WO2019096008A1 - Identification method, computer device, and storage medium - Google Patents

Abstract

Embodiments of the present application provide an identification method, a computer device, and a storage medium. The identification method comprises: identifying whether an object to be identified is a living body; when the computer device identifies that the object to be identified is the living body, obtaining a current face image of the object to be identified; determining whether a face deflection angle in the current face image is less than a preset angle threshold; and when the face deflection angle is less than the preset angle threshold and the current face image of the object to be identified matches a registered face image, succeeding in identifying the object to be identified.

Description

Identification method, computer device and storage medium

The present application claims the priority of the Chinese Patent Application entitled "Identification Method, Apparatus and Storage Device" by the Chinese Patent Office, filed on November 20, 2017, the entire disclosure of which is hereby incorporated by reference. in.

Technical field

The embodiments of the present invention relate to the field of image recognition technologies, and in particular, to an identity recognition method, a computer device, and a storage medium.

Background technique

The current identification method has a certain degree of defects. For example, the method of identifying by face is easy to be attacked by photos; for example, a person who does not have access control can use the photos of internal personnel to pass the access control smoothly, and the security is low. In addition, the method of identifying by face is easy to cause recognition errors due to different angles of face image acquisition; for example, the same user, face images of certain angles can be successfully recognized, face images of certain angles The recognition fails and the recognition accuracy is low.

Summary of the invention

According to various embodiments provided herein, an identification method, a computer device, and a storage medium are provided.

The identity identification method provided by the embodiment of the present application includes:

The computer device identifies whether the object to be identified is a living body;

Obtaining a current face image of the object to be identified when the computer device recognizes that the object to be identified is a living body;

Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.

A computer device comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor such that the processor performs the following steps:

Identify whether the object to be identified is a living body;

Obtaining a current face image of the object to be identified when the object to be identified is identified as a living body;

Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.

One or more non-volatile storage media storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the following steps:

Identify whether the object to be identified is a living body;

Obtaining a current face image of the object to be identified when the object to be identified is identified as a living body;

Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

1 is a schematic diagram of an application scenario of an identity recognition method provided by an embodiment of the present application;

1A is a schematic diagram of another application scenario of an identity recognition method provided by an embodiment of the present application;

1B is an internal structural diagram of a computer device of an identity recognition method provided by an embodiment of the present application;

1C is another internal structural diagram of a computer device of an identity recognition method provided by an embodiment of the present application;

2 is a schematic flowchart of an identity recognition method provided by an embodiment of the present application;

3 is another schematic flowchart of an identity recognition method provided by an embodiment of the present application;

4a is a schematic flowchart of a method for acquiring a preset angle threshold in the embodiment of the present application;

4b is another schematic flowchart of a method for acquiring a preset angle threshold in the embodiment of the present application;

FIG. 5 is a schematic structural diagram of an identity recognition apparatus according to an embodiment of the present application; FIG.

6 is another schematic structural diagram of an identity recognition apparatus according to an embodiment of the present application;

FIG. 7 is another schematic structural diagram of an identity recognition apparatus according to an embodiment of the present application.

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

Because the existing identification method has the problems of insufficient security and low recognition accuracy, the embodiment of the present application provides an identification method, a device, and a storage device. The identity identification method provided by the embodiment of the present application can be implemented in an identity. In the identification device, the identification device can be, for example, a monitoring device. For example, as shown in FIG. 1, when an object to be identified (for example, a person) is to pass through a door or a gate, the identification device can identify whether the object to be identified is a living body, and if the object to be identified is a living body, it can pass its own camera module. Obtaining a current face image of the object to be identified, determining whether a face deflection angle in the current face image is smaller than a preset angle threshold, and if the preset angle threshold is smaller, detecting a current current of the object to be identified Whether the face image matches the registered face image, and if the current face image matches the registered face image, the identity of the object to be identified is successful, and after the identity is successfully recognized, the object to be identified may be allowed to pass the access control or Gate machine. In the embodiment of the present application, by performing living body recognition on the object to be identified, the photo attack can be effectively resisted, and the security of the recognition can be effectively improved. The image can be avoided by performing matching detection by using the current face image whose face deflection angle is smaller than the preset angle threshold. The recognition error caused by the excessive deflection angle of the face in the face improves the accuracy of recognition.

The detailed descriptions of the following embodiments are not intended to limit the specific implementation order.

FIG. 1A is a diagram of an application environment in which an identity recognition method operates in an embodiment. As shown in FIG. 1A, the application environment includes a terminal 110 and a server 120, wherein the terminal 110 and the server 120 communicate via a network.

The terminal 110 can be a smartphone, a tablet, a notebook, a desktop computer, etc., but is not limited thereto. When the terminal 110 recognizes that the object to be identified is a living body, the current face image of the object to be recognized may be acquired from the server 120, and the current face image is transmitted to the terminal 110. The terminal 110 may further determine whether the face deflection angle in the current face image is less than a preset angle threshold, when the face deflection angle is less than the preset angle threshold, and the current face image of the object to be identified matches the registered face image, The terminal 110 considers that the identity of the object to be identified is successful.

