Fingerprint unlocking method and device, and terminal equipment

Abstract

The present disclosure provides a fingerprint unlocking method and device and a terminal device, wherein the method is applied to a terminal device, and the method comprises: in response to detecting a fingerprint unlocking instruction, acquiring target environment data of an environment in which the terminal device is located; determining a target exposure time of an optical sensor when collecting a fingerprint image according to the target environment data; controlling the optical sensor to continuously expose for the target exposure time to acquire the fingerprint image; and unlocking the terminal device according to the fingerprint image. The method can dynamically adjust the exposure time according to the environment data to improve the unlocking speed or the unlocking success rate.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a fingerprint unlocking method and device and a terminal device. BACKGROUND

[0002] At present, more and more terminal devices use fingerprint unlocking mode for unlocking. For example, mobile phones, door locks, computers and the like can use fingerprint unlocking mode for unlocking.

[0003] In the process of fingerprint unlocking of the terminal device, the fingerprint image of the user needs to be collected for identification. Since the quality of the collected fingerprint image is affected by environmental factors in actual application, the success rate of fingerprint unlocking is low, and the speed of fingerprint unlocking is slow. SUMMARY

[0004] Therefore, the present disclosure provides a fingerprint unlocking method and device and a terminal device, which can effectively improve the speed of fingerprint unlocking while ensuring the success rate of fingerprint unlocking.

[0005] According to a first aspect of an embodiment of the present disclosure, a fingerprint unlocking method is provided, the method being applied to a terminal device, and the method comprising:

[0006] In response to detecting a fingerprint unlocking instruction, target environment data of an environment in which the terminal device is located is acquired;

[0007] According to the target environment data, a target exposure time length of an optical sensor when collecting a fingerprint image is determined;

[0008] The optical sensor is controlled to continuously expose for the target exposure time length to acquire the fingerprint image;

[0009] According to the fingerprint image, the terminal device is unlocked.

[0010] According to any one of the embodiments provided by the present disclosure, the target exposure time length of the optical sensor when collecting the fingerprint image is determined according to the target environment data, comprising:

[0011] The target environment data is input into a pre-trained target neural network to acquire a target unlocking result output by the target neural network, the target unlocking result containing a target fingerprint unlocking success rate;

[0012] According to a corresponding relationship between different fingerprint unlocking success rates and different exposure time lengths, an exposure time length corresponding to the target fingerprint unlocking success rate is determined as the target exposure time length.

[0013] According to any one of the embodiments provided by the present disclosure, in the corresponding relationship, the unlocking success rate is negatively correlated with the exposure time length.

[0014] In combination with any of the embodiments provided in the present disclosure, the target neural network is trained in the following manner:

[0015] obtain sample environment data and sample fingerprint unlocking information of the sample fingerprint image in the sample environment;

[0016] input the sample environment data into an initial neural network to obtain candidate fingerprint unlocking information output by the initial neural network;

[0017] determine a loss function based on a difference between the candidate fingerprint unlocking information and the sample fingerprint unlocking information;

[0018] train the initial neural network according to the loss function until the loss function meets a preset stop training condition, to obtain the target neural network.

[0019] In combination with any of the embodiments provided in the present disclosure, the sample fingerprint unlocking information includes at least one of the following:

[0020] whether the sample fingerprint unlocking is successful;

[0021] an image quality parameter of the sample fingerprint image;

[0022] a matching degree parameter between the sample fingerprint image and a pre-determined standard fingerprint image.

[0023] In combination with any of the embodiments provided in the present disclosure, after determining the target exposure time length of the optical sensor when collecting the fingerprint image according to the target environment data, the method further includes:

[0024] determining whether the target exposure time length belongs to an abnormal exposure time length;

[0025] when it is determined that the target exposure time length belongs to an abnormal exposure time length, determining a preset exposure time length as the target exposure time length.

[0026] In combination with any of the embodiments provided in the present disclosure, the determination of whether the target exposure time length belongs to an abnormal exposure time length includes:

[0027] determining whether the target exposure time length exceeds a preset time length threshold.

