Fingerprint identification method, terminal device and storage medium

Abstract

The present disclosure relates to a fingerprint recognition method, terminal device and storage medium. The method includes: when the terminal device is unlocked by fingerprint, radar waves are emitted and returned radar waves are received through the radar sensor of the terminal device; radar wave characteristics are obtained according to the emitted radar waves and the received returned radar waves; when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, the fingerprint sensor of the terminal device is awakened; fingerprints are collected based on the awakened fingerprint sensor, and the collected fingerprints are identified and unlocked. By detecting live fingers, the embodiments of the present disclosure can effectively reduce the false touch unlocking caused by non-finger prosthesis triggering, thereby improving the accuracy of finger fingerprint unlocking.

Description

Technical Field

[0001] The present disclosure relates to the field of information identification technology, and in particular to a fingerprint identification method, a terminal device and a storage medium. Background Art

[0002] With the development of terminal devices and user needs, fingerprint sensors have become an essential module for existing terminal devices. In terminal devices, fingerprint on display (FOD) recognition is becoming more and more popular as a way to unlock terminal devices. Existing screen fingerprint recognition usually determines whether to unlock by analyzing a two-dimensional image. However, there is a problem of poor accuracy in image recognition unlocking when determining whether to unlock by a two-dimensional image. Summary of the invention

[0003] The present disclosure provides a fingerprint recognition method, a terminal device and a storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, a pattern recognition method is provided, comprising:

[0005] transmitting radar waves through a radar sensor of the terminal device and receiving returned radar waves;

[0006] Acquire radar wave characteristics according to the transmitted radar wave and the received returned radar wave;

[0007] When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked.

[0008] In some embodiments, when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked, including:

[0009] When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, waking up the fingerprint sensor of the terminal device;

[0010] The fingerprint sensor is awakened to collect fingerprints, and the collected fingerprints are identified and unlocked.

[0011] In some embodiments, determining that a live finger is detected in the radar emission area of ​​the radar sensor according to the radar wave characteristics includes:

[0012] Inputting the radar wave feature into a living finger recognition model to obtain a matching degree corresponding to the living finger recognition model;

[0013] When the matching degree is greater than a matching threshold, it is determined that the radar transmission area of ​​the radar sensor detects the living finger.

[0014] In some embodiments, the method further comprises:

[0015] Acquiring normal feature samples in a normal finger recognition scenario through the radar sensor;

[0016] Acquiring abnormal feature samples in an abnormal finger recognition scene through the radar sensor;

[0017] The normal feature samples and the abnormal feature samples are input into a classification training model to obtain the live finger recognition model through training; wherein the matching result of the live finger recognition model for matching the normal feature samples is greater than the matching result of the live finger recognition model for matching the abnormal feature samples.

[0018] In some embodiments, the method further comprises:

[0019] When the terminal device records the fingerprint template, the radar template features are acquired through the radar sensor;

[0020] The radar template feature is input into the living finger recognition model to obtain an updated living finger recognition model.

[0021] In some embodiments, the method further comprises:

[0022] Detecting whether the terminal device is in a held state;

[0023] When the terminal device is not in the held state, and / or the collected fingerprint does not match the fingerprint template, the terminal device is refused to be unlocked.

[0024] In some embodiments, acquiring radar wave characteristics according to the transmitted radar wave and the received returned radar wave includes:

[0025] Performing time-frequency processing on the radar wave and the returned radar wave to obtain radar wave characteristics;

[0026] The radar wave characteristics include: shape characteristics of the detected object in the radar transmission area determined based on the returned radar wave, and / or posture change characteristics within a preset time period.

[0027] In some embodiments, the method further comprises:

[0028] Determining whether the detected object is in the shape of a finger according to the shape feature;

[0029] According to the posture change characteristics, it is determined whether the detected object is a living body.

[0030] In some embodiments, the method further comprises:

[0031] When no live finger is detected, the fingerprint sensor is controlled to be in a dormant state.

[0032] In some embodiments, the method further comprises:

[0033] While emitting the radar wave, collecting fingerprints through the fingerprint sensor;

[0034] When no live finger is detected, the fingerprint collected by the fingerprint sensor is discarded.

[0035] According to a second aspect of an embodiment of the present disclosure, a terminal device is provided, the terminal device comprising:

[0036] Screen;

[0037] A fingerprint sensor is located below the screen and faces the screen;

[0038] A radar sensor is arranged at a different position from the fingerprint sensor below the screen, and transmits radar waves to the screen and receives returned radar waves;

[0039] The processor is connected to the radar sensor and the fingerprint sensor respectively, and is used to obtain radar wave characteristics according to the emitted radar waves and the received returned radar waves; when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, the fingerprint sensor is controlled to collect fingerprints, and the collected fingerprints are identified and unlocked.

[0040] In some embodiments, the radar sensor includes:

[0041] at least one transmitter for transmitting the radar wave, disposed adjacent to the fingerprint sensor;

[0042] At least one receiver for receiving the returned radar wave is disposed separately from the transmitter.

[0043] In some embodiments, at least one of the transmitters includes: two transmitters, the two transmitters are disposed on opposite sides of the fingerprint sensor;

[0044] The at least one receiver includes: four receivers, and the four receivers are symmetrically arranged around the fingerprint sensor with the fingerprint sensor as the center.

