CN107832598A - Solve lock control method and Related product - Google Patents

Abstract

The embodiment of the present invention discloses an unlocking control method and related products, wherein the method includes: acquiring the preview image of the target face and the current location of the mobile terminal; when the current location belongs to the preset security location set, from the preset Select M living body detection dimensions corresponding to the current position from the N living body detection dimensions, the N is an integer greater than 1, and the M is a positive integer smaller than the N; according to the M living body detection dimensions Liveness detection is performed on the target face in the preview image to obtain a detection result; when the detection result is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. By adopting the invention, the security of the mobile terminal can be guaranteed, and the verification time of living body detection can be shortened.

Description

Unlock control method and related products

technical field

The invention relates to the technical field of mobile terminals, and mainly relates to an unlocking control method and related products.

Background technique

With the continuous development of mobile terminal technology, the use of mobile terminals such as mobile phones, computers, and tablets is becoming more and more popular, and face recognition methods are allowed to be used for unlocking. In order to avoid the use of two-dimensional forged face images such as photos and videos to complete face recognition for unlocking operations, the method of liveness detection is used to improve the security of mobile terminals. However, the time for liveness detection is often relatively long, resulting in a prolonged unlocking time and poor user experience.

Contents of the invention

Embodiments of the present invention provide an unlocking control method and related products, which can ensure the safety of mobile terminals and shorten the verification time of live body detection.

In a first aspect, an embodiment of the present invention provides an unlocking control method, including:

Obtain the preview image of the target face and the current location of the mobile terminal;

When the current position belongs to the preset safe position set, M living body detection dimensions corresponding to the current position are selected from the preset N living body detection dimensions, where N is an integer greater than 1, and M is a positive integer less than said N;

Performing liveness detection on the target face in the preview image according to the M liveness detection dimensions to obtain a detection result;

When the detection result is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes.

In a second aspect, an embodiment of the present invention provides a mobile terminal, including a processor, a camera connected to the processor, and a memory, wherein:

The memory is used to store N living body detection dimensions, and the N is an integer greater than 1;

The camera is used to collect preview images;

The processor is configured to acquire the preview image and the current location of the mobile terminal; when the current location belongs to a preset safe location set, select a location corresponding to the current location from the N living body detection dimensions M liveness detection dimensions; according to the M liveness detection dimensions, the target face in the preview image is carried out liveness detection to obtain a detection result, and the M is a positive integer less than the N; the detection result is When the person is alive, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes.

In a third aspect, an embodiment of the present invention provides an unlocking control device, including:

An acquisition unit, configured to acquire the preview image of the target face and the current position of the mobile terminal;

A selection unit, configured to select M living body detection dimensions corresponding to the current position from preset N living body detection dimensions when the current position belongs to a preset safe position set, where N is an integer greater than 1 , the M is a positive integer smaller than the N;

A detection unit, configured to perform liveness detection on the target face in the preview image according to the M liveness detection dimensions, to obtain a detection result;

A recognition unit, configured to perform face recognition on the target face when the detection result is a living body;

The unlocking unit is configured to perform an unlocking operation when the face recognition is passed.

In a fourth aspect, an embodiment of the present invention provides another unlocking control method, which is applied to a mobile terminal including a processor, a camera connected to the processor, and a memory, wherein:

The memory stores N living body detection dimensions, and the N is an integer greater than 1;

The camera captures a preview image;

The processor obtains the preview image and the current location of the mobile terminal; when the current location belongs to a preset safe location set, selects M corresponding to the current location from the N living body detection dimensions Living body detection dimension; according to the M living body detection dimensions, live detection is performed on the target face in the preview image to obtain a detection result, and the M is a positive integer smaller than the N; when the detection result is a living body, Face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes.

In a fifth aspect, an embodiment of the present invention provides another mobile terminal, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and are configured by the above executed by a processor, the program includes instructions for some or all of the steps described in the first aspect.

In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the computer program described in the first aspect of the embodiment of the present invention. Some or all of the steps described.

In a seventh aspect, an embodiment of the present invention provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable the computer to execute the Part or all of the steps described in the first aspect of the invention embodiment. The computer program product may be a software installation package.

Implementing the embodiment of the present invention will have the following beneficial effects:

After adopting the above-mentioned unlocking control method and related products, when the current location of the mobile terminal belongs to the preset safe location set, M living detection dimensions corresponding to the current location are selected from the preset N living detection dimensions, and according to M liveness detection dimensions perform liveness detection on the target face in the acquired preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

in:

FIG. 1 is a schematic flowchart of an unlocking control method provided by an embodiment of the present invention;

Fig. 2 is a schematic structural diagram of an unlocking control device provided by an embodiment of the present invention;

FIG. 2A is a schematic structural diagram of a selection unit provided by an embodiment of the present invention;

FIG. 2B is a schematic structural diagram of a detection unit provided by an embodiment of the present invention;

FIG. 2C is a schematic structural diagram of an identification unit provided by an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a mobile terminal provided by an embodiment of the present invention;

FIG. 4 is a schematic flowchart of another unlocking control method provided by an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of another mobile terminal provided by an embodiment of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, products or devices.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

With the maturity of face recognition technology, commercial applications are becoming more and more extensive. However, faces are very easy to copy by means of photos, videos, etc. Therefore, counterfeiting of legitimate user faces is an important threat to the security of face recognition and authentication systems. At present, the commonly used face liveness detection includes motion command liveness detection based on dynamic video, near-infrared face liveness detection and 3D face liveness detection.

