TWM615971U - System of identifying living body by recognizing actions of image - Google Patents

Abstract

A system that recognizes the actions in the image to determine whether the target is a living body. It determines whether a plurality of designated actions including facial and hand movements are identified and whether the target in the target image completes the designated action in sequence, and recognizes according to the living body As a result, the technical means to determine whether the identification target is a living body can confirm whether the other party is a living body during an online meeting, and achieve the technical effect of increasing the security of the online meeting.

Description

A system that recognizes actions in images to determine whether the target is a living body

A living body recognition system, especially a system that recognizes actions in images to determine whether the target is a living body.

With the advancement of the Internet and related technologies, many services that needed to be identified and handled in person in the past can also be completed through the Internet. However, some services, such as account opening and insurance, are still restricted by relevant domestic laws and regulations due to the lack of rigorous methods of identity verification through the Internet. The identification target cannot complete the account opening and insurance online.

In terms of account opening, although it is currently possible to open a digital account online through online banking or mobile banking, the relevant laws and regulations require that the level of the digital account opened is different depending on the method of identity verification, that is, the lower level. Compared with a digital account opened after a more complete identity confirmation, a digital account has many restrictions, for example, some transactions cannot be executed or the amount of money that can be used during the transaction is lower. If you want to open a digital account with more complete functions, it is still the same as opening a general account. The bank’s service personnel need to confirm the identity of the account holder at the counter, which is usually to confirm whether the certificate provided by the account holder is indeed held by the account holder. Have.

In addition, there are similar situations during the insurance application process, that is, the relevant laws and regulations require that the insured person must face-to-face with the salesperson, and the salesperson shall explain the insurance content to the insured person and confirm the identity of the insured person based on the documents provided by the insured person. , Wait for the note from the insurance company to complete the insurance.

In fact, in some cases, for example, when an infectious disease is severe, the account holder or the insured is not suitable for going to the bank counter or meeting with the insurance clerk. It is more suitable for opening an account or applying for insurance through the Internet. For this, there are some The bank/insurance company provides the account opening/insurance method discussed online. Although the two rules of remote and meeting can be met at the same time, people who are interested can still fake the images during the meeting with the bank service staff/insurance clerk, for example, by playing pre-recorded images, which makes it impossible to confirm even through the online conversation. Whether the account holder/insurant is a real person.

In summary, it can be seen that there has been a problem in the prior art that it is impossible to confirm whether the other party is a real person during online meetings for a long time. Therefore, it is necessary to propose improved technical means to solve this problem.

In view of the problem of the prior art that it is impossible to judge whether the identification target is the document holder from the photo on the certificate, this creation discloses a system for identifying the action in the image to determine whether the target is a living body. Among them: the identification disclosed in this creation The system for judging whether the target is a living body by the action in the image at least includes: an action selection module for determining a predetermined number of specified actions; an image capturing module for capturing the number of faces that include a recognition target A target image; a living body recognition module for judging from the target images whether the recognition target has completed the specified actions in sequence and generating a corresponding living body recognition result; the result judgment module is used for the living body recognition result Determine whether the recognition target is recognized by the living body.

The system for identifying the action in the image to determine whether the target is a living body disclosed in the present invention at least includes: a client and a server. The client further includes an action selection module for determining a predetermined number of specified actions; image capture Module for capturing multiple items including a face of a recognition target The target image; the living body identification module is used to determine from the target images whether the identification target completes the specified actions in sequence and generates a corresponding living body identification result; the result judgment module; the server provides the client connection, It also includes a servo communication module and an image detection module. The servo communication module is used to receive the target image sent by the client; the image detection module is used to determine the image depth and/or image information of the target image, and based on the image The depth and/or image information generates the image judgment result, and the servo communication module is used to send the image detection result including or indicating the image judgment result to the client, so that the result judgment module judges whether the identification target is based on the living body recognition result and the image detection result Through living body identification.