[0028] According to a second aspect of the embodiments of the present disclosure, a fingerprint unlocking device is provided, which is applied to a terminal device, and the device includes:

[0029] a data acquisition module, configured to: in response to detecting a fingerprint unlocking instruction, acquire target environment data of an environment in which the terminal device is located;

[0030] a time length determination module, configured to determine a target exposure time length of the optical sensor when collecting a fingerprint image according to the target environment data;

[0031] a fingerprint collection module, configured to control the optical sensor to continuously expose for the target exposure time length to obtain the fingerprint image;

[0032] an identification and unlocking module, configured to unlock the terminal device according to the fingerprint image.

[0033] According to a third aspect of the embodiments of the present disclosure, a non-transitory computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the steps of the method of any one of the first aspect.

[0034] According to a fourth aspect of the embodiments of the present disclosure, a fingerprint unlocking device is provided, comprising:

[0035] a processor;

[0036] a memory for storing processor-executable instructions;

[0037] The processor is configured to implement the steps of the method of any one of the first aspect when executed by the processor.

[0038] The technical solutions provided by the embodiments of the present disclosure can include the following beneficial effects:

[0039] In the present solution, the target exposure time of the optical sensor when unlocking the fingerprint can be dynamically adjusted based on the analysis of the target environment data of the environment where the terminal device is located, so that when the environment factor leads to poor fingerprint collection effect, the exposure time is prolonged to make the fingerprint image collected by the optical sensor have higher quality to increase the success rate of fingerprint unlocking, and when the environment factor leads to good fingerprint collection effect, the exposure time is reduced to speed up the fingerprint unlocking speed.

[0040] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0042] Figure 1 is a fingerprint unlocking method flowchart according to an exemplary embodiment of the present disclosure;

[0043] Figure 2 is a fingerprint unlocking solution according to an exemplary embodiment of the present disclosure;

[0044] Figure 3 is a block diagram of a fingerprint unlocking device according to an example embodiment of the present disclosure;

[0045] Figure 4 is a structural schematic diagram of a terminal device according to an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The example embodiments will be described in detail herein with reference to the accompanying drawings. In the following description, unless otherwise indicated, like numbers in the different drawings represent the same or similar elements. The following example embodiments described in the following description are not meant to represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0047] The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in the present disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0048] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used only to distinguish different sets of information from one another. For example, a first information can be termed a second information, and similarly, a second information can also be termed a first information, without departing from the scope of the present disclosure. As used herein, the word "if' can be interpreted to mean "when" or "upon" or "in response to determining" depending on the context.

[0049] At present, the fingerprint unlocking technology applied in the market is mostly to improve the quality of the collected fingerprint image by standardizing the user's pressing method when pressing the fingerprint, so as to maintain a high fingerprint unlocking rate, and to improve the fingerprint unlocking speed by optimizing the fingerprint template matching strategy, without considering the influence of environmental factors such as weather and climate on fingerprint collection. For the sensor used to collect the fingerprint, especially the optical sensor, the adaptability to environmental factors such as temperature and humidity is poor, and it is easily affected by environmental factors, so that the fingerprint recognition success rate is not high, and the fingerprint unlocking speed is slow.

[0050] Based on this, the present disclosure provides a fingerprint unlocking method, which can fully utilize the environmental information around the fingerprint unlocking, adjust the exposure time of the optical sensor for collecting the fingerprint image, and further optimize the fingerprint unlocking performance and improve the user experience.

[0051] As Figure 1 shown, Figure 1 is a flowchart of a fingerprint unlocking method according to at least one embodiment of the present disclosure, which can be used in a terminal device to be unlocked by fingerprint, and includes the following steps:

[0052] In step 102, in response to detecting a fingerprint unlocking instruction, target environment data of an environment in which the terminal device is located is acquired.

[0053] The terminal device refers to an electronic device with a fingerprint unlocking function, and has an optical fingerprint module for collecting a fingerprint image. For example, the terminal device can be a mobile phone, a notebook computer, a tablet computer, a smart door lock, etc.

[0054] The present embodiment does not limit the way in which the fingerprint unlocking instruction is detected. For example, the fingerprint unlocking instruction can be triggered by touching the touch screen of the terminal device with a finger, and the terminal device detects the fingerprint unlocking instruction when it senses the touch of the finger. The fingerprint unlocking instruction can also be triggered by a button on the terminal device, and the terminal device detects the fingerprint unlocking instruction when it detects the button press.