The living body detection dimensions involved in the embodiments of the present invention are not limited, and may be frame, light reflection, or image quality. is non-living.

Embodiments of the present invention provide an unlocking control method and related products, which can ensure the safety of mobile terminals and shorten the verification time of live body detection. Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of an unlocking control method provided by an embodiment of the present invention. As shown in Figure 1, the above-mentioned unlocking control method includes:

101: Obtain a preview image of the target face and the current location of the mobile terminal.

When face recognition is started, the camera or other image acquisition equipment captures the preview image of the target face. This application does not limit the form of the acquired preview image. It can be a certain image in the acquisition process, or it can be composed of multiple images. A dynamic image composed of consecutive images.

In the embodiment of the present invention, the method for obtaining the current location of the mobile terminal is not limited, and the GPS function or the location service may be invoked on the mobile terminal through the Global Positioning System (Global Positioning System, GPS) function or location service supported by the mobile terminal. Then obtain the current location of the mobile terminal; you can also obtain the current location through wireless communication networks such as wireless networks, Bluetooth or other infrared devices. Since the above wireless communication networks can only be connected within a limited area, you can use the address of the wireless communication network or The domain name obtains the current location of the mobile terminal; the current location can also be obtained according to the symbol object in the preview image or the location information called by the application program of the mobile terminal. Among them, the sign objects can be road signs, road signs, bus stop signs, shopping malls, landmarks (railway stations, monuments, etc.), etc.; the above-mentioned applications can be navigation applications, bus query applications, shared bicycle applications, weather applications, takeaway applications, etc. Wait.

102: When the current location belongs to the preset safe location set, select M living body detection dimensions corresponding to the current location from the preset N living body detection dimensions.

Wherein, the preset safe location set may include the location corresponding to the frequency greater than the preset threshold in the historical location record of the mobile terminal, the safe location set by the user input, or multiple reference locations selected according to the above frequency, and the user selects from multiple reference locations location etc.

M is a positive integer less than N, that is to say, when the current location belongs to the preset safe location set, M living detection dimensions corresponding to the current location can be selected from the preset N living detection dimensions to ensure the security of the mobile terminal. Security, and improve the flexibility of mobile terminal unlocking control. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

In the embodiment of the present invention, there is no limitation on how to select the M living body detection dimensions. Optionally, acquire the target security level of the current location; select the M living body detection dimensions corresponding to the target security level from the N living body detection dimensions.

Among them, the security level can be determined according to the historical location record of the mobile terminal to obtain the frequency of each location and the safety factor of the location, that is, the weight corresponding to the frequency and the safety factor is preset, and the corresponding security value is obtained through weighted calculation. Determine the security level based on the security value. The specific description form of the security level is not limited, and may be a number, wherein a larger number indicates a higher security level.

For example: Assuming that Wang Xiaoer's historical location record has a frequency of home location and company location of 0.6 and 0.5, the safety factor of the home location is 0.9, and since the company location is a public place, the safety factor of the company location is 0.4. If the preset weights of frequency and safety factor are divided into 0.5 and 0.5, then the corresponding safety values of home location and company location are 0.75 and 0.45. Assuming that the mapping relationship between the security value and the corresponding security level is shown in Table 1, the security level of the company location is 4, and the security level of the home location is 3. When the number is larger, the security level is higher, and the security level of the company location is less than The security level of the home location.

Table 1

safe value Security Level [0-0.2] 1 [0.2-0.4] 2 [0.4-0.6] 3 [0.6-0.8] 4 [0.8-1] 5

Each security level can be associated with the living body detection dimension, that is to say, the living body detection dimension can be determined after its security level is determined, thereby improving the speed of determining the living body detection dimension, and performing liveness detection for the security level to ensure the security of the mobile terminal Security, and improve the flexibility of mobile terminal unlocking control.

For example, it is assumed that the N living body detection dimensions preset in the mobile terminal are frame, light reflection and image quality respectively. As shown in Table 2, the mapping relationship between the security level and the living body detection dimension, if the current location of the mobile terminal is the home location, as shown in Table 1, the security level is 4, and the living body detection dimension is light reflection and image quality, reducing up the border.

Table 2

Security Level Liveness Detection Dimensions 1 frame 2 reflection of light 3 picture quality 4 Light reflection and image quality 5 Frames and reflections of light

103: Perform liveness detection on the target face in the preview image according to the M liveness detection dimensions to obtain a detection result.

There are no restrictions on how to perform liveness detection based on the M livingness detection dimensions, but the detection value corresponding to each livingness detection dimension is greater than the livingness threshold, and the detection result is confirmed to be livingness, and each detection value and the weight of the preset weight can also be used. When the value is greater than the living threshold, it is confirmed that the detection result is living.