The system disclosed in this creation is as above. The difference between this creation and the previous technology is that this creation determines whether multiple designated actions including facial and hand motions are determined and whether the recognition target in the target image completes the designated action in sequence. And according to the result of living body identification, it is judged whether the identification target is a living body, so as to solve the problems of the previous technology, and can achieve the technical effect of increasing the security of the online meeting.

100: client

101: Processing Module

110: Image capture module

120: Action selection module

130: Living Body Recognition Module

140: display module

150: data acquisition module

160: feature acquisition module

180: result judgment module

190: Customer Communication Module

200: server

202: trusted host

210: Servo communication module

220: Image comparison module

230: image detection module

240: result generation module

410: Display screen

411: indicator area

412: prompt area

Step 310: The client obtains identification data

Step 320: The client determines a predetermined number of specified actions

Step 321: The client obtains human body characteristics based on the identification data

Step 323: The client decides a designated action that meets the characteristics of the human body

Step 325: The client selects a predetermined number of facial movements and hand movements

Step 327: The client combines facial and hand movements to generate a specified action

Step 330: The client captures a target image containing the face of the recognition target

Step 331: The client determines whether the face of the recognition target is detected

Step 333: The client judges whether the face reaches a certain ratio

Step 335: The client captures the target image

Step 337: The client judges that the identification target has not passed the living body identification

Step 340: The client sends the target image to the server

Step 350: The client judges from the target image whether the identified target completes the specified action in sequence

Step 351: The client performs face recognition and motion detection on the target image

Step 355: According to the face recognition result and the motion detection result, the client judges whether the face and gesture of the recognition target in the target image respectively match the facial motion and hand motion to generate the living body recognition result

Step 360: The client generates a living body recognition result

Step 371: The server obtains a credible image containing the face of the recognition target based on the identification data

Step 373: The server compares the face in the trusted image with the target image and generates an image comparison result

Step 375: The server determines the image depth and/or image information of the target image and generates an image judgment result

Step 379: The server generates and sends the image detection result to the client

Step 391: The client judges whether the identification target passes the living body identification according to the living body identification result

Step 395: The client judges whether the identification target passes the living body identification according to the living body identification result and the image detection result

The first picture is the system architecture diagram of identifying the action in the image to determine whether the target is a living body.

Figure 2 is a schematic diagram of the components of the server mentioned in the creation.

Figure 3A is the flow chart of identifying the action in the image to determine whether the target is a living body.

Figure 3B is a flow chart for generating the specified action mentioned in the creation embodiment.

Figure 3C is the flow chart of generating the identification result mentioned in the creation embodiment.

Fig. 3D is a flow chart of capturing the target image according to the creative embodiment.

Figure 3E is an additional flow chart for determining the designated action mentioned in the creation.

Figure 3F is the flow chart of the creation of the target image through the server to determine whether the target is alive.

Figure 4 is a schematic diagram of the user interface for capturing the target image according to the creative embodiment.

The following will describe the features and implementation methods of this creation in detail with the drawings and embodiments. The content is sufficient to enable any person familiar with relevant skills to easily and fully understand the technical means used in this creation to solve technical problems and implement them accordingly. The achievable effect of this creation.

This creation can request the identification target to make a specified action to determine whether the identification target is a living body.

The specified actions mentioned in this creation can include facial movements and hand movements, where facial movements include but are not limited to turning in a specific direction (such as left and right), raising the head, nodding, blinking, smiling, etc.; hand movements include stretching out The finger and the position of the finger are placed, but this creation is not limited to this. Generally speaking, the position of the finger is usually on the face or around the face, but this creation is not limited to this.

The following first uses the "Picture 1" in this creation to identify the action in the image to determine whether the target is a living body system architecture diagram to illustrate this creation. As shown in "Figure 1", the creative system is applied to the client 100, and includes a processing module 101, an image capture module 110, and an additional display module 140 and a client communication module 190. Among them, the client 100 may be a computing device.