In one embodiment, the internal structure of terminal 110 in FIG. 1A is as shown in FIG. 1B, which includes a processor, memory, network interface, input device, and display screen connected by a system bus. Wherein, the memory comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program that, when executed by the processor, causes the processor to implement the identification method. The internal memory can also store a computer program that, when executed by the processor, causes the processor to perform an identification method. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touchpad provided on the computer device casing, and It can be an external keyboard, trackpad or mouse.

In one embodiment, the internal structure of server 120 in FIG. 1A is as shown in FIG. 1C, which includes a processor, memory, and network interface connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device can store an operating system, a database, and computer readable instructions. The computer readable instructions, when executed, may cause the processor to perform an identification method, the database for storing data, such as storing a current face image of the object to be identified. The processor of the server 120 is used to provide computing and control capabilities to support the operation of the entire server 120. The network interface of the server 120 is used to communicate with the external terminal 110 via a network connection, such as sending the current face image of the object to be identified to the terminal 110, and the like. The structure shown in FIG. 1B or FIG. 1C is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation of a terminal or a server to which the solution of the present application is applied. The specific server may include a comparison diagram. More or fewer components are shown, or some components are combined, or have different component arrangements. It will be understood by those skilled in the art that the structure shown in FIG. 1B or FIG. 1C is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on a server to which the solution of the present application is applied, and a specific server. More or fewer components than those shown in the figures may be included, or some components may be combined, or have different component arrangements. This embodiment will be described from the perspective of an identity recognition device, as shown in FIG. 2, and is applied to a terminal or a server in the application environment, and includes the following steps:

Step 201, it is determined whether the object to be identified is a living body, if it is a living body, step S202 is performed, otherwise, step 206 is performed;

The identification method of the embodiment can be used in the occasions where identification is required, such as gates, access control, and security supervision. Specifically, when the object to be identified is to pass through the gate, the door, and the security zone, it is possible to identify whether the object to be identified is a living body.

A method of identifying whether the object to be identified is a living body, such as an action command detection method, a visible light detection method, a thermal infrared detection method, or the like.

The motion instruction detection method may, for example, generate an action instruction prompt (such as blinking, nodding, shaking, turning left, right turning, etc.), and determining whether the action made by the object to be identified matches the generated action prompt instruction, and if it matches, determining The object to be identified is a living body.

The visible light detecting method may, for example, use an visible light camera to collect an image of an object to be recognized, detect whether a face is imaged in the collected image, and if the face is imaged, determine whether the object to be identified is a living body; or extract a facial feature in the collected image. Point (such as eyebrow, eye, nose, mouth), compare the extracted face feature points with the face feature points of the visible light template image stored in the database, if the feature point matching degree is higher than a preset value, Determine that the object to be identified is a living body.

The thermal infrared detection method, for example, can use an infrared camera to collect an image of an object to be identified, detect whether a face is imaged in the captured image, and if the face is imaged, determine that the object to be identified is a living body; or extract the same in the captured image. The temperature line feature compares the extracted isotherm feature with the same-temperature feature of the thermal infrared template image stored in the database. If the matching degree of the same-temperature feature is higher than a preset value, the object to be identified is determined to be Living body.

The motion command detection can ensure that the detected object is dynamically changed. The visible light detection and the thermal infrared detection can distinguish whether the detected object is a video object or a real object. Therefore, in this embodiment, the above three methods can be combined for living body recognition. At the same time, the motion command detection method, the visible light detection method, and the thermal infrared detection method are used for detection. When the detection results of the above three detection methods are all living bodies, the object to be identified is determined to be a living body, thereby improving the accuracy of the living body recognition.

Step 202: Acquire a current face image of the object to be identified.

Specifically, the current face image of the object to be recognized may be acquired by the camera module of the camera. The camera device may be a camera, a camera, a camera, etc., and after acquiring the current face image, the face in the current face image may be detected. Deflection angle, the specific detection method can be as follows:

The key points of the face in the current face image are located; the key points of the face are generally points with significant features on the face of the person, for example, the inner eye point, the nose point, and the two corner points of the two eyes.

The face deflection angle in the current face image is determined according to the coordinates of the located key points. Since there is a certain proportional relationship between various parts of the human face, there is a specific correspondence between the key points of the face in the extracted frontal face image. Obtaining a correspondence between the located key points according to the coordinates of the key points that are located, and comparing the correspondence between the located key points and the key points in the frontal face image, The face deflection angle in the current face image is determined.

Step 203: Determine whether the face deflection angle in the current face image is less than a preset angle threshold. If it is less, perform step 204. Otherwise, return to step 202 to re-acquire the current face image of the object to be identified.

If the face deflection angle in the current face image is less than the preset angle threshold, the current face image is available; if the face deflection angle in the current face image is not less than the preset angle threshold, the current face is If the image is not available, the current face image of the object to be identified may be retrieved. When reacquiring, the object to be identified may be prompted to be deflected or moved according to an instruction to quickly obtain a face image of a suitable angle.