[0045] In some embodiments, at least one of the receivers is located at an edge location of the terminal device.

[0046] According to a third aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the fingerprint recognition method provided in the second aspect above.

[0047] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0048] The disclosed embodiment first obtains the radar wave characteristics through the returned radar wave received by the radar sensor, and then determines whether a live finger is detected through the radar wave characteristics, and then collects the fingerprint based on the fingerprint sensor when it is determined that a live finger is detected. That is to say, before the fingerprint sensor collects the fingerprint, the disclosed embodiment will first determine whether a live finger is detected in the radar emission area, rather than collecting fingerprints for any detection object. In this way, by detecting live fingers, the false touch unlocking caused by non-finger prosthesis triggering can be effectively reduced, thereby improving the accuracy of finger fingerprint unlocking. In addition, the fingerprint sensor is awakened only when a live finger is detected, which can reduce the increase in system power consumption caused by false touches to wake up the fingerprint collection module, so that the power consumption of the terminal device is effectively saved while realizing the fingerprint unlocking function, thereby extending the use time of the terminal device.

[0049] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0051] Figure 1 This is a schematic diagram of a fingerprint recognition method process shown in an embodiment of the present disclosure. Figure 1 .

[0052] Figure 2 This is a schematic diagram of a fingerprint recognition method process shown in an embodiment of the present disclosure. Figure 2 .

[0053] Figure 3 This is a schematic diagram of a fingerprint recognition method process shown in an embodiment of the present disclosure. Figure 3 .

[0054] Figure 4 It is a schematic diagram of an ultrasonic recognition process shown in an embodiment of the present disclosure.

[0055] Figure 5 This is a schematic diagram of the structure of a terminal device shown in an embodiment of the present disclosure. Figure 1.

[0056] Figure 6 This is a schematic diagram of the structure of a terminal device shown in an embodiment of the present disclosure. Figure 2 .

[0057] Figure 7 It is a structural block diagram of a terminal device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0058] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0059] Figure 1 This is a fingerprint recognition method process shown in the embodiment of the present disclosure Figure 1 ,like Figure 1 As shown, the method applied to the terminal device includes the following steps:

[0060] S101, transmitting radar waves through a radar sensor of a terminal device and receiving returned radar waves;

[0061] S102, acquiring radar wave characteristics according to the transmitted radar wave and the received returned radar wave;

[0062] S103: When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked.

[0063] The terminal device is a terminal device provided with a fingerprint sensor and a radar sensor. The terminal device transmits radar waves through the radar sensor and receives the returned radar waves, including: the terminal device transmits radar waves to the detection object in the fingerprint recognition area through the radar sensor, and receives the radar waves reflected back by the detection object.

[0064] It should be noted that the above-mentioned fingerprint recognition area is an area where the detection object can be recognized by the fingerprint sensor. The position of the fingerprint recognition area can be set according to the orientation of the acquisition surface of the fingerprint sensor. For example, when the acquisition surface of the fingerprint sensor faces the screen, the fingerprint recognition area can be set on the screen; when the acquisition surface of the fingerprint sensor faces the back shell, the fingerprint recognition area can be set on the screen. The above-mentioned detection object includes a finger, and the finger includes a thumb, a middle finger, or a ring finger, which is not limited in the embodiments of the present disclosure.

[0065] In the disclosed embodiment, after receiving the reflected radar wave, the terminal device obtains the radar wave characteristics based on the transmitted radar wave and the received returned radar wave.

[0066] The above-mentioned radar wave characteristics include but are not limited to radar wave coverage area characteristics, distance characteristics, speed characteristics and angle characteristics.

[0067] The above-mentioned distance characteristics can be determined according to the transmission time of the radar wave, the reception time of the returned radar wave and the propagation speed of the radar wave; the above-mentioned speed characteristics can be determined according to the difference between the transmission frequency of the radar wave and the reception frequency of the returned radar wave; the above-mentioned angle characteristics can be determined according to the phase change of the returned radar wave; the above-mentioned radar wave coverage area characteristics can be determined according to the setting position of the radar wave and the transmission and reception range of the radar wave.

[0068] In the disclosed embodiment, the change in the posture of the detection object within a preset time period can be determined through the distance feature, speed feature, and angle feature. The shape feature and shape change feature of the radar wave can be determined through the angle feature and the coverage area feature of the radar wave. In this way, the features estimated by the radar wave features can characterize whether the detection object is in a stationary state or whether the shape of the detection object conforms to the shape of a finger, and then it can be determined whether the detection object is a live finger based on the radar wave features.

[0069] It should be noted that the above-mentioned posture change of the detection object includes: the relative movement distance of the detection object, the relative movement speed of the detection object and the movement direction of the detection object, which is not limited in the present disclosure.

[0070] In some embodiments, radar wave characteristics are obtained based on the transmitted radar waves and the received returned radar waves, including: performing time-frequency processing on the radar waves and the returned radar waves to obtain radar wave characteristics, wherein the radar wave characteristics include: shape characteristics of the detected object in the radar transmission area determined based on the returned radar waves, and / or posture change characteristics within a preset time period.