[0055] The target environment data of the environment in which the terminal device is located is data related to temperature and humidity. Temperature and humidity can affect the quality of the fingerprint image collected by the optical fingerprint module. For example, the environment data at least includes one of the following: local temperature; environmental humidity; latitude and longitude; indoor temperature; indoor humidity; core temperature of the terminal device.

[0056] The environment data can be collected by the sensors of the terminal device itself, or by the sensors of other devices. For example, for a mobile phone, the temperature sensor built-in the mobile phone can collect the core temperature of the mobile phone, and the GPS module of the mobile phone can collect the latitude and longitude. For example, a plurality of thermohygrometers can be installed near the terminal device, and the thermohygrometers can synchronize the collected temperature and humidity to the terminal device. When the terminal device is located indoors and there is an indoor thermohygrometer, the data of the closest thermohygrometer can be acquired. For example, temperature and humidity sensors can be built-in the terminal device to collect the temperature and humidity of the environment.

[0057] In step 104, according to the target environment data, a target exposure time of the optical sensor when collecting the fingerprint image is determined.

[0058] The optical sensor refers to a photosensitive element in the optical fingerprint module for collecting a fingerprint image, and is used for collecting a fingerprint through an optical fingerprint collection technology. For example, the optical sensor can be a CCD (Charge-coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor) sensor, which can generate a corresponding charge signal according to light irradiated on the surface thereof.

[0059] The optical sensor is generally arranged below the touch screen. For example, when a finger is pressed on the screen of a mobile phone, the screen area below the finger emits strong light to illuminate the entire surface of the finger. The light is reflected by the finger and then enters the screen again, and is imaged on the CCD or CMOS sensor below the screen through the lens below the screen. The photosensitive elements collect the fingerprint image and compare it with the recorded fingerprint in the storage to achieve the effect of identity authentication.

[0060] The exposure time length refers to the photosensitive time length of the optical sensor after the light source or the screen in the optical fingerprint module emits light. The longer the exposure time, the more detailed the fingerprint in the collected fingerprint image, the higher the image quality, and the higher the success rate of fingerprint image unlocking.

[0061] For the optical fingerprint module, the temperature and humidity of the working environment have certain requirements. If the temperature or humidity is too high or too low, it will affect the quality of the collected fingerprint image within a fixed exposure time. Therefore, when the temperature or humidity is not suitable for the fingerprint collection effect, the image quality can be improved by prolonging the exposure time to improve the success rate of fingerprint unlocking. When the temperature and humidity are suitable for the working of the optical fingerprint module, the collected fingerprint image within a short time is sufficient for unlocking, and the fingerprint unlocking speed can be accelerated by reducing the exposure time.

[0062] In this step, the target exposure time length of the optical sensor when collecting a fingerprint image is determined according to the target environment data. The mapping relationship between the environment data and the exposure time length can be pre-set, so that the target exposure time length is determined according to the target environment data.

[0063] In one embodiment, in order to fully utilize the target environment data and improve the effect of dynamically adjusting the target exposure time length, a deep learning neural network technology can be used in this step. The target exposure time length of the optical sensor when collecting a fingerprint image is determined according to the target environment data, including:

[0064] The target environment data is input into a pre-trained target neural network, and a target unlocking result output by the target neural network is obtained. The target unlocking result includes a target fingerprint unlocking success rate.

[0065] According to the correspondence between different fingerprint unlocking success rates and different exposure durations, the exposure duration corresponding to the target fingerprint unlocking success rate is determined as the target exposure duration.

[0066] The target neural network can be a convolutional neural network, such as Faster RCNN (Faster Region-based Convolutional Neural Network), Fast RCNN (Fast Region-based Convolutional Neural Network), R-CNN (Region-based Convolutional Neural Network). The specific neural network and training method used by the target neural network are not limited in the embodiment.

[0067] The target unlocking result is the current unlocking result predicted by the target neural network according to the target environment data, which includes the target fingerprint unlocking success rate. For example, the target neural network outputs the confidence degree of the current fingerprint unlocking result belonging to the successful unlocking. The confidence degree is positively correlated with the target fingerprint unlocking success rate. The higher the confidence degree, the higher the target fingerprint unlocking success rate. The lower the confidence degree, the lower the target fingerprint unlocking success rate.