Step 204, detecting whether the current face image of the object to be identified matches the registered face image, if yes, step S205 is performed, otherwise, step 206 is performed;

The registered face image refers to the face image provided by the object to be recognized at the time of registration.

Specifically, the current face image and the face feature information in the registered face image, the face feature information such as the eyebrow, the eye, the nose, the mouth, the face, and the like may be extracted, the related information such as the shape, the size, and the relative information. Location, color, etc. The face information is compared one by one, and the matching degree between the current face image and the registered face image is obtained according to the comparison result. If the matching degree is greater than the preset matching degree threshold, the current face image and the registered face image are considered as match.

Step S205, the identity recognition of the object to be identified is successful;

When the identity of the object to be identified is successful, further operations, such as opening a gate, accessing, etc., may be performed.

Step 206: The identity recognition of the object to be identified fails.

When the identification of the object to be identified fails, the object to be identified is prohibited from passing through the gate, the door, and the like. Further, an alarm message can be generated and sent to the relevant manager.

In this embodiment, when the object to be identified is identified, it is first identified whether the object to be identified is a living body, which can effectively resist photo attacks and improve the security of the recognition; when the object to be identified is a living body, obtain the to-be-identified The current face image of the object is only matched when the face deflection angle in the current face image of the acquired object to be recognized is less than the preset angle threshold, so that the face deflection angle in the image can be avoided. Large identification errors lead to improved recognition accuracy.

The method described in the foregoing embodiment is further described in detail in the embodiment. As shown in FIG. 3, the identity identification method in this embodiment includes the following steps:

Step 301: Obtain identification information of an object to be identified.

Before performing step 301, the identity recognition apparatus of this embodiment can also register the object to be identified. The specific registration process may include: collecting identification information of the object to be identified and a registered face image, storing the identification information of the object to be identified and the registered face image in a database, and forming an identifier for carrying the object to be identified for the object to be identified The Near Field Communication (NFC) card of the information, the identification information of the object to be identified may be the name, number, and work number of the object to be identified.

When the object to be identified enters the identification area, the identification device may obtain the identification information of the object to be identified, and the specific acquisition method may be: acquiring the identification information of the object to be identified from the NFC card of the object to be identified. For example, after the object to be identified enters the identification area, the NFC card of the NFC card can be placed on the NFC sensor module of the identity recognition device, and the NFC sensor module reads the identification information of the object to be identified stored in the NFC card. Acquisition of identification information of the object to be identified.

In addition, the identification device may provide an information input window, and the object to be identified may input its own identification information in the information input window, and the identity recognition device acquires its own identification information input by the object to be identified. In this way, the identification can be continued even if the NFC card of the object to be identified is forgotten or lost.

Step 302, detecting whether there is identification information of the object to be identified in the database, if yes, executing step 303, otherwise, performing step 309;

Step 303: Extract a registered face image from the database according to the identification information of the object to be identified.

Step 304: Identify whether the object to be identified is a living body;

Specifically, in the embodiment, the motion instruction detection method, the visible light detection method, and the thermal infrared detection method can be simultaneously used for detecting and identifying. When the detection results of the above three detection methods are all living bodies, determining that the object to be identified is a living body, Improve the accuracy of living recognition.

Step 305: Acquire a current face image of the object to be identified.

Specifically, the current face image of the object to be identified may be acquired by the camera module of the identity recognition device. The camera module may be, for example, a camera, a camera, a camera, etc., after acquiring the current face image, the camera image may be detected in the current face image. The angle of deflection of the face can be as follows:

The key points of the face in the current face image are located; the key points of the face are generally points with significant features on the face of the person, for example, the inner eye point, the nose point, and the two corner points of the two eyes.

The face deflection angle in the current face image is determined according to the coordinates of the located key points. Since there is a certain proportional relationship between various parts of the human face, there is a specific correspondence between the key points of the face in the extracted frontal face image. Obtaining a correspondence between the located key points according to the coordinates of the key points that are located, and comparing the correspondence between the located key points and the key points in the frontal face image, The face deflection angle in the current face image is determined.

Step 306, determining whether the face deflection angle in the current face image is less than a preset angle threshold, if less, step 307 is performed, otherwise, step 309 is performed;

The preset angle threshold can be obtained by random forest algorithm when registering. The specific acquisition process can be seen in Figure 4a and Figure 4b, including the following steps:

Step 401: Obtain a sample set of an object to be identified.

In a specific implementation, when the object to be identified is registered, a plurality of face images of the object to be identified are collected by the camera module of the identity recognition device, and a face deflection angle in each face image is obtained, and one of the objects to be identified is acquired. The face image and the corresponding face deflection angle are taken as one sample, and a large number of samples constitute a sample set of the object to be identified.

Step 402: Mark each sample to generate a sample label of each sample;

The specific marking method is, for example, detecting whether the face image in each sample matches the registered face image; marking the sample corresponding to the matched face image as a positive sample, and marking the sample corresponding to the unmatched face image Is a negative sample. Positive samples can be identified by the value "1" and negative samples can be represented by the value "0".