The computing device mentioned in this creation includes but is not limited to one or more processing modules, one or more memory modules, and connecting different hardware components (including memory modules and processing modules) Hardware components such as buses. Through the included multiple hardware components, the computing device can load and execute the operating system, make the operating system run on the computing device, and can also execute software or programs. In addition, the computing device also includes a housing, and each of the above-mentioned hardware components is arranged in the housing.

The bus of the computing device mentioned in this creation can include one or more types, such as data bus, address bus, control bus, and extended function bus ( expansion bus), and/or local bus (local bus). The bus bars of computing devices include but are not limited to Industry Standard Architecture (ISA) bus, Peripheral Component Interconnect (PCI) bus, Video Electronics Standards Association (VESA) Bureau Domain bus, serial universal serial bus (Universal Serial Bus, USB), fast peripheral component interconnection (PCI Express, PCI-E/PCIe) bus, etc.

The processing module of the computing device mentioned in this creation is coupled with the bus. The processing module includes a register group or register space. The register group or register space can be completely set on the processing chip of the processing module, or all or part of it can be set outside the processing chip It is coupled to the processing chip via a dedicated electrical connection and/or via a bus. The processing module can be a central processing unit, a microprocessor or any suitable processing element. If the computing device is a multi-processor device, that is, the computing device includes multiple processing modules, the processing modules included in the computing device are all the same or similar, and they are coupled and communicated through a bus. The processing module can interpret a computer instruction or a series of multiple computer instructions to perform specific operations or operations, such as mathematical operations, logical operations, data comparison, copy/move data, etc., to drive other hardware in the computing device Components or run operating systems or execute various programs and/or modules.

Computing equipment usually also contains one or more chipsets. The processing module of the computing device can be coupled to the chipset or electrically connected to the chipset through a bus. The chipset is composed of one or more integrated circuits (Integrated Circuit, IC), including memory controller and peripheral input and output (I/O) controllers, that is, memory controller and peripheral input and output control The device can be included in one integrated circuit, or it can be implemented using two or more integrated circuits. Chipsets usually provide I/O and memory management functions, as well as multiple general-purpose and/or special-purpose registers, timers, etc., among which the aforementioned general-purpose and/or special-purpose registers and timers can be coupled or One or more processing modules electrically connected to the chipset are accessed or used.

The processing module of the computing device can also access the data in the memory module and the mass storage area installed on the computing device through the memory controller. The above-mentioned memory modules include any type of volatile memory (volatile memory) and/or non-volatile (NVRAM) memory, such as Static Random Access Memory (SRAM) , Dynamic Random Access Memory (DRAM), Read-Only Memory (ROM), Flash memory, etc. The aforementioned mass storage area can include any type of storage device or storage medium, such as hard disk drives, optical discs, flash drives, memory cards, and solid state disks. ,SSD), or any other storage device, etc. In other words, the memory controller can access data in static random access memory, dynamic random access memory, flash memory, hard disk drives, and solid state drives.

The processing module of the computing device can also connect and communicate with peripheral output devices, peripheral input devices, communication interfaces, and GPS receivers and other peripheral devices or interfaces through the peripheral I/O controller via the peripheral I/O bus. The peripheral input device can be any type of input device, such as a keyboard, Mouse, trackball, touchpad, joystick, etc. The peripheral output device can be any type of output device, such as a monitor, printer, etc. The peripheral input device and the peripheral output device can also be the same device, such as a touch screen Wait. The communication interface can include a wireless communication interface and/or a wired communication interface. The wireless communication interface can include support for wireless local area networks (such as Wi-Fi, Zigbee, etc.), Bluetooth, infrared, and Near-field communication (NFC), 3G/4G/5G and other mobile communication network (cellular network) or other wireless data transmission protocol interface, wired communication interface can be Ethernet device, DSL modem, cable modem, asynchronous transmission Mode (Asynchronous Transfer Mode, ATM) device, or optical fiber communication interface and/or components, etc. The processing module can periodically poll various peripheral devices and interfaces, so that the computing device can input and output data through various peripheral devices and interfaces, and can also interact with another computing device with the hardware components described above. To communicate.