[0068] The target unlocking result can also include the predicted image quality parameter of the current collected fingerprint image, and the predicted matching degree parameter between the current collected fingerprint image and the pre-determined standard fingerprint image. The meanings of the above parameters in the target unlocking result are the same. The higher the target fingerprint unlocking success rate, the greater the possibility of the current collected fingerprint image being a high-quality image, and the higher the matching degree parameter between the current collected fingerprint image and the pre-determined standard fingerprint image.

[0069] According to different fingerprint unlocking success rates, the exposure duration can be adjusted. The correspondence between the two can be set by those skilled in the art according to actual needs, which is not limited in the embodiment. For example, the binary correspondence can be a functional relationship or a one-to-one correspondence, so that a unique target exposure duration can be determined according to the target fingerprint unlocking success rate.

[0070] In an embodiment, in the correspondence, the unlocking success rate is negatively correlated with the exposure time. For example, when the fingerprint unlocking success rate is low, the image quality can be improved by prolonging the exposure time to improve the fingerprint unlocking success rate; when the fingerprint unlocking success rate is high, the fingerprint image collected in a short time is sufficient for unlocking, and the fingerprint unlocking speed can be accelerated by reducing the exposure time. For another example, the exposure time of the three divided A, B, and C positions can be divided, wherein the exposure position A has the longest time, the exposure position B has the shortest time, if the fingerprint unlocking success rate in the current scene is poor, lower than the preset minimum threshold, the exposure position A is used to increase the exposure time to ensure that the fingerprint image acquisition can obtain enough features; if the fingerprint unlocking success rate in the current scene is high, higher than the preset maximum threshold, the exposure position B is used to reduce the exposure time to increase the unlocking speed as much as possible; of course, if the fingerprint unlocking success rate in the current scene is at a general level, not higher than the maximum threshold and not lower than the minimum threshold, the exposure position C is used, that is, the standard exposure time is fixed.

[0071] In an embodiment, the target neural network is trained in the following manner:

[0072] Obtain sample environment data and sample fingerprint unlocking information of a sample fingerprint image in a sample environment;

[0073] Input the sample environment data into an initial neural network to obtain candidate fingerprint unlocking information output by the initial neural network;

[0074] Determine a loss function based on the difference between the candidate fingerprint unlocking information and the sample fingerprint unlocking information;

[0075] Train the initial neural network according to the loss function until the loss function meets a preset stop training condition, to obtain the target neural network.

[0076] A large amount of training sample data is collected in advance: in a certain scene, before unlocking each time using a terminal device, the local temperature, humidity, latitude and longitude, and other weather information, and the sensor data of the terminal device at that time, and in the case of the existence of indoor hygrometer, the data of the nearest hygrometer are obtained; after unlocking, the above sample environment data and sample fingerprint unlocking information of the fingerprint unlocking, such as the result of whether the fingerprint unlocking is successful or not, the image quality, the matching score, and other data, are saved to the local. In this way, after collecting a large amount of data in different scenes and in multiple sample environments, the training of the convolutional neural network can be prepared, and the initial neural network is adjusted to a model corresponding to the environment data and the unlocking result through training.

[0077] According to the collected training sample data, relevant training parameters are set, and convolutional neural network training is performed. Specifically, the sample environment data can be input into the initial neural network, the initial neural network is used to extract features from the sample environment data, and candidate fingerprint unlocking information is predicted based on the extracted features. The candidate fingerprint unlocking information can include the confidence of sample fingerprint unlocking success, or can also be the confidence of sample fingerprint unlocking failure. The confidence range is between 0 and 1. The actual sample fingerprint unlocking information is unlocking success or unlocking failure, which can be represented by 0 and 1 respectively. Based on the difference between the confidence and the actual sample fingerprint unlocking information, the network loss can be calculated through the loss function.

[0078] The loss function is used to determine the difference between the actual output and the expected output. The present embodiment does not limit the specific use of the loss function. For example, quantile loss function, mean square error loss function or cross-entropy loss function can be used.