[0071] The fingerprint recognition area is within the radar transmission area, and the area of ​​the radar transmission area is larger than the fingerprint recognition area. In this way, the radar sensor can better transmit radar waves to the detection object located in the fingerprint recognition area.

[0072] The above-mentioned time-frequency processing includes time domain processing and frequency domain processing. After time-frequency processing, the range Doppler spectrum, range spectrum, Doppler spectrum and angle spectrum can be obtained. The radar wave characteristics of the detection object in the preset time period can be determined by the range Doppler spectrum, range spectrum, Doppler spectrum and angle spectrum.

[0073] The above-mentioned preset time period may include the time corresponding to the fixed frame length, and the fixed frame length may be set according to actual conditions. For example, the fixed frame length may be set to 8 frames or 10 frames, which is not limited in the embodiments of the present disclosure.

[0074] In the disclosed embodiment, it is possible to determine whether the detected object is a live finger based on the shape feature and / or posture change feature of the detected object. In some embodiments, it is determined whether the detected object is a finger shape based on the shape feature; and it is determined whether the detected object is a live object based on the posture change feature.

[0075] In this way, the shape features and posture change features can be used to determine whether the detection object is a living finger, and then the detection object can be identified before fingerprint collection. This can effectively reduce the false touch unlocking caused by non-finger prosthesis triggering, and improve the accuracy of finger fingerprint unlocking.

[0076] Wherein, determining whether the detected object is in the shape of a finger according to the shape feature includes: determining the shape of the detected object according to the shape feature; and determining that the detected object is in the shape of a finger when the shape of the detected object matches a preset shape. The finger shape includes a thumb shape, a middle finger shape, or a ring finger shape, which is not limited in the embodiments of the present disclosure.

[0077] According to the above-mentioned posture change characteristics of the detection object, the posture change of the detection object can be determined, and then the detected posture change can be used to determine whether the detection object is a living body. The posture change of the detection object includes but is not limited to the displacement change of the detection object, the speed change of the detection object, or the angle change of the detection object. For example, when the displacement change and the speed change within the preset time period are detected to be within the preset threshold range, it is characterized that the movement of the detection object is coherent, and then it can be determined that the detection object is a living body rather than a prosthesis.

[0078] In the disclosed embodiment, whether the detected object is a living body or a prosthesis can be directly determined by detecting whether the object has posture changes. For example, if there is a posture change, it is a living body, and if there is no posture change, it is a prosthesis.

[0079] Furthermore, the terminal device may also determine that the detection object is a living body when the posture change of the detection object meets a preset condition.

[0080] It should be noted that the preset condition includes a preset range of movable angles. A living finger has a range of movable angles. When the movable angle of the detected object is not within the range of movable angles, it can be determined that the detected object is a prosthesis.

[0081] For example, the range of angles at which a living finger can move may be between 0 and 180 degrees. When the moving angle of the detection object is 270 degrees, the detection object is determined to be a prosthesis, and when the moving angle of the detection object is 90 degrees, the detection object is determined to be a living body.

[0082] In the disclosed embodiment, the living finger has a movable joint, and the angle between the two parts connecting the movable joint can change relative to each other. For example, when the living finger rotates 90 degrees, the angle between the two parts of the movable joint can change from 180 degrees to 90 degrees, while the relative angle of a prosthetic finger such as a plastic finger will not change when it rotates 90 degrees. Therefore, the preset condition may also include whether a relative angle change occurs. When the two parts of the detection object change relative to each other, it is determined that the detection object is a living object. When the two parts of the detection object do not change relative to each other, it is determined that the detection object is a prosthesis.

[0083] In this way, the prosthesis can be further effectively excluded by detecting the activity angle of the object and the relative angle change of the object, thereby improving the accuracy of living body detection.

[0084] In the embodiment of the present disclosure, the above-mentioned radar wave characteristics may include, in addition to the shape characteristics and posture change characteristics of the detection object, also a contact area characteristic of the detection object, which is not limited in the embodiment of the present disclosure.

[0085] In some embodiments, the terminal device may also determine whether the detected object is a finger based on the contact area characteristics, or determine whether the detected object is a finger based on the shape characteristics and the contact area characteristics, which is not limited in the embodiments of the present disclosure.

[0086] In some embodiments, Figure 2 As shown, when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked, that is, step S103 includes:

[0087] S103a, when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, waking up the fingerprint sensor of the terminal device;

[0088] S103b, collecting fingerprints based on the awakened fingerprint sensor, and identifying and unlocking the collected fingerprints.

[0089] In the disclosed embodiment, in order to reduce the power consumption of the fingerprint sensor, the fingerprint sensor is in a dormant state during the fingerprint unlocking process of the terminal device. When a live finger is detected, the fingerprint sensor of the terminal device needs to be awakened first. In this way, the increase in system power consumption caused by the invalid operation of the fingerprint collection module due to the false touch of the prosthesis other than the finger can be reduced, so that the power consumption of the terminal device can be effectively saved while realizing the fingerprint unlocking function, thereby extending the use time of the terminal device.

[0090] In some embodiments, the terminal device further includes: when no live finger is detected, controlling the fingerprint sensor to be in a sleep state.