In this creation, the processing module 101 in the client 100 can load and execute one or a group of computer instructions stored in the memory module (not shown in the figure) through the bus, and can be generated after the computer instructions are executed. The action selection module 120, the living body recognition module 130, and the result judgment module 180. In some embodiments, the processing module 101 can also generate a data acquisition module 150 and a feature acquisition module 160 after executing computer instructions.

The image capturing module 110 may include elements such as a lens, a photosensitive element, etc. (none of which is shown in the figure). Among them, the lens can let light pass and let the passing light illuminate the photosensitive element, and the photosensitive element can convert the light irradiated on the photosensitive element into an image signal.

The image capturing module 110 is responsible for capturing the target image. The target image captured by the image capturing module 110 includes human faces and gestures. Wherein, the image capturing module 110 can continuously use the image signal output by the photosensitive element as the target image when being driven by the living body recognition module 130 or receiving the coordination message sent by the living body recognition module 130.

The image capturing module 110 can also capture data images. Generally speaking, the data image captured by the image capturing module 110 contains a complete character string or a bar code sufficient to identify the indicated content, but the creation is not limited to this. The image capturing module 110 can continue to use the image signal output by the photosensitive element as a data image when it is driven by the data obtaining module 150 or receiving a cooperative message from the data obtaining module 150.

The image capture module 110 can also determine whether the face of the recognition target is detected within the image capture range, and determine whether the face of the recognition target is detected within the image capture range, and can determine whether the detected face reaches The target image is captured when a certain proportion of the image capturing range.

The action selection module 120 is responsible for determining a predetermined number of specified actions. The number of designated actions determined by the action selection module 120 can be a predetermined value or set through the data acquisition module 150, and there is no special restriction on this creation.

The action selection module 120 can select a facial movement and a hand movement from a pre-established movement database (not shown in the figure), and can combine the selected facial movement and hand movement to generate a specified movement. The action selection module 120 may repeat the above-mentioned process of generating the specified actions until a predetermined number of specified actions are generated.

The living body recognition module 130 is responsible for performing living body recognition according to the specified action generated by the action selection module 120. The living body recognition process performed by the living body recognition module 130 is, for example, the display module 140 prompts the recognition target to complete the first specified action generated in front of the image capturing module 110, and at the same time, it continues to check the image capturing module 110. The captured face recognition and/or motion detection in the instruction image that completes the first specified action to obtain the facial features and gesture features in the instruction image, and based on the facial features and gesture features in the instruction image Determine whether the identification target in the instruction image has completed the specified action. If yes, prompt the identification target to complete the second specified action generated by the display module 140 and repeat the upload The comparison process is described, until the identification target completes all the specified actions correctly, so as to carry out the living body identification. However, the method of living body identification mentioned in this creation is not limited to the above. Among them, the living body recognition module 130 can usually compare the facial features/gesture features in the indicated image with the facial features/gesture features corresponding to the specified action read from the action database to determine whether the identification target has completed the specified action, but This creation is not limited to this.

The living body identification module 130 is also responsible for generating a corresponding living body identification result after performing the living body identification. The living body recognition module 130 can determine that the living body has passed and generate a living body recognition result indicating that the living body has passed the living body recognition when the designated actions generated are completed correctly or the number of consecutively correctly completed designated actions reaches the parameter value; the living body recognition module 130 can also When any specified action generated is not completed correctly or the number of specified actions that are not completed correctly reaches a predetermined value, it is determined that the living body identification has failed and a living body identification result indicating that the living body identification has not passed is generated.

The living body identification module 130 may also accumulate the number of times that the living body identification has not passed, and perform the living body identification again. The living body identification module 130 can generate a living body identification result indicating that the living body identification has not passed when the accumulated number of failures reaches a predetermined value.

The display module 140 can display the data image, the target image, and the instruction image captured by the image capturing module 110 on the display screen of the client 100. The display module 140 can also display prompt messages such as an indicator box and text generated by the data acquisition module 150 on the display screen of the client 100. The display module 140 may also display the judgment result generated by the result judgment module 180 on the display screen of the client 100.