[0079] In a specific implementation, the network parameters in the initial neural network can be adjusted through back propagation according to the loss function. When the preset stopping training condition is reached, the network training is ended, wherein the stopping training condition can be that the iteration reaches a certain number of times, or the network loss is less than a certain threshold. A large amount of data is required for training, and then a relatively reliable target neural network is obtained.

[0080] In the above training process, the local temperature, environmental humidity, latitude and longitude and other weather information before unlocking, and the sensor data of the phone at that time, such as core temperature, are collected. If an indoor temperature and humidity meter exists, the data of the nearest temperature and humidity meter is also collected as the input sample environment data. The unlocking result data under this scene data is collected as a label to establish a convolutional neural network model corresponding to the environmental data and the unlocking result.

[0081] In one embodiment, the sample fingerprint unlocking information includes at least one of the following:

[0082] Whether the sample fingerprint unlocking is successful;

[0083] An image quality parameter of the sample fingerprint image;

[0084] A matching degree parameter between the sample fingerprint image and a predetermined standard fingerprint image.

[0085] The sample fingerprint unlocking success or failure can be sample fingerprint unlocking success or sample fingerprint unlocking failure; the image quality parameter of the sample fingerprint image is used to evaluate the quality of the sample fingerprint image collected by the optical fingerprint module in the terminal device, and can be related to the definition and completeness of the fingerprint image; and the matching degree parameter between the sample fingerprint image and the pre-determined standard fingerprint image is used to represent the similarity of the sample fingerprint image and the pre-recorded standard fingerprint image of the same user.

[0086] It should be noted that when the sample fingerprint unlocking information contains more than two of the above options, the multiple options are used as multi-label category labels for the corresponding sample environment data, and the alternative fingerprint unlocking information contains corresponding multiple output values. For example, when the sample fingerprint unlocking information contains whether the sample fingerprint unlocking is successful and the image quality parameter of the sample fingerprint image, the alternative fingerprint unlocking information contains the sample fingerprint unlocking success rate and the predicted value of the image quality parameter of the sample fingerprint image. When determining the network loss, the loss function can be calculated according to the difference between the sample fingerprint unlocking success and the sample fingerprint unlocking success rate, and the difference between the image quality parameter of the sample fingerprint image and the predicted value of the image quality parameter, to obtain the network loss. Training the target neural network using the training samples labeled with multi-labels can improve the robustness and accuracy of the target neural network.

[0087] In step 106, the optical sensor is controlled to continuously expose for the target exposure duration to obtain the fingerprint image.

[0088] The optical sensor in the terminal device is controlled to continuously expose for the target exposure duration, and of course, the light source in the terminal device also needs to be turned on for the target exposure duration, so that the optical sensor can continuously perceive the imaging of the light emitted by the light source after being reflected by the finger within the target exposure duration, and then collect the fingerprint image of the user.

[0089] The longer the exposure duration, the more fingerprint features the optical sensor can obtain, the richer the collected fingerprint details, and the better the quality of the fingerprint image.

[0090] In step 108, the terminal device is unlocked according to the fingerprint image.

[0091] The fingerprint image is identified and analyzed, and when it is determined that the fingerprint image is consistent with the pre-stored standard fingerprint image in the fingerprint database, for example, the similarity reaches a preset similarity threshold, the terminal device is unlocked, which can be unlocking the screen, the door lock, etc.

[0092] In one embodiment, on the basis of the above embodiment, after the target exposure duration of the optical sensor when collecting the fingerprint image is determined according to the target environment data, the method further comprises:

[0093] determine whether the target exposure duration is an abnormal exposure duration;

[0094] when it is determined that the target exposure duration is an abnormal exposure duration, determine a preset exposure duration as the target exposure duration.

[0095] In the embodiment, the target exposure duration is additionally subjected to an abnormal value edge judgment to determine whether the target exposure duration is an abnormal exposure duration. If the target exposure duration is an abnormal exposure duration, a preset exposure duration is used as a new target exposure duration, and the preset exposure duration is a standard exposure duration to avoid the influence of abnormal values on user experience.

[0096] In one example, the determination of whether the target exposure duration is an abnormal exposure duration includes:

[0097] determine whether the target exposure duration exceeds a preset duration threshold.