Optionally, the detection value of each living body detection dimension in the M living body detection dimensions is obtained to obtain M detection values; according to the correspondence between the M detection values and each living body detection dimension in the M living body detection dimensions The preset weight of the target face determines the liveness evaluation value of the target face; when the liveness evaluation value is greater than the liveness threshold, it is confirmed that the detection result is a liveness.

Wherein, each living body detection dimension corresponds to a preset weight, and each living body detection dimension corresponds to a detection value for the target face in the preview image, and the living body of the target face is obtained by the weighted sum of the preset weight and the detection value. The evaluation value can also avoid the technical problem that the detection value of a certain living body detection dimension is too low, which leads to the failure of verification, and can improve the flexibility of living body detection.

For example, suppose the living body threshold is 0.8, and the M living body detection dimensions are frame, light reflection and image quality, where the preset weight of frame is 0.3, the preset weight of light reflection is 0.4, and the preset weight of image quality is Set the weight to 0.3. Liveness detection is performed according to the three living body detection dimensions of frame, light reflection and image quality. When the detection values corresponding to the three living body detection dimensions of frame, light reflection and image quality are 0.9, 0.7 and 0.9 respectively, the living body evaluation value is 0.3 *0.9+0.4*0.7+0.3*0.9＝0.82 is greater than the living body threshold, confirming that the detection result is living; the detection values corresponding to the three living body detection dimensions of Dangdang frame, light reflection and image quality are 0.9, 0.7 and 0.8 respectively, indicating that the living body The evaluation value of 0.3*0.9+0.4*0.7+0.3*0.8=0.79 is less than the living body threshold, and the detection result is confirmed as non-living body. That is to say, regardless of whether the detection value of each living body detection dimension is greater than the living body threshold, when the living body evaluation value is greater than the living body threshold, the detection result is confirmed as living, which can improve the flexibility of living body detection.

Optionally, acquire scene parameters and environmental parameters of the mobile terminal; determine a preset weight corresponding to each living body detection dimension in the M living body detection dimensions and the living body according to the scene parameters and the environmental parameters threshold.

Wherein, the scene parameter may include at least one of the following: application type, occupied network speed, transmission data and data type, and the like. The application scenario corresponding to the scenario parameter may be unlocking operations such as screen unlocking, payment unlocking, and login unlocking of the mobile terminal, and the embodiment of the present invention does not limit specific scenario parameters. Different scene parameters have different security requirements for the liveness detection dimension. For example, if the security requirements are higher when payment is unlocked, the liveness threshold for liveness detection needs to be increased.

Environmental parameters may include at least one of the following: light intensity, temperature, humidity, electromagnetic interference, distance value or infrared variation detected by proximity sensors, etc., the specific environmental parameters are not limited in the embodiment of the present invention, different environmental parameters It has a certain impact on the detection results of the living body detection dimension. For example, the reflection of light requires high light intensity.

The preset weight and living body threshold corresponding to each living body detection dimension in the M living body detection dimensions are determined by scene parameters and environmental parameters, which can ensure the safety of the mobile terminal and improve the accuracy of the living body evaluation value.

104: When the detection result is a living body, perform face recognition on the target face, and perform an unlocking operation when the face recognition passes.

When the detection result is a living body, that is, the target face in the preview image is a living body, further face recognition can be performed. There is no limitation on how to perform face recognition based on the target face in the preview image, and the target in the corresponding preview image can be extracted based on the preset angle, preset action or preset expression set in the action command liveness detection face recognition; or select the target image corresponding to the highest evaluation value among several consecutive images in the preview image, and then extract the face image in the target image for face recognition.

Optionally, when the preview image includes multiple target images, split the preview image to obtain the multiple target images; perform image segmentation on each target image in the multiple target images to obtain A plurality of face images; obtain the image evaluation value corresponding to each face image in the plurality of face images, and obtain a plurality of image evaluation values; obtain the target face corresponding to the highest evaluation value in the plurality of image evaluation values image; performing face recognition on the target face image.

Wherein, the image evaluation value may be one or more evaluation values of the overall evaluation value, focus evaluation value, angle evaluation value, expression evaluation value and/or feature point integrity of the face image. The calculation formula for obtaining the image evaluation value can be:

EV＝b ₁ ×ev ₁ +b ₂ ×ev ₂ +b ₃ ×ev ₃ +...+b _n ×ev _n (1)

In formula (1), EV is the image evaluation value, ev ₁ , ev ₂ , ev ₃ and ev _n are different evaluation values, b ₁ , b ₂ , b ₃ and b _n are ev ₁ , ev ₂ , ev ₃ respectively The weight corresponding to ev _n . Wherein, the specific value of b ₁ ( _i = ₁ , ₂ , ₃ , .

It can be understood that the preview image is split to obtain multiple target images, and the face images in the multiple target images are extracted to obtain multiple face images, and the face image with the highest image evaluation value among the multiple face images is used as the target Face image, face recognition is performed on the target face image. That is to say, selecting the target face image corresponding to the highest evaluation value for face recognition can improve the accuracy of face recognition.