The data acquisition module 150 can acquire identification data. In more detail, the data acquisition module 150 can acquire the identification target's mobile phone number, digital certificate, and financial card information as the identification data.

The data acquisition module 150 can also set the number of specified actions generated by the living body recognition module 130 for living body recognition, and it can also set the number of times that the living body recognition module 130 determines that the specified action needs to be continuously and correctly completed through the living body recognition (ie, the living body recognition module 130 parameter values used for judgment).

The feature obtaining module 160 can obtain the human body feature based on the identity data obtained by the data obtaining module 150. The human body feature obtained by the feature obtaining module 160 may indicate whether the face or hand of the recognition target is defective.

The result judgment module 180 is responsible for the living body identification result generated by the living body identification module 130 to judge whether the identification target passes the living body identification. In more detail, the result judgment module 180 can generate a judgment result indicating that the identification target has passed the living body identification when the living body identification result indicates that the living body identification has passed; Produce a judgment result indicating that the identification target has not passed the living body identification.

The result judging module 180 determines whether the identification target passes the living body identification according to the living body identification result generated by the living body identification module 130, in some embodiments, it can also be combined with reference to the image detection received by the client communication module 190 As a result, it is judged whether the identification target passes the living body identification. In more detail, the result judgment module 180 can generate a judgment result indicating that the identification target passes the living body identification when the living body identification result indicates that the living body identification is passed and the image detection result indicates that the target image has passed the detection; The identification result indicates that the living body identification is not passed or when the image detection result indicates that the target image has not passed the detection, a judgment result indicating that the identification target has not passed the living body identification is generated.

The client communication module 190 can send the target image captured by the image capture module 110 to the server 200, and the client communication module 190 can also receive the image detection result sent by the server 200. fruit. In some embodiments, the client communication module 190 may also send the identification data obtained by the data obtaining module 150 and/or the living body identification result generated by the living body identification module 130 to the server 200.

The server 200 may further perform liveness detection on the target image captured by the client 100, and in some embodiments, may also store the live body recognition result of the client 100. The server 200 may include a servo communication module 210, an image comparison module 220, an image detection module 230, and a result generation module 240 as shown in the schematic diagram of the components in “FIG. 2”. Generally speaking, the server 200 is also a computing device.

The server communication module 210 can receive the target image sent by the client 100, and can also send the image detection result generated by the result generation module 240 back to the client 100. In some embodiments, the server communication module 210 may also receive the identity identification data and/or the living body identification result sent by the client 100.

The servo communication module 210 can also download the trusted image corresponding to the received identification data from the trusted host 202. The credible image downloaded by the servo communication module 210 includes the face of the identification target. For example, the credible image may include the identification photo of the identification target, etc., but this creation is not limited to this. The trusted host 202 is as This creation is not limited to servers provided by trusted units or organizations such as government agencies.

The image comparison module 220 can obtain a credible image of the identification target based on the identification data received by the servo communication module 210. The image comparison module 220 can download the credible image or read the credible image stored in advance through the server communication module 210 to the credible host 202. The credible image can be uploaded by the identification target itself or previously The host 202 downloads.

The image comparison module 220 can also compare the target image received by the servo communication module 210 with the face in the obtained credible image to generate an image comparison result, for example, image comparison The module 220 can compare the similarity between the target image and the face in the credible image, and can generate an image comparison result indicating that the image comparison is passed when the generated similarity is greater than or equal to the threshold value, or can When it is judged that the generated similarity is less than the threshold value, an image comparison result indicating that the image comparison has not passed is generated.

The image detection module 230 can determine the image depth of the target image received by the servo communication module 210. The image depth determined by the image detection module 230 is the distance between the image capture module 110 and each object or area in the target image. This distance is usually a rough value, but the creation is not limited to this. For example, the image detection module 230 can use Convolutional Neural Network (CNN) such as AlexNet, GoogleNet, VGG, Residual net, etc. to determine the distance of each object or region in the target image, but this creation does not Limited by this.