Step 403: Randomly extract a preset number of samples from the sample set to form a plurality of training sets;

The number of training sets and the number of samples included in the training set can be set according to actual needs. For example, it can be set according to factors such as the computing power of the identification device and the number of samples in the sample set. If each training set includes M samples, the sample labels for each of the training sets and the training set can be as shown in Table 1:

Sample number	Face image	Face deflection angle	Sample label
1	P1		D1	0
2	P2	D2	1
...	...	...	...
M	PM	DM	1

Table 1

Step 404: Generate a corresponding decision tree according to each training set.

Taking the face deflection angle as a splitting feature, the splitting condition is determined according to the face deflection angle included in each training set and the sample label of the corresponding sample, and the corresponding decision tree is generated according to the splitting condition. A training set correspondingly generates a decision tree. For example, as shown in FIG. 4b, when there are N training sets, N decision trees are generated.

The plurality of decision trees generated by steps 401 to 404 constitute a random forest.

Step 405: Perform prediction on each sample in the sample set by using multiple decision trees to obtain a prediction result.

When predicting any one sample, each decision tree outputs a prediction result for the sample, and N decision trees will output N prediction results, and the prediction result may be positive (image matching success) or negative (image mismatch) ), based on the prediction results of all the decision trees on the sample, the probability that the sample is a positive sample can be determined. For example, 10 decision trees are generated. The prediction results of the 9 decision trees are positive for the sample, and the remaining one decision tree is negative for the sample. The probability that the sample is a positive sample is 0.9.

Using the generated multiple decision trees to predict all samples in the sample set will give the probability that each sample is a positive sample.

Step 406: Determine a preset angle threshold according to the prediction result of each sample.

In a specific implementation, the sample with the highest probability of the positive sample in the sample set (ie, the sample with the most positive prediction result) may be determined, and the face deflection angle in the sample with the highest probability of the positive sample is taken as the pre-predetermined Set the angle threshold.

In some embodiments, steps 401-406 may be repeated to determine different preset angle thresholds for different objects to be identified to further improve the accuracy of the recognition. When a new object is registered, steps 401 to 406 may be repeated to determine a preset angle threshold for the new object.

In fact, steps 401-406 use a random forest algorithm to obtain a preset angle threshold. In addition, a certain number of samples may be extracted from the sample set to form a test set. After generating a random forest (multiple decision trees) in step 404, the test set may be used to test the prediction accuracy of the random forest, if the prediction accuracy does not satisfy the accuracy. If required, the training set can be reconstructed and a random forest generated until the generated random forest meets the accuracy requirements.

Step 307, detecting whether the current face image of the object to be identified matches the registered face image, if yes, step 308 is performed, otherwise, step 309 is performed;

Step 308: The identity of the object to be identified is successfully identified.

When the identification of the object to be identified is successful, further operations, such as opening a gate, an access control, etc., may be performed to allow the object to be identified to pass.

Step 309: The identity of the object to be identified fails.

When the identification of the object to be identified fails, the object to be identified is prohibited from passing through the gate, the door, etc., and further, the alarm information may be generated, and the alarm information is sent to the relevant management personnel.

In this embodiment, when the object to be identified is identified, it is possible to identify whether the object to be identified is a living body, which can effectively resist photo attacks and improve the security of the recognition; when the object to be identified is a living body, obtain the to-be-identified The current face image of the object is only matched when the face deflection angle in the current face image of the acquired object to be recognized is less than the preset angle threshold, so that the face deflection angle in the image can be avoided. Large identification errors lead to improved recognition accuracy. In an embodiment, a computer device is also provided. The internal structure of the computer device can be as shown in FIG. 1B or FIG. 1C. The computer device includes an identity recognition device, and each module includes each module. It is implemented in whole or in part by software, hardware or a combination thereof.

In order to better implement the above method, the present application further provides an identity recognition apparatus. As shown in FIG. 5, the apparatus of this embodiment includes: an identification unit 501, a first acquisition unit 502, a determination unit 503, and a first detection. Unit 504 is as follows:

The identifying unit 501 is configured to identify whether the object to be identified is a living body;

The first obtaining unit 502 is configured to acquire a current face image of the object to be identified when the object to be identified is a living body;

a determining unit 503, configured to determine whether a face deflection angle in the current face image is less than a preset angle threshold;

The first detecting unit 504 is configured to detect, when the face deflection angle in the current face image is less than a preset angle threshold, whether the current face image of the object to be identified matches the registered face image, and if yes, Then, the identity of the object to be identified is successful.

In some embodiments, as described in FIG. 6, the apparatus further includes:

a second acquisition unit 505, configured to acquire a sample set of the object to be identified, where each sample of the sample set includes a face image of the object to be identified and a corresponding face deflection angle;

The constituting unit 507 is configured to randomly extract a preset number of samples from the sample set to form a plurality of training sets;

a generating unit 508, configured to generate a corresponding decision tree according to each training set;

a prediction unit 509, configured to predict, by using a plurality of decision trees, each sample in the sample set to obtain a prediction result;

The determining unit 510 is configured to determine the preset angle threshold according to the prediction result of each sample.