[0091] It should be noted that when no live finger is detected, it indicates that the terminal device is accidentally touched, for example, the terminal device is placed in a pocket, or the fingerprint recognition area of ​​the screen is accidentally touched by a non-finger while holding the terminal device. At this time, the fingerprint sensor does not need to perform fingerprint recognition, and the terminal device does not need to wake up the fingerprint sensor in the dormant state.

[0092] In this way, the embodiment of the present disclosure can reduce the increase in power consumption caused by waking up the terminal device due to accidental touches of the terminal device by controlling the fingerprint sensor to be in a sleep state when no live finger is detected, thereby saving the power consumption of the terminal device and extending the usage time of the terminal device.

[0093] In an embodiment of the present disclosure, when no live finger is detected, controlling the fingerprint sensor to be in a dormant state includes:

[0094] When no live finger is detected, the fingerprint sensor in dormant state is not awakened;

[0095] When no live finger is detected, the fingerprint sensor is controlled to exit the awake state and enter the sleep state.

[0096] That is to say, the embodiment of the present disclosure can determine the working state of the fingerprint sensor in advance. When the working state of the fingerprint sensor is the sleep state and no living body is detected, the fingerprint sensor is not awakened, so that the fingerprint sensor continues to remain in sleep; when the working state of the fingerprint sensor is the awake state and no living body is detected, the fingerprint sensor is controlled to switch from the awake state to the sleep state. In this way, when a live finger is detected, the embodiment of the present disclosure can flexibly control the fingerprint sensor to enter the sleep state from different states, which can reduce the power consumption of the terminal device and extend the use time of the terminal device.

[0097] In the disclosed embodiment, after waking up the fingerprint sensor of the terminal device, the fingerprint is collected based on the awakened fingerprint sensor, and the collected fingerprint is identified and unlocked. The process of collecting fingerprints by the fingerprint sensor may include: emitting light to the detection object and receiving the returned reflected light, forming a fingerprint image based on the reflected light, and then realizing fingerprint identification and unlocking.

[0098] Among them, the fingerprint sensor can unlock by identifying the fingerprint in the identification area on the terminal device screen, and can also unlock by identifying the fingerprint in the identification area on the back shell of the terminal device, which is not limited in the embodiments of the present disclosure.

[0099] In the disclosed embodiment, the unlocking process of the terminal device is as follows: when the collected fingerprint matches the fingerprint template entered by the terminal device, the locked state of the terminal device is unlocked; when the collected fingerprint does not match the fingerprint template entered by the terminal device, the terminal device continues to process the locked state. In this way, the fingerprint unlocking of the terminal device can be achieved by comparing the collected fingerprint with the fingerprint module.

[0100] It should be noted that the embodiment of the present disclosure first obtains the radar wave characteristics through the returned radar wave received by the radar sensor, and then determines whether a live finger is detected through the radar wave characteristics, and then wakes up the fingerprint sensor to collect fingerprints when it is determined that a live finger is detected. That is to say, before the fingerprint sensor collects the fingerprint, the embodiment of the present disclosure will first determine whether a live finger is detected in the radar emission area, rather than collecting fingerprints for any detection object. In this way, by detecting live fingers, the false touch unlocking caused by non-finger prosthesis triggering can be effectively reduced, thereby improving the accuracy of finger fingerprint unlocking. In addition, the fingerprint sensor is only awakened when a live finger is detected, which can reduce the increase in system power consumption caused by false touches to wake up the fingerprint collection module, so that the power consumption of the terminal device is effectively saved while realizing the fingerprint unlocking function, thereby extending the use time of the terminal device.

[0101] In some embodiments, determining that a live finger is detected in a radar emission area of ​​a radar sensor according to radar wave characteristics includes:

[0102] Inputting the radar wave characteristics into the live finger recognition model, and obtaining the matching degree corresponding to the live finger recognition model;

[0103] When the matching degree is greater than the matching threshold, it is determined that a live finger is detected in the radar emission area of ​​the radar sensor.

[0104] In the disclosed embodiment, the terminal device pre-stores a live finger recognition model. After acquiring the radar wave characteristics, the terminal device can perform matching based on the live finger recognition model to determine whether a live finger is detected.

[0105] It should be noted that the live finger recognition model can be composed of multiple sub-models corresponding to different fingers, and the multiple sub-models can detect whether the radar wave characteristics of different detection objects are live fingers. For example, the fingers include: middle finger and ring finger; the sub-model corresponding to the middle finger can detect that the detection object is a live middle finger; the sub-model corresponding to the ring finger can detect that the detection object is a live ring finger.

[0106] In the embodiment of the present disclosure, there may be multiple radar sensors, and multiple groups of radar wave features may be obtained through the multiple radar sensors, and then the multiple groups of radar wave features are input into the live finger recognition model to obtain multiple groups of matching degrees of the multiple groups of radar wave features. After obtaining the multiple groups of matching degrees, the embodiment of the present disclosure may perform normalization processing on the multiple groups of matching degrees of the multiple groups of radar wave features, and then determine that the detected object is a live finger when the normalized matching result is greater than the matching threshold.