The image detection module 230 can also determine the image information of the target image received by the servo communication module 210. The image information determined by the image detection module 230 may include information indicating whether the target image contains moiré, reflection, and facial distortion, but the creation is not limited to this.

The image detection module 230 can also generate an image determination result based on the determined image depth and/or image information. For example, the image detection module 230 can determine whether the image depths of the face and the area behind the face in the target image are similar. When the two are similar, the image detection module 230 can generate an image judgment result that fails the depth judgment. The image detection module 230 can also generate an image judgment result that fails the optical judgment when there is information in the image information of the target image indicating that the face range in the target image contains moiré, reflection, and facial distortion. The module 230 can also achieve a certain value between the image depth of the face in the target image and the area behind the face and the absence of the image information of the target image indicates that the face range in the target image contains moiré and reflections. , When the facial distortion information is generated, the image judgment result judged by the image is generated.

The result generation module 240 generates an image detection result including the image comparison result generated by the image comparison module 220 and the image determination result generated by the image detection module 230.

Next, an example is used to explain the operation of the system of this creation, and please refer to "Figure 3A" for the flow chart of identifying the actions in the image mentioned in this creation to determine whether the target is a living body.

When identifying the target to use this creation, the action selection module 120 of the client 100 may first determine a predetermined number of designated actions (step 320). In this embodiment, assuming that the predetermined number is three, the action selection module 120 may first select three (predetermined number) facial actions and three hand actions as shown in the flow of "Figure 3B" (step 325) , And combine a facial motion and a hand motion three times to generate three designated motions (step 327), such as turning the head to the right, blinking, and placing the right finger under the left eye.

After the action selection module 120 of the client 100 determines the specified action (step 320), the image capture module 110 of the client 100 can capture the target image including the face of the recognition target (step 330). In this embodiment, it is assumed that the image capturing module 110 can generate a prompt message to the display module 140 as shown in the process of "Figure 3D", and the display module 140 of the client 100 can be as shown in "Figure 4". In the prompt area 412 of the display screen 410, the recognition target is prompted to point the camera of the mobile phone (client 100) to the front of the face and adjust the position of the mobile phone, so that the recognition target can be placed on the front of the face in the indication area of the display screen 410 411 When the face ratio is similar to the indicated area 411, press the shutter to trigger the image capturing module 110 to capture the target image including the front face of the target face (step 333); for another example, the image capturing module 110 can continue to determine Whether the captured target image contains a frontal face with sufficient proportions (step 333), when the target image contains a frontal face and the ratio of the face to the indication area 411 is similar (such as the height of the face and the indication area 411 or When the width difference is within 10%), the image capturing module 110 can capture the target image (step 335). In the process of capturing the target image three times, the image capturing module 110 can To determine whether the face of the recognition target is continuously in the image capturing range (step 331), if not, a living body recognition result that the recognition target does not pass the living body recognition can be generated (step 337).

Returning to "Figure 3A", also after the image capturing module 110 of the client terminal 100 captures the target image (step 330), the living body recognition module 130 of the client terminal 100 can determine whether the recognition target is completed in sequence. A designated action (step 350) is used to perform a living body identification, and a corresponding living body identification result can be generated after the living body identification (step 360). In this embodiment, it is assumed that the living body recognition module 130 can prompt the recognition target in the prompt area 412 through the display module 140 to aim the client 100 at the face so that the face is placed in the indication area 411 of the display screen 410 and the ratio of the face is It is similar to the indication area 411, so that the recognition target completes three specified actions according to the prompts in sequence. In this way, the living body recognition module 130 can perform face recognition and motion detection on the target image as shown in the process of "Figure 3C" (step 351), and can judge whether the face and gesture of the recognition target are consistent with the facial motion and hand motion of the specified action according to the result of face recognition and motion detection (step 355), and then the recognition target is successfully completed three times in succession When the designated action produces a living body identification result that passes the living body identification, on the contrary, the living body identification module 130 can generate a living body identification result that does not pass the living body identification.