[0098] The preset duration threshold can include an upper limit of a maximum duration threshold or a lower limit of a minimum duration threshold, and can also include both thresholds. When the target exposure duration exceeds the lower limit or the upper limit, it is determined that the target exposure duration is an abnormal exposure duration.

[0099] For example, when a sensor for measuring environmental data fails, causing some environmental data to be missing or abnormal, and further causing the target exposure duration determined based on the target environmental data to be much higher or much lower than a general value, or causing the target exposure duration used for multiple unlocking operations to be a certain value and no longer dynamically adjusted following changes in environmental factors, or causing the user to fail to unlock at a given target exposure duration one or more times, the embodiment introduces an abnormal value edge judgment to avoid the occurrence of the above abnormal situations.

[0100] For example, when it is determined that the target exposure duration is not an abnormal exposure duration, the target exposure duration determined based on the target environmental data is used for this unlocking operation (retry0, which refers to the first attempt of the same user to unlock). If the unlocking operation fails, the target exposure duration is determined to be an abnormal exposure duration in the next unlocking operation (retry1), and a preset exposure duration is determined as a new target exposure duration.

[0101] For the foregoing method embodiments, in order to simply describe, they are all expressed as a combination of a series of actions, but those skilled in the art should know that the disclosure is not limited by the order of the described actions, because according to the disclosure, certain steps can be performed in other orders or simultaneously.

[0102] Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the disclosure.

[0103] An example is a mobile phone. The complete fingerprint unlocking solution of the present disclosure is shown in Figure 2 .

[0104] First, the data collection phase, in a large number of different unlocking scenarios, unlock, at each time of unlocking, collect local temperature, humidity, latitude and longitude, etc. Weather information before unlocking, and the sensor data of the phone at that time, such as the core temperature, to get the data set for training, and to establish an unlocking scene recognition library to store different unlocking scenes. And multi-label category labeling is performed on the data set, for example, for an environment data containing temperature and humidity, according to the unlocking result, it is labeled as: unlocking success, high image quality, and matching degree 98%.

[0105] Then the training phase, according to the multi-label category labeled training set, the deep convolutional neural network is trained, and the deep convolutional neural network model corresponding to the environment data and the unlocking result is obtained.

[0106] Finally, the application phase, the real-time environment data is collected before the user actually unlocks the scene, and the trained deep convolutional neural network model is input, and the unlocking result is predicted, and the corresponding exposure time is output as the exposure time scheme of this unlocking according to the unlocking result; Further determine whether the exposure time belongs to a trusted space, if it belongs to, the exposure time is not an abnormal exposure time, and the final exposure time scheme of this unlocking is output, and the optical sensor is controlled to expose according to the exposure time when collecting the fingerprint; If not, the exposure time is an abnormal exposure time, and the exposure time scheme is discarded, and the optical sensor is controlled to expose according to the original exposure time when collecting the fingerprint.

[0107] Corresponding to the foregoing application function implementation method embodiment, the present disclosure also provides an application function implementation device and a corresponding terminal embodiment.

[0108] Referring to Figure 3 A block diagram of a fingerprint unlocking device according to an example embodiment is shown, the device is applied to a terminal device, and the device can include:

[0109] The data acquisition module 31 is configured to: in response to detecting a fingerprint unlocking instruction, acquire target environment data of an environment in which the terminal device is located;

[0110] The time determination module 32 is configured to: determine a target exposure time of an optical sensor when collecting a fingerprint image according to the target environment data;

[0111] The fingerprint acquisition module 33 is configured to: control the optical sensor to continuously expose for the target exposure time to acquire the fingerprint image;

[0112] The recognition unlocking module 34 is configured to unlock the terminal device according to the fingerprint image.

[0113] In some embodiments, the time length determination module 32 is specifically configured to:

[0114] inputting the target environment data into a pre-trained target neural network to obtain a target unlocking result output by the target neural network, the target unlocking result including a target fingerprint unlocking success rate;

[0115] determining, according to a corresponding relationship between different fingerprint unlocking success rates and different exposure time lengths, an exposure time length corresponding to the target fingerprint unlocking success rate as the target exposure time length.