[0107] It should be noted that the normalization process is to convert the multiple matching degrees of the multiple groups of radar wave features into decimals between 0 and 1. The multiple matching degrees of the multiple groups of radar wave features are normalized, including: obtaining the highest matching degree and the lowest matching degree among the multiple groups of radar wave features, and determining the normalized matching results of the multiple groups of radar wave features based on the highest matching degree and the lowest matching degree.

[0108] In this way, determining whether the detection object is a live finger by the matching result obtained through normalization processing can effectively reduce the situation where the detection error of different radar sensors leads to inaccurate detection results, and improve the accuracy of detecting live fingers.

[0109] Exemplarily, the above-mentioned matching threshold can be set according to the actual detection accuracy requirement of the live finger. For example, the matching threshold can be set to 0.65 or 0.75, etc., which is not limited in the embodiment of the present disclosure.

[0110] In some embodiments, the method further comprises:

[0111] Acquire normal feature samples in a normal finger recognition scenario through a radar sensor;

[0112] Acquire abnormal feature samples in abnormal finger recognition scenarios through radar sensors;

[0113] The normal feature samples and the abnormal feature samples are input into the classification training model to obtain the live finger recognition model through training; wherein the matching result of the live finger recognition model for matching the normal feature samples is greater than the matching result of the live finger recognition model for matching the abnormal feature samples.

[0114] In the disclosed embodiment, the finger recognition model is a model obtained by training with feature samples in a finger recognition scene and a classification training model.

[0115] The above-mentioned normal feature samples are samples obtained by the radar sensor in the fingerprint unlocking scenario of a live finger. The abnormal feature samples are samples other than normal feature samples. Among them, the abnormal feature samples can be samples obtained by the radar sensor in multiple abnormal scenarios. The abnormal scenarios include recognition scenarios of non-fingerprint recognition areas, recognition scenarios of prosthetic fingers, recognition scenarios of non-fingerprints, or recognition scenarios of multiple fingers, which are not limited in the embodiments of the present disclosure.

[0116] It should be noted that the terminal device has a fingerprint recognition area, and the non-fingerprint recognition area is an area of ​​the terminal device other than the fingerprint recognition area. For example, the non-fingerprint recognition area may include an area where a camera decoration is located or an area where a housing on the side of the terminal device is located.

[0117] The above-mentioned recognition scenario of the non-fingerprint recognition area can be a scenario where the detection object acts on the non-fingerprint recognition area to perform fingerprint unlocking. When the detection object acts on the non-fingerprint recognition area, the fingerprint sensor cannot collect the fingerprint of the detection object, and thus cannot realize fingerprint recognition and unlocking. Therefore, the recognition scenario of the non-fingerprint recognition area can be used as an abnormal finger recognition scenario in fingerprint unlocking.

[0118] The recognition scenario of the above-mentioned prosthetic finger may be a scenario of fingerprint unlocking by using the prosthetic finger in the fingerprint recognition area, and the colloid finger may be a finger made of plastic or silicone material.

[0119] The above-mentioned non-finger recognition scenario can be a recognition scenario in which the user uses a part other than a finger as a detection object. The part other than a finger includes: an elbow, a finger joint or a stylus, which is not limited in the embodiment of the present disclosure.

[0120] The above-mentioned multiple finger recognition scenario can be a recognition scenario where multiple fingers act on the fingerprint recognition area at the same time. For example, multiple fingers act on the fingerprint recognition area at the same time, including: two fingers act on the fingerprint recognition area at the same time; or three fingers act on the finger recognition area at the same time, which is not limited in the embodiments of the present disclosure.

[0121] In the disclosed embodiment, both the normal feature samples and the abnormal feature samples are multiple samples, and the normal feature samples and the abnormal feature samples can be samples extracted by artificially simulating different scenes. In this way, the normal feature samples and the abnormal feature samples can accurately reflect the recognition process in the real scene, and then the live finger recognition model trained by the normal feature samples and the abnormal feature samples can obtain an accurate matching degree, so that the live fingerprint determined based on the matching degree is more accurate.

[0122] Exemplarily, the classification training model includes a model formed by a convolutional neural network (CNN), which is not limited in the embodiments of the present disclosure.

[0123] In some embodiments, the method further comprises:

[0124] When the fingerprint template is entered into the terminal device, the radar template features are obtained through the radar sensor;

[0125] The radar template features are input into the living finger recognition model to obtain an updated living finger recognition model.

[0126] In the disclosed embodiment, when the terminal device enters the fingerprint template, the fingerprint sensor collects the fingerprint of the detection object and stores the detected historical fingerprint as the fingerprint template in the terminal device. After determining that the detection object is a live finger, the terminal device matches the current fingerprint collected by the fingerprint sensor with the fingerprint template, thereby realizing the identification and unlocking of the terminal device. Among them, the fingerprint module is a complete finger fingerprint, and the terminal device can be unlocked through the fingerprint module.

[0127] The terminal device has pre-stored a live finger recognition model. When the terminal device uses a template fingerprint, the live recognition model can be updated through the radar template features obtained by the radar sensor.

[0128] It should be noted that the scenario where the terminal device enters the template fingerprint belongs to the normal finger recognition scenario. Therefore, the radar template feature belongs to the normal feature sample. Inputting the radar template feature into the live finger recognition model can retrain the live finger recognition model to obtain a more accurate live finger recognition model.