In the unlocking control method as shown in Figure 1, when the current location of the mobile terminal belongs to the preset safe location set, M living detection dimensions corresponding to the current position are selected from the preset N living detection dimensions, and according to M liveness detection dimensions perform liveness detection on the target face in the acquired preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

Consistent with the embodiment in FIG. 1 , please refer to FIG. 2 . FIG. 2 is an unlocking control device provided by an embodiment of the present invention. As shown in Figure 2, the unlocking control device 200 includes:

The obtaining unit 201 is configured to obtain a preview image of a target face and a current location of the mobile terminal.

The selecting unit 202 is configured to select M living body detection dimensions corresponding to the current position from preset N living body detection dimensions when the current position belongs to a preset safe position set, where N is greater than 1 Integer, the M is a positive integer smaller than the N.

The detecting unit 203 is configured to perform liveness detection on the target face in the preview image according to the M livingness detection dimensions, and obtain a detection result.

The recognition unit 204 is configured to perform face recognition on the target face when the detection result is a living body.

The unlocking unit 205 is configured to perform an unlocking operation when the face recognition is passed.

In a possible example, as shown in FIG. 2A, the selecting unit 202 includes:

The first acquiring module 2021 is configured to acquire the target security level of the current location;

The selecting module 2022 selects the M living detection dimensions corresponding to the target security level from the N living detection dimensions.

In a possible example, as shown in FIG. 2B, the detection unit 203 includes:

The second acquiring module 2031 is configured to acquire the detection value of each living body detection dimension in the M living body detection dimensions, and obtain M detection values;

A determining module 2032, configured to determine the liveness evaluation value of the target face according to the M detection values and the preset weight corresponding to each living body detection dimension in the M living body detection dimensions; in the living body evaluation value When it is greater than the living body threshold, it is confirmed that the detection result is a living body.

In a possible example, the second acquiring module 2031 is also configured to acquire scene parameters and environment parameters of the mobile terminal;

The determining module 2032 is further configured to determine a preset weight corresponding to each living body detection dimension in the M living body detection dimensions and the living body threshold according to the scene parameters and the environmental parameters.

In a possible example, as shown in FIG. 2C, the identifying unit 204 includes:

A splitting module 2041, configured to split the preview image to obtain the multiple target images when the preview image includes multiple target images;

A segmentation module 2042, configured to perform image segmentation on each target image in the multiple target images to obtain multiple face images;

The third obtaining module 2043 is used to obtain the image evaluation value corresponding to each face image in the plurality of face images to obtain a plurality of image evaluation values; obtain the target corresponding to the highest evaluation value in the plurality of image evaluation values face image;

The recognition module 2044 is configured to perform face recognition on the target face image.

In the unlocking control device as shown in FIG. 2, when the current position of the mobile terminal belongs to the preset safe position set, M living body detection dimensions corresponding to the current position are selected from the preset N living body detection dimensions, and according to M liveness detection dimensions perform liveness detection on the target face in the acquired preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of liveness detection is reduced, which can shorten the verification time of liveness detection and facilitate the unlocking speed.

It can be understood that the functions of each program unit or module of the unlocking control device in this embodiment can be implemented according to the method in the method embodiment, and the specific implementation process can refer to the relevant description of the method embodiment, and will not be repeated here.

Please refer to FIG. 3 . FIG. 3 is a schematic structural diagram of a mobile terminal 300 provided by an embodiment of the present invention. The above-mentioned mobile terminal 300 includes: a processor 310 , a memory 320 , a camera 330 and an environment sensor 340 , and the processor 310 is connected to the memory 320 , the camera 330 and the environment sensor 340 through a bus 350 .

The embodiment of the present invention does not limit the specific form of the camera. For details, reference may be made to the camera configured in the mobile terminal 300. The default is a front camera, and a rear camera or a rotating camera may also be used. Image acquisition is performed through a variety of cameras, which improves the convenience of operation and the flexibility of unlocking.

Based on the mobile terminal 300 described in FIG. 3, the following operations can be performed:

In the embodiment of the present invention, the memory 320 is used to store N living body detection dimensions; the camera 330 is used to collect preview images.

Wherein, N is an integer greater than 1. The living body detection dimension in the embodiment of the present invention is not limited, it can be a frame, light reflection or image quality, etc., when there is an obvious frame, abnormal light reflection or poor image quality, the target face in the preview image is considered is non-living.

When face recognition is started, the camera 330 or other image acquisition devices will preview the image of the target face. This application does not limit the form of the acquired preview image. It can be a certain image in the acquisition process, or it can be composed of multiple A dynamic image composed of consecutive images.

In the embodiment of the present invention, the processor 310 is configured to obtain the preview image and the current location of the mobile terminal; when the current location belongs to a preset safe location set, select from the N living body detection dimensions The M living body detection dimensions corresponding to the current position; according to the M living body detection dimensions, live body detection is performed on the target face in the preview image to obtain a detection result, and the M is a positive integer smaller than the N; When the detection result is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes.

