For example, a first fingerprint anti-counterfeiting detection is performed on the fingerprint signal to obtain a first detection result; and a second fingerprint anti-counterfeiting detection is performed on the device posture information to obtain a second detection result. Accordingly, the anti-counterfeiting determination module 503 is further configured to determine the authenticity of the fingerprint to be tested based on the first and second detection results. For example, if the first and / or second detection results indicate a fake fingerprint, the fingerprint to be tested is determined to be a fake fingerprint.

[0140] The detection module 502 in the above-mentioned device is further configured to perform a first fingerprint anti-counterfeiting test on the fingerprint signal to obtain a first test result; if the first test result indicates a genuine fingerprint or the first test result indicates a pending fingerprint, perform a second fingerprint anti-counterfeiting test on the device posture information to obtain a second test result. Accordingly, the anti-counterfeiting determination module 503 is further configured to determine the authenticity of the pending fingerprint based on the second test result. For example, if the second test result indicates a fake fingerprint, the pending fingerprint is determined to be a fake fingerprint.

[0141] The first detection result in the above-mentioned device is a probability value that the fingerprint to be tested is a fake fingerprint. If the probability value is less than a preset first threshold, the first detection result is characterized as a true fingerprint; or; if the probability value is less than a preset second threshold, the first detection result is characterized as a true fingerprint, and if the probability value is greater than or equal to the second threshold and less than or equal to the first threshold, the first detection result is a pending fingerprint; wherein the first threshold is greater than the second threshold.

[0142] The electronic device in the above-mentioned device includes a first type of application scenario equipped with a first fingerprint anti-counterfeiting function and a second type of application scenario equipped with a second fingerprint anti-counterfeiting function; wherein, the security level of the first type of application scenario is higher than the security level of the second type of application scenario; if the electronic device is in the first type of application scenario, a fingerprint anti-counterfeiting detection is performed based on the fingerprint signal and the device posture information to obtain a detection result; if the electronic device is in the second type of application scenario, a fingerprint anti-counterfeiting detection is performed based on the fingerprint signal or the device posture information to obtain a detection result.

[0143] The fingerprint signal in the above device is a fingerprint image of the fingerprint to be tested; the detection module 502 is further used to: extract actual feature parameters of the fingerprint image; wherein the actual feature parameters include at least one of the following: pixel value statistical parameters, texture parameters and brightness parameters; determine the first detection result according to the actual feature parameters.

[0144] The device posture information in the above-mentioned apparatus includes acceleration information and / or angular velocity information of the electronic device; the above-mentioned detection module 502 is further used to: determine the second detection result based on the acceleration information and / or angular velocity information of the electronic device and the posture parameters corresponding to the pre-stored pseudo fingerprint.

[0145] Specifically, the device posture information corresponding to the fingerprint to be tested is obtained in at least one of the following ways: (1) when the electronic device first collects the fingerprint signal of the fingerprint to be tested, the device posture information corresponding to the moment of the first collection is obtained; (2) at a first sampling interval, the device posture information corresponding to each moment from the start to the end of the fingerprint signal collection of the fingerprint to be tested is obtained, and a first device posture information sequence is obtained; (3) at a second sampling interval, the device posture information corresponding to each moment within a preset first time period after the start of the fingerprint signal collection of the fingerprint to be tested is obtained, and a second device posture information sequence is obtained; (4) when the electronic device is in the device posture collection mode, the device posture information of the electronic device is obtained and stored at a third sampling interval, and part or all of the device posture information stored before the start of the fingerprint signal collection of the fingerprint to be tested is retained, and a third device posture information sequence is obtained.

[0146] The above-mentioned device posture collection mode is the electronic device's on state, low power consumption state, or a state triggered by the user.

[0147] The detection module 502 in the above device is also used to: input the fingerprint signal into the first neural network model to perform a first fingerprint anti-counterfeiting detection to obtain a first detection result; input the device posture information into the second neural network model to perform a second fingerprint anti-counterfeiting detection to obtain a second detection result.

[0148] The first neural network model in the above device is obtained by training using real fingerprint samples and forged fingerprint samples; the second neural network model is obtained by training using real posture samples and forged posture samples.

[0149] The fingerprint anti-counterfeiting detection device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the above-mentioned device, reference can be made to the corresponding content in the aforementioned fingerprint anti-counterfeiting detection method embodiment.