[0129] In some embodiments, the method further comprises:

[0130] Detect whether the terminal device is in a held state;

[0131] When the terminal device is not in a held state, and / or the collected fingerprint does not match the fingerprint template, the terminal device is refused to be unlocked.

[0132] In the disclosed embodiment, the pressure sensor and temperature sensor of the terminal device can be used to detect whether the terminal device is in a held state. For example, when the pressure value detected by the pressure sensor is greater than a pressure threshold and / or the temperature detected by the temperature sensor is greater than a temperature threshold, it is determined that the terminal device is in a held state.

[0133] It should be noted that if the terminal device is not in a held state, it can indicate that the unlocking behavior is a non-user behavior or an accidental touch behavior, and if the collected fingerprint does not match the fingerprint template, it can indicate that the unlocking behavior is not a user behavior authenticated by the terminal device. Therefore, by refusing to unlock when the terminal device is not in a held state and / or the collected fingerprint does not match the fingerprint template, the accuracy of unlocking the terminal device can be improved.

[0134] In some embodiments, the method further comprises:

[0135] While emitting the radar wave, collecting fingerprints through the fingerprint sensor;

[0136] When no live finger is detected, the fingerprint collected by the fingerprint sensor is discarded.

[0137] That is to say, when no live finger is detected, the embodiment of the present disclosure directly discards the fingerprint collected by the fingerprint sensor instead of continuing to process the fingerprint, which can effectively reduce the power consumption required to process the fingerprint, thereby saving the power consumption of the terminal device and extending the usage time of the terminal device.

[0138] In the disclosed embodiment, when the radar sensor and the fingerprint sensor are both in working state, the terminal device will be unlocked only when the acquisition result of the fingerprint sensor and the detection result of the radar sensor meet the requirements. Before the detection result of the radar sensor is confirmed, the terminal device will not be unlocked even if the acquisition result of the fingerprint sensor meets the requirements.

[0139] In order to better understand the embodiments of the present disclosure, Figure 3 As shown, a fingerprint recognition method proposed in an embodiment of the present disclosure includes the following steps:

[0140] S201, transmitting radar waves through a radar sensor of a terminal device and receiving returned radar waves;

[0141] S202, acquiring radar wave characteristics according to the transmitted radar wave and the received returned radar wave;

[0142] S203, determining whether a live finger is detected in the radar transmission area according to the radar wave characteristics; if so, go to step S204; if not, go to step S201;

[0143] S204, waking up the fingerprint sensor, and collecting fingerprints based on the awakened fingerprint sensor;

[0144] S205, determine whether the collected fingerprint matches the preset fingerprint; if so, go to step S206; if not, go to step S207;

[0145] S206, authentication is passed, unlocking the terminal device;

[0146] S207: Unlocking is rejected, and the terminal device remains in a locked state.

[0147] It should be noted that before waking up the fingerprint sensor, an ultrasonic sensor can also be used to identify the prosthesis. The ultrasonic sensor can use the changes in the reflection of ultrasonic waves by different detection objects to determine the material of the detection object, thereby realizing the recognition of the prosthesis. Figure 4 As shown, the steps of identifying the prosthesis include: step S301, obtaining ultrasonic features based on the ultrasonic sensor; step S302, determining whether the ultrasonic features match the ultrasonic template features; if they match, go to step S303; if they do not match, go to step S301; step S303, detecting that the object is a prosthesis. It can be seen from the steps of ultrasonic prosthesis identification that the ultrasonic sensor can only identify the prosthesis, but cannot identify whether the detection object is a finger, which leads to the problem of misoperation caused by the identification and unlocking of non-finger objects, and the power consumption of the terminal device increases due to the identification and unlocking of non-finger objects.

[0148] Based on this, the embodiment of the present disclosure first obtains the radar wave characteristics through the returned radar wave received by the radar sensor, and then determines whether a live finger is detected through the radar wave characteristics, and then wakes up the fingerprint sensor to collect fingerprints when it is determined that a live finger is detected. That is to say, before the fingerprint sensor collects the fingerprint, the embodiment of the present disclosure will first determine whether a live finger is detected in the radar emission area, rather than collecting fingerprints for any detection object. In this way, by detecting live fingers, the false touch unlocking caused by the triggering of the prosthesis that is not touched by the finger can be effectively reduced, thereby improving the accuracy of finger fingerprint unlocking. In addition, the fingerprint sensor is only awakened when a live finger is detected, which can reduce the increase in system power consumption caused by the false touch awakening the fingerprint collection module, so that the power consumption of the terminal device is effectively saved while realizing the fingerprint unlocking function, thereby extending the use time of the terminal device.

[0149] The present disclosure also provides a terminal device, such as Figure 5 As shown, the terminal device includes:

[0150] Screen 401;

[0151] A fingerprint sensor 402 is located below the screen and faces the screen;

[0152] The radar sensor 403 is arranged at a different position from the fingerprint sensor below the screen, and transmits radar waves to the screen and receives returned radar waves;

[0153] The processor 404 is connected to the radar sensor and the fingerprint sensor respectively, and is used to obtain radar wave characteristics based on the transmitted radar waves and the received returned radar waves; and when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, the fingerprint sensor is controlled to collect the fingerprint, and the collected fingerprint is identified and unlocked.