[0116] In some embodiments, in the corresponding relationship, the unlocking success rate is negatively correlated with the exposure time length.

[0117] In some embodiments, the target neural network is trained in the following manner:

[0118] obtaining sample environment data and sample fingerprint unlocking information of a sample fingerprint image in a sample environment;

[0119] inputting the sample environment data into an initial neural network to obtain candidate fingerprint unlocking information output by the initial neural network;

[0120] determining a loss function based on a difference between the candidate fingerprint unlocking information and the sample fingerprint unlocking information;

[0121] training the initial neural network according to the loss function until the loss function meets a preset stop training condition to obtain the target neural network.

[0122] In some embodiments, the sample fingerprint unlocking information includes at least one of the following:

[0123] whether the sample fingerprint unlocking is successful;

[0124] an image quality parameter of the sample fingerprint image;

[0125] a matching degree parameter between the sample fingerprint image and a pre-determined standard fingerprint image.

[0126] In some embodiments, after the time length determination module 32 determines the target exposure time length of the optical sensor when collecting the fingerprint image according to the target environment data, the time length determination module 32 is further configured to:

[0127] determine whether the target exposure time length is an abnormal exposure time length;

[0128] When it is determined that the target exposure duration belongs to an abnormal exposure duration, a preset exposure duration is determined as the target exposure duration.

[0129] In some embodiments, the duration determining module 32, when determining whether the target exposure duration belongs to an abnormal exposure duration, is specifically configured to: determine whether the target exposure duration exceeds a preset duration threshold.

[0130] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts are described in the part of the method embodiments. The device embodiments described above are only illustrative, and the units described above as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Some or all of the modules can be selected to achieve the purpose of the present disclosure according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0131] Correspondingly, in one aspect, the embodiments of the present disclosure provide a terminal device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute executable instructions to implement the fingerprint unlocking method of any of the above.

[0132] With reference to Figure 4 The terminal device 400 can include one or more of the following components: a processing component 402, a memory 404, a power supply component 406, a multimedia component 408, an audio component 410, an input / output (I / O) interface 412, a sensor component 414, and a communication component 416.

[0133] The processing component 402 generally controls the overall operation of the terminal device 400, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 402 can include one or more processors 420 to execute instructions to complete all or part of the steps of the above methods. In addition, the processing component 402 can include one or more modules to facilitate interaction between the processing component 402 and other components. For example, the processing component 402 can include a multimedia module to facilitate the interaction between the multimedia component 408 and the processing component 402.

[0134] The memory 404 is configured to store various types of data to support the operation of the device 400. Examples of such data include instructions for any application or method operating on the terminal device 400, contact data, phonebook data, messages, pictures, videos, and the like. The memory 404 can be implemented by any type of volatile or nonvolatile memory, 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 disc, or optical disc.

[0135] The power supply component 406 supplies power for various components of the terminal device 400. The power supply component 406 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the terminal device 400.

[0136] The multimedia component 408 includes a screen providing an output interface between the terminal device 400 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes the touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action. In some embodiments, the multimedia component 408 includes a front camera and / or a back camera. The front and / or back camera can receive external multimedia data when the device 400 is in an operation mode, such as a shooting mode or a video mode. Each of the front and back camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0137] The audio component 410 is configured to output and / or input an audio signal. For example, the audio component 410 includes a microphone (MIC) configured to receive an external audio signal when the terminal device 400 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 404 or transmitted via the communication component 416. In some embodiments, the audio component 410 also includes a speaker for outputting an audio signal.

[0138] The I / O interface 412 provides an interface between the processing component 402 and peripheral interface modules, which can be a keyboard, a click wheel, a button, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0139] The sensor component 414 includes one or more sensors to provide status assessments for various aspects of the terminal device 400. For example, the sensor component 414 can detect an open / closed status of the device 400, relative positioning of components, such as a display and keypad of the terminal device 400, a change in position of the terminal device 400 or a component of the terminal device 400, presence or absence of user contact with the terminal device 400, orientation or acceleration / deceleration of the terminal device 400, and temperature changes of the terminal device 400. The sensor component 414 can include proximity sensors configured to detect the presence of objects in a proximity without any physical contact. The sensor component 414 can also include optical sensors, such as CMOS or CCD image sensors, for use in imaging applications. In some embodiments, the sensor component 414 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0140] The communication component 416 is configured to facilitate wired or wireless communication between the terminal device 400 and another device. The terminal device 400 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR, or a combination thereof. In an example embodiment, the communication component 416 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 416 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.