In some embodiments, as described in FIG. 6, the apparatus further includes:

A marking unit 506 is configured to mark each sample to generate a sample label for each sample.

In some embodiments, the marking unit 506 is specifically configured to:

Detecting whether the face image in each sample matches the registered face image, marking the sample corresponding to the matched face image as a positive sample, and marking the sample corresponding to the unmatched face image as a negative sample.

In some embodiments, the determining unit 510 is specifically configured to:

Determining the sample with the highest probability of the positive sample as the positive sample, and using the face deflection angle in the sample with the highest probability of the positive sample as the preset angle threshold.

In some embodiments, as shown in FIG. 6, the apparatus further includes:

The second detecting unit 512 is configured to detect whether the identifier information of the object to be identified exists in the database;

The extracting unit 513 is configured to extract the registered face image from the database according to the identification information of the object to be identified when the identification information of the object to be identified exists in the database.

In some embodiments, as shown in FIG. 6, the apparatus further includes:

The third obtaining unit 511 is configured to acquire the identification information of the object to be identified carried in the short-range wireless communication NFC card of the object to be identified, or obtain the identification information of the object to be identified input by the object to be identified .

In some embodiments, the identifying unit 501 is specifically configured to:

The action command detection method, the visible light detection method, and the thermal infrared detection method are used to identify whether the object to be identified is a living body.

It should be noted that, when the identity identification device provided by the foregoing embodiment is used for identification, only the division of each functional module is used for example. In an actual application, the function distribution may be completed by different functional modules as needed. The internal structure of the device is divided into different functional modules to perform all or part of the functions described above. In addition, the identity recognition device and the identity identification method provided by the foregoing embodiments are in the same concept, and the specific implementation process is described in detail in the method embodiment, and details are not described herein again.

The device of the present embodiment can identify the object to be identified as a living body by the identification unit, and can effectively resist the photo attack and improve the security of the identification; when the object to be identified is a living body, the first acquiring unit acquires the object to be identified. The current face image is detected by the detecting unit only when the face deflection angle in the current face image of the object to be recognized is less than the preset angle threshold, so that the face deflection angle in the image can be avoided. Large identification errors lead to improved recognition accuracy.

Correspondingly, the embodiment of the present application further provides an identification device. As shown in FIG. 7, the device may include a radio frequency (RF) circuit 601, and a memory 602 including one or more computer readable storage media. The input unit 603, the display unit 604, the sensor 605, the audio circuit 606, the Wireless Fidelity (WiFi) module 607, the processor 608 including one or more processing cores, and the power supply 609 and the like. It will be understood by those skilled in the art that the device structure illustrated in FIG. 7 does not constitute a limitation to the device, and may include more or less components than those illustrated, or some components may be combined, or different component arrangements. among them:

The RF circuit 601 can be used for receiving and transmitting signals during the transmission or reception of information or during a call. Specifically, after receiving the downlink information of the base station, the downlink information is processed by one or more processors 608. In addition, the data related to the uplink is sent to the base station. . Generally, the RF circuit 601 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM), a transceiver, a coupler, and a low noise amplifier (LNA, Low Noise Amplifier), duplexer, etc. In addition, the RF circuit 601 can also communicate with the network and other devices through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), and Code Division Multiple Access (CDMA). , Code Division Multiple Access), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), e-mail, Short Messaging Service (SMS), and the like.

The memory 602 can be used to store software programs and modules, and the processor 608 executes various functional applications and data processing by running software programs and modules stored in the memory 602. The memory 602 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the device (such as audio data, phone book, etc.). Moreover, memory 602 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 602 may also include a memory controller to provide access to memory 602 by processor 608 and input unit 603.

The input unit 603 can be configured to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls. In particular, in one particular embodiment, input unit 603 can include a touch-sensitive surface as well as other input devices. Touch-sensitive surfaces, also known as touch screens or trackpads, collect touch operations on or near the user (such as the user using a finger, stylus, etc., any suitable object or accessory on a touch-sensitive surface or touch-sensitive Operation near the surface), and drive the corresponding connecting device according to a preset program. Alternatively, the touch sensitive surface may include two parts of a touch detection device and a touch controller. Wherein, the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information. The processor 608 is provided and can receive commands from the processor 608 and execute them. In addition, touch-sensitive surfaces can be implemented in a variety of types, including resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch-sensitive surface, the input unit 603 can also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.

Display unit 604 can be used to display information entered by the user or information provided to the user, as well as various graphical user interfaces of the terminal, which can be composed of graphics, text, icons, video, and any combination thereof. The display unit 604 can include a display panel. Alternatively, the display panel can be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch-sensitive surface can cover the display panel, and when the touch-sensitive surface detects a touch operation thereon or nearby, it is transmitted to the processor 608 to determine the type of the touch event, and then the processor 608 displays the type according to the type of the touch event. A corresponding visual output is provided on the panel. Although in FIG. 7, the touch-sensitive surface and display panel are implemented as two separate components to perform input and input functions, in some embodiments, the touch-sensitive surface can be integrated with the display panel to implement input and output functions.