In the embodiment of the present invention, the method for obtaining the current location of the mobile terminal is not limited, and the current location of the mobile terminal can be obtained after the mobile terminal turns on GPS or calls the location service through the GPS function or location service supported by the mobile terminal; The current location can be obtained through wireless communication networks such as wireless networks, Bluetooth or other infrared devices. Since the above wireless communication networks can only be connected within a limited area, the current location of the mobile terminal can be obtained through the address or domain name of the wireless communication network; The current location can be obtained according to the landmark object in the preview image or the location information invoked in the application program of the mobile terminal. Among them, the sign objects can be road signs, road signs, bus stop signs, shopping malls, landmarks (railway stations, monuments, etc.), etc.; the above-mentioned applications can be navigation applications, bus query applications, shared bicycle applications, weather applications, takeaway applications, etc. Wait.

Wherein, the preset safe location set may include the location corresponding to the frequency greater than the preset threshold in the historical location record of the mobile terminal, the safe location set by the user input, or multiple reference locations selected according to the above frequency, and the user selects from multiple reference locations location etc.

M is a positive integer less than N, that is to say, when the current location belongs to the preset safe location set, M living detection dimensions corresponding to the current location can be selected from the preset N living detection dimensions to ensure the security of the mobile terminal. Security, and improve the flexibility of mobile terminal unlocking control. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

In the embodiment of the present invention, there is no limitation on how to select the M living body detection dimensions. Optionally, in the aspect that the processor 310 selects M living body detection dimensions corresponding to the current location from the N living body detection dimensions, the processor 310 is specifically configured to obtain the target security of the current location. Level: selecting the M living body detection dimensions corresponding to the target security level from the N living body detection dimensions.

Among them, the security level can be determined according to the historical location record of the mobile terminal to obtain the frequency of each location and the safety factor of the location, that is, the weight corresponding to the frequency and the safety factor is preset, and the corresponding security value is obtained through weighted calculation. Determine the security level based on the security value. The specific description form of the security level is not limited, and may be a number, wherein a larger number indicates a higher security level.

Each security level can be associated with the living body detection dimension, that is to say, the living body detection dimension can be determined after its security level is determined, thereby improving the speed of determining the living body detection dimension, and performing liveness detection for the security level to ensure the security of the mobile terminal Security, and improve the flexibility of mobile terminal unlocking control.

There are no restrictions on how to perform liveness detection based on the M livingness detection dimensions, but the detection value corresponding to each livingness detection dimension is greater than the livingness threshold, and the detection result is confirmed to be livingness, and each detection value and the weight of the preset weight can also be used. When the value is greater than the living threshold, it is confirmed that the detection result is living.

Optionally, the memory 320 is also used to store preset weights and living body thresholds corresponding to each living body detection dimension in the N living body detection dimensions; In terms of liveness detection of the target face in the preview image to obtain the detection result, the processor 310 is specifically configured to obtain the detection value of each of the M livingness detection dimensions to obtain M detection values; according to The M detection values and the preset weights corresponding to each living body detection dimension in the M living body detection dimensions determine the living body evaluation value of the target face; when the living body evaluation value is greater than the living body threshold, Confirm that the test result is a living body.

Wherein, each living body detection dimension corresponds to a preset weight, and each living body detection dimension corresponds to a detection value for the target face in the preview image, and the living body of the target face is obtained by the weighted sum of the preset weight and the detection value. The evaluation value can also avoid the technical problem that the detection value of a certain living body detection dimension is too low, which leads to the failure of verification, and can improve the flexibility of living body detection.

Optionally, the environment sensor 340 is used to obtain the environmental parameters of the mobile terminal; the processor 310 is also used to obtain the scene parameters of the mobile terminal; The preset weight corresponding to each living body detection dimension in the M living body detection dimensions and the living body threshold.

Wherein, the scene parameter may include at least one of the following: application type, occupied network speed, transmission data and data type, and the like. The application scenario corresponding to the scenario parameter may be unlocking operations such as screen unlocking, payment unlocking, and login unlocking of the mobile terminal, and the embodiment of the present invention does not limit specific scenario parameters. Different scene parameters have different security requirements for the liveness detection dimension. For example, if the security requirements are higher when payment is unlocked, the liveness threshold for liveness detection needs to be increased.

Environmental parameters may include at least one of the following: light intensity, temperature, humidity, electromagnetic interference, distance value or infrared variation detected by proximity sensors, etc., the specific environmental parameters are not limited in the embodiment of the present invention, different environmental parameters It has a certain impact on the detection results of the living body detection dimension. For example, the reflection of light requires high light intensity.

The preset weight and living body threshold corresponding to each living body detection dimension in the M living body detection dimensions are determined by scene parameters and environmental parameters, which can ensure the safety of the mobile terminal and improve the accuracy of the living body evaluation value.