[0141] In an example embodiment, the terminal device 400 can be implemented with 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, micro-controllers, microprocessors, or other electronic elements to perform the above-described methods.

[0142] In an example embodiment, a non-transitory computer-readable storage medium, such as the memory 404 including instructions, is also provided, which when executed by the processor 420 of the terminal device 400, enables the terminal device 400 to perform any of the above-described fingerprint unlocking methods.

[0143] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the disclosure be construed as including any paterns of this disclosure that can be derived from the description and illustrations presented herein without departing from the scope and spirit of the disclosure. The specification and examples are exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0144] It is to be understood that the disclosure is not limited to the precise construction here described and illustrated and that various modifications and changes can be made without departing from the scope thereof. The only scope of the disclosure is to be determined by the appended claims.

Claims

1. A fingerprint unlocking method, characterized in that, The method is applied to a terminal device and includes: In response to the detection of a fingerprint unlock command, target environment data of the environment in which the terminal device is located is obtained; The target environment data is input into a pre-trained target neural network, and the target unlocking result output by the target neural network is obtained. The target unlocking result includes the target fingerprint unlocking success rate. Based on the correspondence between different fingerprint unlocking success rates and different exposure times, the exposure time corresponding to the target fingerprint unlocking success rate is determined as the target exposure time of the optical sensor when acquiring fingerprint images. The optical sensor is controlled to continuously expose to achieve the target exposure time in order to acquire the fingerprint image; The terminal device is unlocked based on the fingerprint image.

2. The method according to claim 1, characterized in that, In the aforementioned correspondence, the unlocking success rate is negatively correlated with the exposure duration.

3. The method according to claim 1, characterized in that, The target neural network is trained using the following method: Acquire sample environment data and sample fingerprint image in the sample environment to obtain sample fingerprint unlocking information; The sample environment data is input into the initial neural network to obtain the alternative fingerprint unlocking information output by the initial neural network; Based on the difference between the candidate fingerprint unlocking information and the sample fingerprint unlocking information, a loss function is determined; The initial neural network is trained according to the loss function until the loss function meets the preset stopping training condition, thereby obtaining the target neural network.

4. The method according to claim 3, characterized in that, The sample fingerprint unlocking information includes at least one of the following: Was the fingerprint unlock successful? Image quality parameters of the sample fingerprint image; The matching degree parameter between the sample fingerprint image and the pre-determined standard fingerprint image.

5. The method according to claim 1, characterized in that, After determining the target exposure time of the optical sensor when acquiring the fingerprint image based on the target environment data, the method further includes: Determine whether the target exposure duration is an abnormal exposure duration; When it is determined that the target exposure duration is an abnormal exposure duration, the preset exposure duration is determined as the target exposure duration.

6. The method according to claim 5, characterized in that, Determining whether the target exposure duration is an abnormal exposure duration includes: Determine whether the target exposure duration exceeds a preset duration threshold.

7. A fingerprint unlocking device, characterized in that, The device is used in a terminal device, and the device includes: The data acquisition module is used to: in response to the detection of a fingerprint unlocking command, acquire target environment data of the environment in which the terminal device is located; The duration determination module is used for: The target environment data is input into a pre-trained target neural network, and the target unlocking result output by the target neural network is obtained. The target unlocking result includes the target fingerprint unlocking success rate. Based on the correspondence between different fingerprint unlocking success rates and different exposure times, the exposure time corresponding to the target fingerprint unlocking success rate is determined as the target exposure time of the optical sensor when acquiring fingerprint images. The fingerprint acquisition module is used to: control the optical sensor to continuously expose to the target exposure time in order to acquire the fingerprint image; The identification and unlocking module is used to unlock the terminal device based on the fingerprint image.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the fingerprint unlocking method according to any one of claims 1 to 6.

9. A terminal device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the executable instructions to implement the steps of the fingerprint unlocking method according to any one of claims 1 to 6.

Images