[0150] The embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, it is a structural diagram of the electronic device, wherein the electronic device includes a processor 601 and a memory 602, the memory 602 stores computer executable instructions that can be executed by the processor 601, and the processor 601 executes the computer executable instructions to implement the above-mentioned fingerprint anti-counterfeiting detection method.

[0151] exist Figure 6 In the illustrated embodiment, the electronic device further includes a bus 603 and a communication interface 604 , wherein the processor 601 , the communication interface 604 and the memory 602 are connected via the bus 603 .

[0152] Among them, the memory 602 may include high-speed random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 604 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 603 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 603 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0153] The processor 601 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or by instructions in the form of software. The above-mentioned processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a neural network processing unit (NPU), etc.; it can also be a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory, and the processor 601 reads the information in the memory and, in conjunction with its hardware, completes the steps of the fingerprint anti-counterfeiting detection method of the aforementioned embodiment.

[0154] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the above-mentioned fingerprint anti-counterfeiting detection method. The specific implementation can be found in the aforementioned method embodiment and will not be repeated here.

[0155] The computer program products of the fingerprint anti-counterfeiting detection method, device, and electronic device provided in the embodiments of the present invention include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. For specific implementation, please refer to the method embodiments and will not be repeated here.

[0156] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0157] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0158] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0159] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A fingerprint anti-counterfeiting detection method, characterized in that: The method is applied to an electronic device, the electronic device including a first type of application scenario configured with a first fingerprint anti-counterfeiting function and a second type of application scenario configured with a second fingerprint anti-counterfeiting function; wherein the security level of the first type of application scenario is higher than the security level of the second type of application scenario; the method comprises: Obtaining device posture information corresponding to the fingerprint to be measured, the device posture information being used to represent the posture state of the electronic device during the process of the electronic device collecting the fingerprint signal of the fingerprint to be measured; the device posture information includes acceleration information and / or angular velocity information of the electronic device; Performing fingerprint anti-counterfeiting detection according to the device posture information to obtain a detection result; Determining the authenticity of the fingerprint to be tested according to the detection result; The step of performing fingerprint anti-counterfeiting detection according to the device posture information and obtaining a detection result includes: if the electronic device is in the first type of application scenario, performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information to obtain a detection result; if the electronic device is in the second type of application scenario, performing fingerprint anti-counterfeiting detection according to the fingerprint signal or the device posture information to obtain a detection result.

2. The method according to claim 1, characterized in that The step of performing fingerprint anti-counterfeiting detection according to the device posture information and obtaining the detection result includes: A fingerprint anti-counterfeiting detection is performed according to the acceleration information and / or angular velocity information of the electronic device to obtain a detection result.

3. The method according to claim 1 or 2, characterized in that The step of obtaining device posture information corresponding to the fingerprint to be tested includes at least one of the following: When the electronic device first collects the fingerprint signal of the fingerprint to be tested, obtaining the device posture information corresponding to the moment of first collection; At a first sampling interval, acquiring device posture information corresponding to each moment from the start to the end of fingerprint signal acquisition of the fingerprint to be measured, to obtain a first device posture information sequence; At a second sampling interval, acquiring device posture information corresponding to each moment within a first time period after the start of fingerprint signal acquisition of the fingerprint to be measured, to obtain a second device posture information sequence; When the electronic device is in a device posture acquisition mode, device posture information of the electronic device is acquired and stored at a third sampling interval, and part or all of the device posture information stored before the fingerprint signal acquisition of the fingerprint to be measured begins is retained to obtain a third device posture information sequence.

4. The method according to claim 3, characterized in that The device posture acquisition mode is a powered-on state, a low-power state, or a state triggered and set by a user.

5. The method according to any one of claims 1 to 4, characterized in that The step of performing fingerprint anti-counterfeiting detection according to the device posture information and obtaining the detection result includes: Perform fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information to obtain a detection result.

6. The method according to claim 5, characterized in that The step of performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information to obtain a detection result includes: Performing a first fingerprint anti-counterfeiting test on the fingerprint signal to obtain a first test result; Performing a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result; The step of determining the authenticity of the fingerprint to be tested according to the detection result includes: The authenticity of the fingerprint to be tested is determined according to the first detection result and the second detection result.