The device may also include at least one type of sensor 605, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel according to the brightness of the ambient light, and the proximity sensor may turn off the display panel and/or the backlight when the device moves to the ear. . As a kind of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity. It can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the terminal can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.

The audio circuit 606, the speaker, and the microphone provide an audio interface between the user and the terminal. The audio circuit 606 can transmit the converted electrical signal of the audio data to the speaker, and convert it into a sound signal output by the speaker; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 606 and then converted. The audio data is then processed by the audio data output processor 608, sent via RF circuitry 601 to, for example, another device, or the audio data is output to memory 602 for further processing. The audio circuit 606 may also include an earbud jack to provide communication of the peripheral earphones to the device.

WiFi is a short-range wireless transmission technology, and the device can help users to send and receive emails, browse web pages, and access streaming media through the WiFi module 607, which provides wireless broadband Internet access for users. Although FIG. 7 shows the WiFi module 607, it can be understood that it does not belong to the essential configuration of the device, and may be omitted as needed within the scope of not changing the essence of the application.

Processor 608 is the control center of the device, interconnecting various portions of the entire device using various interfaces and lines, executing or executing software programs and/or modules stored in memory 602, and invoking data stored in memory 602, executing The various functions of the terminal and processing data to monitor the device as a whole. Optionally, the processor 608 may include one or more processing cores; preferably, the processor 608 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like. The modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 608.

The device also includes a power source 609 (such as a battery) that supplies power to the various components. Preferably, the power source can be logically coupled to the processor 608 through a power management system to manage functions such as charging, discharging, and power management through the power management system. The power supply 609 may also include any one or more of a DC or AC power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

Although not shown, the device may further include a camera, a Bluetooth module, and the like, and details are not described herein again. Specifically, in this embodiment, the processor 608 in the device loads the executable file corresponding to the process of one or more application programs into the memory 602 according to the following instructions, and is executed by the processor 608 to be stored in the memory. The application in 602 to implement various functions:

Identify whether the object to be identified is a living body;

Obtaining a current face image of the object to be identified if the object to be identified is a living body;

Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

If the threshold value is smaller than the preset angle threshold, it is detected whether the current face image of the object to be identified matches the registered face image. If the image is matched, the identity of the object to be identified is successfully identified.

In some embodiments, the processor 608 is further configured to perform the following steps before identifying whether the object to be identified is a living body:

Obtaining a sample set of the object to be identified, where each sample of the sample set includes a face image of the object to be identified and a corresponding face deflection angle;

Randomly extracting a preset number of samples from the sample set to form a plurality of training sets;

Generating a corresponding decision tree according to each training set;

Predicting each sample in the sample set using a plurality of decision trees to obtain a prediction result;

The preset angle threshold is determined based on the prediction result of each sample.

In some embodiments, after acquiring the sample set of the object to be identified, the processor 608 is further configured to perform the following steps:

Each sample is labeled to generate a sample label for each sample.

In some embodiments, when each sample is tagged to generate a sample tag for each sample, the processor 608 is specifically configured to perform the following steps:

Detecting whether a face image in each sample matches the registered face image;

The samples corresponding to the matched face images are marked as positive samples, and the samples corresponding to the unmatched face images are marked as negative samples.

In some embodiments, when determining the preset angle threshold according to the prediction result of each sample, the processor 608 is specifically configured to perform the following steps:

Determining the sample with the highest probability of the positive sample as the positive sample, and using the face deflection angle in the sample with the highest probability of the positive sample as the preset angle threshold.

In some embodiments, the processor 608 is further configured to perform the following steps before identifying whether the object to be identified is a living body:

Detecting whether the identification information of the object to be identified exists in the database;

And if the identifier information of the object to be identified exists in the database, extracting the registered face image from the database according to the identifier information of the object to be identified.

In some embodiments, before detecting whether the identification information of the object to be identified exists in the database, the processor 608 is further configured to perform the following steps:

Acquiring the identification information of the object to be identified carried in the short-range wireless communication NFC card of the object to be identified; or

Obtaining identification information of the object to be identified input by the object to be identified.

In some embodiments, when identifying whether the object to be identified is a living body, the processor 608 is specifically configured to perform the following steps:

The action command detection method, the visible light detection method, and the thermal infrared detection method are used to identify whether the object to be identified is a living body.

The living body identification device of the embodiment first identifies whether the object to be identified is a living body when the object to be identified is identified, so that the photo attack can be effectively defended and the security of the identification is improved; when the object to be identified is a living body, Acquiring the current face image of the object to be identified, and performing matching detection of the image only when the face deflection angle in the current face image of the acquired object to be recognized is less than a preset angle threshold, thereby avoiding the face in the image The recognition error caused by the excessive deflection angle improves the accuracy of recognition.