[0154] The above-mentioned terminal device can be a wearable electronic device and a mobile terminal. The mobile terminal includes a mobile phone, a notebook and a tablet computer, and the wearable electronic device includes a smart watch, which is not limited in the embodiments of the present disclosure.

[0155] The above-mentioned screen may be a screen formed by a liquid crystal display (Liquid Crystal Display, LCD), or may be a screen formed by an organic light emitting semiconductor (Organic Electroluminesence Display, OLED), and the embodiments of the present disclosure are not limited thereto.

[0156] In the disclosed embodiment, the terminal device has a fingerprint recognition area, which can be set on the screen, and the corresponding fingerprint sensor collection surface faces the screen, so that fingerprint recognition can be achieved by collecting the detection object on the fingerprint recognition area on the screen.

[0157] The fingerprint collection area can also be set on the back shell of the terminal device, with the corresponding fingerprint sensor collection surface facing the back shell, so that fingerprint recognition can be achieved through the detection object on the fingerprint collection area on the back shell.

[0158] In the embodiment of the present disclosure, the direction of the collection surface of the radar sensor is the same as the direction of the collection surface of the fingerprint sensor. The radar sensor can be one or more, and the embodiment of the present disclosure is not limited.

[0159] Exemplarily, the radar sensor includes but is not limited to a millimeter wave radar sensor. The millimeter wave radar sensor may use an extremely high frequency millimeter wave of 60 GHz and a wavelength of 5 mm to transmit radar waves to improve detection accuracy.

[0160] It should be noted that the terminal device first obtains the radar wave characteristics through the returned radar wave received by the radar sensor, and then determines whether a live finger is detected through the radar wave characteristics, and then wakes up the fingerprint sensor to collect fingerprints when it is determined that a live finger is detected. That is to say, before the fingerprint sensor collects the fingerprint, the embodiment of the present disclosure will first determine whether a live finger is detected in the radar emission area, rather than collecting fingerprints for any detection object. In this way, by detecting live fingers, the false touch unlocking caused by non-finger triggering or prosthesis triggering can be effectively reduced, thereby improving the accuracy of finger fingerprint unlocking. In addition, the fingerprint sensor is only awakened when a live finger is detected, which can reduce the increase in system power consumption caused by waking up the fingerprint collection module due to false touches, so that the power consumption of the terminal device is effectively saved while realizing the fingerprint unlocking function, thereby extending the use time of the terminal device.

[0161] In some embodiments, the radar sensor includes:

[0162] at least one transmitter for emitting radar waves, disposed adjacent to the fingerprint sensor;

[0163] At least one receiver for receiving the returning radar waves is disposed separately from the transmitter.

[0164] In the disclosed embodiment, the number of transmitters may be less than or equal to the number of receivers, and this public course embodiment does not limit this.

[0165] It should be noted that the terminal device is provided with multiple transmitters to obtain multiple groups of returned radar waves and corresponding multiple groups of radar wave features, and then through the multiple groups of radar wave features, it is possible to more accurately determine whether the detected object is a live finger. In addition, the embodiment of the present disclosure is provided with multiple receivers to improve the acceptance rate of receiving multiple groups of returned radar waves, and then through the radar wave features corresponding to the groups of returned radar waves, it is also possible to more accurately determine whether the detected object is a live finger.

[0166] In some embodiments, Figure 6 As shown, the at least one transmitter includes: two transmitters 403a, the two transmitters 403a are arranged on opposite sides of the fingerprint sensor 402;

[0167] The at least one receiver 403 b includes four receivers 403 b , and the four receivers 403 b are symmetrically arranged around the fingerprint sensor 402 with the fingerprint sensor 402 as the center.

[0168] In the disclosed embodiment, the transmitter is arranged at the opposite position of the fingerprint sensor, so that the transmitter can emit radar waves in different directions of the detection object, and the corresponding radar wave characteristics can be more comprehensively obtained. The four receivers are arranged symmetrically around the fingerprint sensor with the fingerprint sensor as the center, so that the radar waves returned by the detection object can be received by the receivers, thereby improving the reception rate of the returned radar waves.

[0169] In some embodiments, Figure 6 As shown, at least one receiver 403b is located at an edge position of the terminal device.

[0170] In the disclosed embodiment, arranging the receiver at the edge of the terminal device can enable the receiver to better receive the returned radar waves.

[0171] Regarding the terminal device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the above embodiment of the method, and will not be elaborated here.

[0172] Figure 7 1 is a block diagram of a terminal device according to an exemplary embodiment. For example, the terminal device may be a mobile phone, a mobile computer, etc.

[0173] Reference Figure 7 The terminal device may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0174] The processing component 802 generally controls the overall operation of the terminal device, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0175] The memory 804 is configured to store various types of data to support the operation of the device. Examples of such data include instructions for any application or method operating on the terminal device, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0176] The power component 806 provides power to various components of the terminal device. The power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal device.