7. The method according to claim 6, characterized in that The step of determining the authenticity of the fingerprint to be tested based on the first detection result and the second detection result includes: If the first detection result and / or the second detection result is characterized as a fake fingerprint, it is determined that the fingerprint to be detected is a fake fingerprint.

8. The method according to claim 5, characterized in that The step of performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information to obtain a detection result includes: Performing a first fingerprint anti-counterfeiting test on the fingerprint signal to obtain a first test result; If the first detection result indicates a genuine fingerprint or the first detection result indicates a pending fingerprint, performing a second fingerprint anti-counterfeiting detection on the device posture information to obtain a second detection result; The step of determining the authenticity of the fingerprint to be tested according to the detection result includes: The authenticity of the fingerprint to be tested is determined according to the second detection result.

9. The method according to claim 8, characterized in that The step of determining the authenticity of the fingerprint to be tested according to the second detection result includes: If the second detection result indicates a fake fingerprint, the fingerprint to be detected is determined to be a fake fingerprint.

10. The method according to any one of claims 6 to 9, characterized in that: The fingerprint signal is a fingerprint image of the fingerprint to be tested; The step of performing a first fingerprint anti-counterfeiting test on the fingerprint signal to obtain the first test result includes: Extracting actual feature parameters of the fingerprint image; wherein the actual feature parameters include at least one of the following: pixel value statistical parameters, texture parameters and brightness parameters; A first detection result is determined according to the actual characteristic parameter.

11. The method according to claim 5, characterized in that The step of performing fingerprint anti-counterfeiting detection according to the fingerprint signal and the device posture information includes: Inputting the fingerprint signal into a first neural network model to perform a first fingerprint anti-counterfeiting detection to obtain a first detection result; Inputting the device posture information into a second neural network model to perform a second fingerprint anti-counterfeiting detection to obtain a second detection result; Among them, the first neural network model is obtained by training using real fingerprint samples and forged fingerprint samples; the second neural network model is obtained by training using real posture samples and forged posture samples, the real posture samples are the posture states of the electronic device during the process of collecting fingerprint signals of real fingerprints, and the forged posture samples are the posture states of the electronic device during the process of collecting fingerprint signals of forged fingerprints.

12. The method according to any one of claims 6 to 11, characterized in that: The first detection result is a probability value that the fingerprint to be tested is a fake fingerprint; If the probability value is less than a preset first threshold, the first detection result is characterized as a true fingerprint; or; If the probability value is less than a preset second threshold, the first detection result is characterized as a true fingerprint; and if the probability value is greater than or equal to the second threshold and less than or equal to the first threshold, the first detection result is characterized as a pending fingerprint; The first threshold is greater than the second threshold.

13. A fingerprint anti-counterfeiting detection device, characterized in that: The device is applied to an electronic device, wherein the electronic device includes a first type of application scenario configured with a first fingerprint anti-counterfeiting function and a second type of application scenario configured with a second fingerprint anti-counterfeiting function; wherein the security level of the first type of application scenario is higher than the security level of the second type of application scenario; the device includes: an acquisition module, configured to acquire device posture information corresponding to the fingerprint to be tested, wherein the device posture information is used to represent the posture state of the electronic device during the process of the electronic device acquiring the fingerprint signal of the fingerprint to be tested; the device posture information includes acceleration information and / or angular velocity information of the electronic device; a detection module, configured to perform fingerprint anti-counterfeiting detection based on the device posture information and obtain a detection result; wherein performing fingerprint anti-counterfeiting detection based on the device posture information and obtaining a detection result comprises: if the electronic device is in the first type of application scenario, performing fingerprint anti-counterfeiting detection based on the fingerprint signal and the device posture information and obtaining a detection result; if the electronic device is in the second type of application scenario, performing fingerprint anti-counterfeiting detection based on the fingerprint signal or the device posture information and obtaining a detection result; The anti-counterfeiting determination module is used to determine the authenticity of the fingerprint to be tested based on the detection result.

14. An electronic device, characterized in that: The electronic device includes: an acquisition device, a processing device and a storage device; The acquisition device is used to collect the fingerprint signal and device posture information of the fingerprint to be tested; The storage device stores a computer program, which, when executed by the processing device, executes the fingerprint anti-counterfeiting detection method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the fingerprint anti-counterfeiting detection method according to any one of claims 1 to 12 are executed.

Images