The embodiment of the present application further provides a storage device, where the storage device stores a computer program, and when the computer program runs on a computer, causes the computer to perform the video transcoding method in any of the above embodiments, such as: Determining whether the object to be identified is a living body; if the object to be identified is a living body, acquiring a current face image of the object to be identified; determining whether a face deflection angle in the current face image is less than a preset angle threshold; If the threshold value is smaller than the preset angle threshold, it is detected whether the current face image of the object to be identified matches the registered face image. If the image is matched, the identity of the object to be identified is successfully identified.

It should be understood that the various steps in the various embodiments of the present application are not necessarily performed in the order indicated by the steps. Except as explicitly stated herein, the execution of these steps is not strictly limited, and the steps may be performed in other orders. Moreover, at least some of the steps in the embodiments may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be executed at different times, and the execution of these sub-steps or stages The order is also not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of the other steps.

One of ordinary skill in the art can understand that all or part of the process of implementing the above embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a non-volatile computer readable storage medium. Wherein, the program, when executed, may include the flow of an embodiment of the methods as described above. Any reference to a memory, storage, database or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of formats, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization chain. Synchlink DRAM (SLDRAM), Memory Bus (Rambus) Direct RAM (RDRAM), Direct Memory Bus Dynamic RAM (DRDRAM), and Memory Bus Dynamic RAM (RDRAM).

In the above embodiments, the descriptions of the various embodiments are different, and the details that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

It should be noted that, for the identity identification method in the embodiment of the present application, an ordinary decision maker in the field can understand all or part of the process of implementing the identity identification method in the embodiment of the present application, which can be completed by using a computer program to control related hardware. The computer program may be stored in a computer readable storage medium, such as in a memory of the electronic device, and executed by at least one processor in the electronic device, and may include, for example, an identification method during execution. The flow of the embodiment. The storage medium may be a magnetic disk, an optical disk, a read only memory, a random access memory, or the like.

For the identity recognition device of the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated module, if implemented in the form of a software functional module and sold or used as a standalone product, may also be stored in a computer readable storage medium, such as a read only memory, a magnetic disk or an optical disk, etc. .

The foregoing describes an identity identification method, apparatus, and storage device provided by the embodiments of the present application. The specific examples are used to describe the principles and implementation manners of the present application. The description of the above embodiments is only for helping. The method of the present application and its core idea are understood; at the same time, those skilled in the art, according to the idea of the present application, will have some changes in the specific implementation manner and application scope. In summary, the content of this specification should not be It is understood to be a limitation on the present application.

Claims (24)

1. An identification method, comprising:

   The computer device identifies whether the object to be identified is a living body;

   Obtaining a current face image of the object to be identified when the computer device identifies that the object to be identified is a living body;

   Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

   When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.
2. The method according to claim 1, wherein before the computer device identifies whether the object to be identified is a living body, the method further comprises:

   The computer device acquires a sample set of the object to be identified, and each sample of the sample set includes a face image of the object to be identified and a corresponding face deflection angle;

   The computer device randomly extracts a preset number of samples from the sample set to form a plurality of training sets;

   The computer device generates a corresponding decision tree according to each training set;

   The computer device uses a plurality of decision trees to predict each sample in the sample set to obtain a prediction result;

   The computer device determines the preset angle threshold based on a prediction result of each sample.
3. The method according to claim 2, further comprising: after the computer device acquires the sample set of the object to be identified, further comprising:

   When the computer device detects that the face image in each sample matches the registered face image, marking the sample corresponding to the matched face image as a positive sample;

   When the computer device detects that the face image in each sample does not match the registered face image, the sample corresponding to the unmatched face image is marked as a negative sample.
4. The method according to claim 3, wherein the determining, by the computer device, the preset angle threshold according to a prediction result of each sample comprises:

   The computer device determines a sample having the highest probability that the sample set is a positive sample, and uses a face deflection angle in the sample having the highest probability of the positive sample as the preset angle threshold.
5. The method according to any one of claims 1 to 4, further comprising: before the computer device identifies whether the object to be identified is a living body, further comprising:

   When the computer device detects that the identification information of the object to be identified exists in the database, the registered face image of the object to be identified is extracted from the database according to the identification information of the object to be identified.
6. The method according to claim 5, further comprising: before the detecting, by the computer device, the identification information of the object to be identified in the database,

   The computer device acquires the identification information of the object to be identified carried in the short-range wireless communication NFC card of the object to be identified.
7. The method according to claim 5, further comprising: before the detecting, by the computer device, the identification information of the object to be identified in the database,

   The computer device acquires identification information of the object to be identified input by the object to be identified.
8. The method according to claim 1, wherein the computer device identifies whether the object to be identified is a living body, comprising:

   The computer device uses an action command detection method, a visible light detection method, and a thermal infrared detection method to identify whether the object to be identified is a living body.
9. A computer device comprising a memory and a processor, the memory storing computer readable instructions, the computer readable instructions being executed by the processor such that the processor performs the following steps:

   Identify whether the object to be identified is a living body;

   Obtaining a current face image of the object to be identified when the object to be identified is identified as a living body;

   Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

   When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.
10. The computer apparatus according to claim 9, wherein said computer readable instructions further cause said processor to perform the following steps before identifying whether the object to be identified is a living body:

    Obtaining a sample set of the object to be identified, where each sample of the sample set includes a face image of the object to be identified and a corresponding face deflection angle;

    Randomly extracting a preset number of samples from the sample set to form a plurality of training sets;

    Generating a corresponding decision tree according to each training set;

    Predicting each sample in the sample set using a plurality of decision trees to obtain a prediction result;

    The preset angle threshold is determined based on the prediction result of each sample.
11. The computer apparatus according to claim 10, wherein, after acquiring the sample set of the object to be identified, the computer readable instructions further cause the processor to perform the following steps:

    When detecting that the face image in each sample matches the registered face image, marking the sample corresponding to the matched face image as a positive sample;

    When it is detected that the face image in each sample does not match the registered face image, the sample corresponding to the unmatched face image is marked as a negative sample.
12. The computer device according to claim 11, wherein the determining the preset angle threshold according to the prediction result of each sample comprises:

    Determining the sample with the highest probability of the positive sample as the positive sample, and using the face deflection angle in the sample with the highest probability of the positive sample as the preset angle threshold.
13. The computer device according to any one of claims 9 to 12, wherein the computer readable instructions further cause the processor to perform the following steps before identifying whether the object to be identified is a living body:

    When the identification information of the object to be identified exists in the detection database, the registered face image of the object to be identified is extracted from the database according to the identification information of the object to be identified.
14. The computer apparatus according to claim 13, wherein said computer readable instructions further cause said processor to perform the following steps before detecting identification information of said object to be identified in said database:

    Obtaining identification information of the object to be identified carried in the short-range wireless communication NFC card of the object to be identified.
15. The computer apparatus according to claim 13, wherein said computer readable instructions further cause said processor to perform the following steps before detecting identification information of said object to be identified in said database:

    Obtaining identification information of the object to be identified input by the object to be identified.
16. The computer device according to claim 9, wherein the identifying whether the object to be identified is a living body comprises:

    The action command detection method, the visible light detection method, and the thermal infrared detection method are used to identify whether the object to be identified is a living body.
17. One or more non-volatile storage media storing computer readable instructions, when executed by one or more processors, cause one or more processors to perform the following steps:

    Identify whether the object to be identified is a living body;

    Obtaining a current face image of the object to be identified when the object to be identified is identified as a living body;

    Determining whether a face deflection angle in the current face image is less than a preset angle threshold;

    When the face deflection angle is smaller than the preset angle threshold, and the current face image of the object to be recognized matches the registered face image, the identity recognition of the object to be identified is successful.
18. The storage medium according to claim 17, wherein said computer readable instructions further cause said processor to perform the following steps before identifying whether the object to be identified is a living body:

    Obtaining a sample set of the object to be identified, where each sample of the sample set includes a face image of the object to be identified and a corresponding face deflection angle;

    Randomly extracting a preset number of samples from the sample set to form a plurality of training sets;

    Generating a corresponding decision tree according to each training set;

    Predicting each sample in the sample set using a plurality of decision trees to obtain a prediction result;

    The preset angle threshold is determined based on the prediction result of each sample.
19. The storage medium according to claim 18, wherein, after acquiring the sample set of the object to be identified, the computer readable instructions further cause the processor to perform the following steps:

    When detecting that the face image in each sample matches the registered face image, marking the sample corresponding to the matched face image as a positive sample;

    When it is detected that the face image in each sample does not match the registered face image, the sample corresponding to the unmatched face image is marked as a negative sample.
20. The storage medium according to claim 19, wherein the determining the preset angle threshold according to the prediction result of each sample comprises:

    Determining the sample with the highest probability of the positive sample as the positive sample, and using the face deflection angle in the sample with the highest probability of the positive sample as the preset angle threshold.
21. The storage medium according to any one of claims 17 to 20, wherein the computer readable instructions further cause the processor to perform the following steps before identifying whether the object to be identified is a living body:

    When the identification information of the object to be identified exists in the detection database, the registered face image of the object to be identified is extracted from the database according to the identification information of the object to be identified.
22. The storage medium according to claim 21, wherein said computer readable instructions further cause said processor to perform the following steps before detecting whether said identification information of said object to be identified exists in said database:

    Obtaining identification information of the object to be identified carried in the short-range wireless communication NFC card of the object to be identified.
23. The storage medium according to claim 21, wherein said computer readable instructions further cause said processor to perform the following steps before detecting whether said identification information of said object to be identified exists in said database:

    Obtaining identification information of the object to be identified input by the object to be identified.
24. The storage medium according to claim 17, wherein the identifying whether the object to be identified is a living body comprises:

    The action command detection method, the visible light detection method, and the thermal infrared detection method are used to identify whether the object to be identified is a living body.

Images