When the detection result is a living body, that is, the target face is a living body, further face recognition can be performed. There is no limitation on how to perform face recognition based on the target face in the preview image, and the target in the corresponding preview image can be extracted based on the preset angle, preset action or preset expression set in the action command liveness detection face recognition; or select the target image corresponding to the highest evaluation value among several consecutive images in the preview image, and then extract the face image in the target image for face recognition.

Optionally, in terms of performing face recognition on the target face by the processor 310, the processor 310 is specifically configured to split the preview image when the preview image includes multiple target images , to obtain the multiple target images; perform image segmentation on each target image in the multiple target images to obtain multiple face images; obtain the image evaluation corresponding to each face image in the multiple target images value, obtaining a plurality of image evaluation values; acquiring a target face image corresponding to the highest evaluation value among the plurality of image evaluation values; performing face recognition on the target face image.

Wherein, the image evaluation value may be one or more evaluation values of the overall evaluation value, focus evaluation value, angle evaluation value, expression evaluation value and/or feature point integrity of the face image.

It can be understood that the preview image is split to obtain multiple target images, and the face images in the multiple target images are extracted to obtain multiple face images, and the face image with the highest image evaluation value among the multiple face images is used as the target Face image, face recognition is performed on the target face image. That is to say, selecting the target face image corresponding to the highest evaluation value for face recognition can improve the accuracy of face recognition.

In the mobile terminal shown in Figure 3, when the current location of the mobile terminal belongs to the preset safe location set, M living detection dimensions corresponding to the current location are selected from the preset N living detection dimensions, and according to M Liveness detection is performed on the target face in the obtained preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

Consistent with the embodiment in FIG. 3 , please refer to FIG. 4 . FIG. 4 is an unlocking control method provided by an embodiment of the present invention, which is applied to the mobile terminal as described in FIG. 3 . in:

401: The memory stores N living body detection dimensions.

402: The camera collects preview images.

403: The processor acquires the preview image and the current location of the mobile terminal; when the current location belongs to the preset safe location set, select M living body detection dimensions corresponding to the current location from the N living body detection dimensions; according to the M living body detection dimensions Perform liveness detection on the target face in the preview image to obtain the detection result; when the detection result is live, perform face recognition on the target face, and perform an unlocking operation when the face recognition passes.

In a possible example, the selecting, by the processor, of the M living body detection dimensions corresponding to the current location from the N living body detection dimensions includes: acquiring the target security level of the current location by the processor; The M living body detection dimensions corresponding to the target security level are selected from the N living body detection dimensions.

In a possible example, the memory stores a preset weight and a living body threshold corresponding to each living body detection dimension in the N living body detection dimensions;

The processor performing liveness detection on the target face in the preview image according to the M liveness detection dimensions to obtain the detection result includes: the processor acquiring the detection of each liveness detection dimension in the M liveness detection dimensions value, to obtain M detection values; determine the living body evaluation value of the target face according to the M detection values and the preset weights corresponding to each living body detection dimension in the M living body detection dimensions; in the living body When the evaluation value is greater than the living body threshold, it is confirmed that the detection result is a living body.

In a possible example, before the processor acquires the detection value of each of the M life detection dimensions to obtain M detection values, the method further includes: the environment sensor acquires the The environmental parameters of the mobile terminal; the processor acquires the scene parameters of the mobile terminal; according to the scene parameters and the environmental parameters, the preset weights and values corresponding to each living body detection dimension in the M living body detection dimensions are determined The living body threshold.

In a possible example, the face recognition performed by the processor on the target face includes: when the preview image includes multiple target images, splitting the preview image to obtain the multiple target images; performing image segmentation on each target image in the multiple target images to obtain multiple face images; obtaining an image evaluation value corresponding to each face image in the multiple target images to obtain a plurality of image evaluation values; Acquiring a target face image corresponding to the highest evaluation value among the plurality of image evaluation values; performing face recognition on the target face image.

In the unlocking control method as shown in Figure 4, when the current location of the mobile terminal belongs to the preset security location set, M living detection dimensions corresponding to the current position are selected from the preset N living detection dimensions, and according to M liveness detection dimensions perform liveness detection on the target face in the acquired preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

Consistent with the embodiments of FIG. 1 , FIG. 2 , FIG. 3 and FIG. 4 , please refer to FIG. 5 . FIG. 5 is a schematic structural diagram of a mobile terminal provided by an embodiment of the present invention. As shown in FIG. 5 , the mobile terminal 500 includes Processor 510, memory 520, communication interface 530 and one or more programs 540, wherein, one or more programs 540 are stored in the memory 520, and are configured to be executed by the processor 510, the program 540 includes the following steps for performing The command:

Obtain the preview image of the target face and the current location of the mobile terminal;

When the current position belongs to the preset safe position set, M living body detection dimensions corresponding to the current position are selected from the preset N living body detection dimensions, where N is an integer greater than 1, and M is a positive integer less than said N;

Performing liveness detection on the target face in the preview image according to the M liveness detection dimensions to obtain a detection result;

When the detection result is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes.