[0177] The multimedia component 808 includes a screen that provides an output interface between the terminal device and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0178] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the terminal device is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0179] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0180] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the terminal device. For example, the sensor assembly 814 can detect the open / closed state of the device, the relative positioning of the components, such as the display and keypad of the terminal device, and the sensor assembly 814 can also detect the position change of the terminal device or a component of the terminal device, the presence or absence of user contact with the terminal device, the orientation or acceleration / deceleration of the terminal device and the temperature change of the terminal device. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

[0181] The communication component 816 is configured to facilitate wired or wireless communication between the terminal device and other devices. The terminal device can access a wireless network based on a communication standard, such as Wi-Fi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0182] In an exemplary embodiment, the terminal device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0183] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of a terminal device to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0184] A non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a terminal device, enables the terminal device to perform a fingerprint recognition method, the method comprising:

[0185] When the fingerprint unlocks the terminal device, a radar wave is emitted through the radar sensor of the terminal device and a returned radar wave is received;

[0186] Acquire radar wave characteristics according to the transmitted radar wave and the received returned radar wave;

[0187] When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, waking up the fingerprint sensor of the terminal device;

[0188] The fingerprint sensor is awakened to collect fingerprints, and the collected fingerprints are identified and unlocked.

[0189] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0190] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A fingerprint recognition method, characterized in that: Applied to a terminal device, the method comprises: transmitting radar waves through a radar sensor of the terminal device and receiving returned radar waves; Acquire radar wave characteristics according to the transmitted radar wave and the received returned radar wave; When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked; The acquiring radar wave characteristics according to the transmitted radar wave and the received returned radar wave comprises: Performing time-frequency processing on the radar wave and the returned radar wave to obtain radar wave characteristics; The radar wave characteristics include: shape characteristics of the detected object in the radar transmission area and posture change characteristics within a preset time period determined based on the returned radar wave; The method further comprises: Determining whether the detected object is in the shape of a finger according to the shape feature; Determining whether the detected object is a living body according to the posture change characteristics; The posture change feature includes at least one of a relative moving distance of the detection object, a relative moving speed of the detection object, and a moving direction of the detection object.

2. The method according to claim 1, characterized in that When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, a fingerprint is collected based on the fingerprint sensor of the terminal device, and the collected fingerprint is identified and unlocked, including: When it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, waking up the fingerprint sensor of the terminal device; The fingerprint sensor is awakened to collect fingerprints, and the collected fingerprints are identified and unlocked.

3. The method according to claim 1, characterized in that: The step of determining, according to the radar wave feature, that a live finger is detected in the radar emission area of ​​the radar sensor comprises: Inputting the radar wave feature into a live finger recognition model to obtain a matching degree corresponding to the live finger recognition model; When the matching degree is greater than a matching threshold, it is determined that the radar transmission area of ​​the radar sensor detects the living finger.

4. The method according to claim 3, characterized in that The method further comprises: Acquiring normal feature samples in a normal finger recognition scenario through the radar sensor; Acquiring abnormal feature samples in an abnormal finger recognition scene through the radar sensor; The normal feature samples and the abnormal feature samples are input into a classification training model to obtain the live finger recognition model through training; wherein the matching result of the live finger recognition model for matching the normal feature samples is greater than the matching result of the live finger recognition model for matching the abnormal feature samples.

5. The method according to claim 3, characterized in that: The method further comprises: When the terminal device enters a fingerprint template, the radar template features are acquired through the radar sensor; The radar template feature is input into the living finger recognition model to obtain an updated living finger recognition model.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Detecting whether the terminal device is in a held state; When the terminal device is not in the held state, and / or the collected fingerprint does not match the fingerprint template, the terminal device is refused to be unlocked.

7. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: When no live finger is detected, the fingerprint sensor is controlled to be in a dormant state.

8. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: While emitting the radar wave, collecting fingerprints through the fingerprint sensor; When no live finger is detected, the fingerprint collected by the fingerprint sensor is discarded.

9. A terminal device, characterized in that: The terminal device is used to execute the fingerprint recognition method provided in any one of claims 1 to 8, comprising: Screen; A fingerprint sensor is located below the screen and faces the screen; A radar sensor is arranged at a different position from the fingerprint sensor below the screen, and transmits radar waves to the screen and receives returned radar waves; The processor is connected to the radar sensor and the fingerprint sensor respectively, and is used to obtain radar wave characteristics according to the emitted radar waves and the received returned radar waves; and when it is determined according to the radar wave characteristics that a live finger is detected in the radar emission area of ​​the radar sensor, the fingerprint sensor is controlled to collect fingerprints, and the collected fingerprints are identified and unlocked.

10. The terminal device according to claim 9, characterized in that: The radar sensor comprises: at least one transmitter for transmitting the radar wave, disposed adjacent to the fingerprint sensor; At least one receiver for receiving the returned radar wave is disposed separately from the transmitter.

11. The terminal device according to claim 10, characterized in that: The at least one transmitter comprises: two transmitters, the two transmitters are arranged on opposite sides of the fingerprint sensor; The at least one receiver includes: four receivers, and the four receivers are symmetrically arranged around the fingerprint sensor with the fingerprint sensor as the center.

12. The terminal device according to claim 10, characterized in that: At least one of the receivers is located at an edge position of the terminal device.

13. A non-transitory computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the fingerprint recognition method provided in any one of claims 1 to 8.

Images