It can be seen that in the embodiment of the present invention, when the current location of the mobile terminal belongs to the preset safe location set, M living detection dimensions corresponding to the current location are selected from the preset N living detection dimensions, and according to the M The liveness detection dimension performs liveness detection on the target face in the acquired preview image. When the detection result obtained by the living body detection is a living body, face recognition is performed on the target face, and an unlocking operation is performed when the face recognition passes. That is to say, the living body detection is performed according to the living body detection dimension selected according to the current position of the mobile terminal, so as to ensure the safety of the mobile terminal and improve the flexibility of unlocking control of the mobile terminal. In addition, the dimension of living body detection is reduced, which can shorten the verification time of living body detection and facilitate the improvement of unlocking speed.

As an optional embodiment, in terms of selecting M living body detection dimensions corresponding to the current position from the preset N living body detection dimensions, the above-mentioned program 540 is specifically used to execute the following steps:

Obtain the target security level of the current location;

Selecting the M living body detection dimensions corresponding to the target security level from the N living body detection dimensions.

As an optional embodiment, in terms of performing liveness detection on the target face in the preview image according to the M livingness detection dimensions and obtaining the detection result, the above-mentioned program 540 is specifically used to execute the following steps: :

Obtain the detection value of each living body detection dimension in the M living body detection dimensions, and obtain M detection values;

determining the living body evaluation value of the target face according to the M detection values and the preset weight corresponding to each living body detection dimension in the M living body detection dimensions;

When the living body evaluation value is greater than the living body threshold, it is confirmed that the detection result is a living body.

As an optional embodiment, before acquiring the detection value of each of the M living body detection dimensions to obtain M detection values, the above-mentioned program 540 is also used to execute the following steps:

Obtain scene parameters and environment parameters of the mobile terminal;

A preset weight corresponding to each of the M living body detection dimensions and the living body threshold are determined according to the scene parameter and the environment parameter.

As an optional embodiment, in terms of performing face recognition on the target face, the above-mentioned program 540 is specifically used to execute instructions for the following steps:

When the preview image includes multiple target images, splitting the preview image to obtain the multiple target images;

Image segmentation is performed on each target image in the plurality of target images to obtain multiple face images;

Acquire the image evaluation value corresponding to each face image in the plurality of face images, and obtain a plurality of image evaluation values;

Acquiring the target face image corresponding to the highest evaluation value among the plurality of image evaluation values;

Face recognition is performed on the target face image.

An embodiment of the present invention also provides a computer storage medium, wherein the computer storage medium is used to store a computer program, and the computer program enables the computer to perform some or all steps of any method described in the method embodiments, and the computer includes a mobile terminal.

An embodiment of the present invention also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause the computer to execute any part of the method as described in the method embodiments or all steps. The computer program product may be a software installation package, and the computer includes a mobile terminal.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence. Because of the present invention, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

In the embodiments, the description of each embodiment has its own emphases, and for the part not described in detail in a certain embodiment, refer to the relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative, such as the division of units, which is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into Another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical or other forms.

A unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

An integrated unit may be stored in a computer-readable memory if implemented in the form of a software function unit and sold or used as an independent product. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory. Several instructions are included to make a computer device (which may be a personal computer, server or network device, etc.) execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned memory includes: various media capable of storing program codes such as U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk.

The embodiments of the present invention have been described in detail above, and specific examples have been used in this paper to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only used to help understand the method and core idea of the present invention; at the same time, for Those skilled in the art will have changes in the specific implementation and scope of application according to the idea of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims (14)

1. one kind solution lock control method, it is characterised in that including：

Obtain the preview image of target face and the current location of mobile terminal；

When belonging to default home collection in the current location, choose from default N number of In vivo detection dimension and work as with described M In vivo detection dimension corresponding to front position, the N are the integer more than 1, and the M is the positive integer less than the N；

In vivo detection is carried out to the target face in the preview image according to the M In vivo detection dimension, obtains detection knot Fruit；

When the testing result is live body, to the target face carry out recognition of face, and recognition of face by when perform Unblock operation.

2. according to the method for claim 1, it is characterised in that it is described from default N number of In vivo detection dimension choose with M In vivo detection dimension corresponding to the current location, including：

Obtain the targeted security grade of the current location；

The M In vivo detection dimension corresponding with the targeted security grade is chosen from N number of In vivo detection dimension.

3. method according to claim 1 or 2, it is characterised in that it is described according to the M In vivo detection dimension to described Target face in preview image carries out In vivo detection, obtains testing result, including：

The detected value of each In vivo detection dimension in the M In vivo detection dimension is obtained, obtains M detected value；

It is true according to preset weights corresponding to each In vivo detection dimension in the M detected value and the M In vivo detection dimension The vivo assessment value of the fixed target face；

When the vivo assessment value is more than live body threshold value, it is live body to confirm the testing result.

4. according to the method for claim 3, it is characterised in that each in the acquisition M In vivo detection dimension The detected value of In vivo detection dimension, before obtaining M detected value, methods described also includes：

Obtain the scenario parameters and ambient parameter of the mobile terminal；

Each In vivo detection dimension pair in the M In vivo detection dimension is determined according to the scenario parameters and the ambient parameter The preset weights and the live body threshold value answered.

5. according to the method described in claim any one of 1-4, it is characterised in that described to carry out face knowledge to the target face Not, including：

When the preview image includes multiple target images, the preview image is split, obtains multiple described targets Image；

Image segmentation is carried out to every target image in multiple described target images, obtains multiple facial images；

Picture appraisal value corresponding to every facial image in multiple described facial images is obtained, obtains multiple images evaluation of estimate；

Obtain target facial image corresponding to highest evaluation of estimate in the multiple picture appraisal value；

Recognition of face is carried out to the target facial image.

A kind of 6. mobile terminal, it is characterised in that the camera and memory being connected including processor, with the processor, its In：

The memory, for storing N number of In vivo detection dimension, the N is the integer more than 1；

The camera, for gathering preview image；

The processor, for obtaining the current location of the preview image and the mobile terminal；Belong in the current location When default home collection, M In vivo detection corresponding with the current location is chosen from N number of In vivo detection dimension Dimension；In vivo detection is carried out to the target face in the preview image according to the M In vivo detection dimension and obtains detection knot Fruit, the M are the positive integer less than the N；When the testing result is live body, face knowledge is carried out to the target face Not, and recognition of face by when perform unblock operation.

7. mobile terminal according to claim 6, it is characterised in that tieed up in the processor from N number of In vivo detection In terms of choosing M In vivo detection dimension corresponding with the current location in degree, the processor is specifically used for obtaining described work as The targeted security grade of front position；The M corresponding with the targeted security grade is chosen from N number of In vivo detection dimension Individual In vivo detection dimension.

8. the mobile terminal according to claim 6 or 7, it is characterised in that

The memory, it is additionally operable to store preset weights corresponding to each In vivo detection dimension in N number of In vivo detection dimension With live body threshold value；

In vivo detection is carried out to the target face in the preview image according to the M In vivo detection dimension in the processor In terms of obtaining testing result, the processor is specifically used for obtaining each In vivo detection dimension in the M In vivo detection dimension Detected value, obtain M detected value；According to each In vivo detection dimension in the M detected value and the M In vivo detection dimension Preset weights corresponding to degree determine the vivo assessment value of the target face；It is more than the live body threshold value in the vivo assessment value When, it is live body to confirm the testing result.

9. mobile terminal according to claim 8, it is characterised in that the mobile terminal also includes connecting with the processor The environmental sensor connect；

The environmental sensor, for obtaining the ambient parameter of the mobile terminal；

The processor, it is additionally operable to obtain the scenario parameters of the mobile terminal；Joined according to the scenario parameters and the environment Number determines preset weights corresponding to each In vivo detection dimension and the live body threshold value in the M In vivo detection dimension.

10. according to the mobile terminal described in claim any one of 6-9, it is characterised in that in the processor to the target In terms of face carries out recognition of face, the processor is specifically used for when the preview image includes multiple target images, to institute State preview image to be split, obtain multiple described target images；Every target image in multiple described target images is carried out Image is split, and obtains multiple facial images；Picture appraisal value corresponding to every facial image in multiple described facial images is obtained, Obtain multiple images evaluation of estimate；Obtain target facial image corresponding to highest evaluation of estimate in the multiple picture appraisal value；To institute State target facial image and carry out recognition of face.

11. one kind solution lock control device, it is characterised in that including：

Acquiring unit, for obtaining the preview image of target face and the current location of mobile terminal；

Unit is chosen, during for belonging to default home collection in the current location, from default N number of In vivo detection dimension M In vivo detection dimension corresponding with the current location is chosen, the N is the integer more than 1, and the M is less than the N's Positive integer；

Detection unit, for carrying out live body inspection to the target face in the preview image according to the M In vivo detection dimension Survey, obtain testing result；

Recognition unit, for when the testing result is live body, recognition of face to be carried out to the target face；

Unlocking unit, for recognition of face by when perform unblock operation.

12. one kind solution lock control method, it is characterised in that applied to the camera being connected including processor, with the processor With the mobile terminal of memory, wherein：

The N number of In vivo detection dimension of memory storage, the N are the integer more than 1；

The camera gathers preview image；

The processor obtains the current location of the preview image and the mobile terminal；Belong to default in the current location During home collection, M In vivo detection dimension corresponding with the current location is chosen from N number of In vivo detection dimension； In vivo detection is carried out to the target face in the preview image according to the M In vivo detection dimension and obtains testing result, institute It is the positive integer less than the N to state M；When the testing result is live body, to target face progress recognition of face, and Recognition of face by when perform unblock operation.

A kind of 13. mobile terminal, it is characterised in that including processor, memory, communication interface and one or more programs, Wherein, one or more of programs are stored in the memory, and are configured by the computing device, the journey Sequence includes being used for the instruction that perform claim requires the step in any one of 1-5 method.

A kind of 14. computer-readable recording medium, it is characterised in that it is used to store computer program, wherein, the computer Program causes computer to perform the method as described in claim any one of 1-5.