In more detail, the living body recognition module 130 may first prompt the recognition target to complete the first specified action. When the recognition target turns its head to the right, the image capturing module 110 captures the information that includes the recognition target turning its head to the right. After indicating the image, the living body recognition module 130 can perform face feature analysis on the indicating image to determine the direction of rotation of the face in the indicating image. When the rotation direction is different from the designated direction, the living body recognition module 130 can determine that the living body recognition has not passed; and when the rotation direction is the same as the designated direction, the living body recognition module 130 can prompt the recognition target to complete the second designated action again. The target blinks according to the prompt, so that after the image capturing module 110 captures the indication image containing the blink of the recognition target, the living body recognition module 130 can perform facial feature analysis on the indication image to determine whether the face in the indication image is No blink. If not, the living body recognition module 130 can judge that the living body recognition has not passed; if so, the living body recognition module 130 can prompt the recognition target to complete the third specified action again. When the recognition target places the right finger under the left eye according to the prompts, so that After the image capturing module 110 captures the instruction image containing the recognition target, the living body recognition module 130 can perform face recognition and motion detection on the instruction image to determine whether the position of the face in the instruction image and the right finger are correct Placed under the left eye. If not, the living body identification module 130 can judge that the living body identification has failed; if so, the living body identification module 130 can judge that the living body identification has passed and can generate a living body identification result indicating that the living body identification has passed.

In the above-mentioned living body identification process, if the living body identification module 130 judges that the living body identification has not passed, the living body identification module 130 can accumulate the number of failures, and can provide the identification target again before the number of failures reaches the predetermined value. Recognition, that is, regenerate three designated actions, and complete the three designated actions according to the prompts in order to identify the target. When the accumulated number of failures reaches a predetermined value, the living body identification module 130 can generate a living body identification result indicating that the living body identification has not passed .

After the living body recognition module 130 of the client terminal 100 generates a living body recognition result, the result judgment module 180 of the client terminal 100 can judge whether the identification target passes the living body recognition according to the living body recognition result generated by the living body recognition module 130 (step 391). In this embodiment, the hypothesis result judgment module 180 can judge whether the living body recognition result indicates that the recognition target passes the living body recognition, and the result judgment module 180 can judge that the recognition target passes the living body recognition.

In this way, through this creation, the client 100 can determine whether the recognition target is a living body according to whether the recognition target in the image performs a specified action.

In the above-mentioned embodiment, the result judgment module 180 of the client 100 can also judge whether the cumulative number of failures is higher than the preset value. If yes, it means that the identification target has not passed the living body identification. If not, the result judgment module 180 A prompt message indicating that the comparison fails is generated and the display module 140 of the client terminal 100 A prompt message is displayed to prompt the recognition target to point the lens of the client 100 to the front of the recognition target again, so that the image capturing module 110 can capture the target image of the recognition target again (step 320), and the living body recognition module 130 It can also be judged whether the identification target completes the specified actions in order to perform the living body identification, and the corresponding living body identification result can be generated after the living body identification (step 350), and the result judgment module 180 can generate according to the living body identification module 130 From the result of the living body identification, it is judged whether the identification target passes the living body identification (step 360).

In addition, the above-mentioned embodiment may also be as shown in the flow of "Figure 3E". When the action selection module 120 of the client 100 determines the specified action (step 320), the data acquisition module 150 of the client 100 can first obtain the identification The identity data of the target (step 310), the feature acquisition module 160 of the client 100 can acquire the corresponding human body characteristics based on the identity data acquired by the data acquisition module 150 (step 321), and the action selection model of the client 100 The group 120 can determine a designated action that matches the human body feature retrieved by the feature acquisition module 160 (step 323).

In addition, in the above-mentioned embodiment, as shown in the process of "Figure 3F", after the image capturing module 110 of the client 100 captures the target image (step 330), the client 100 can The client communication module 190 may send the target image to the server 200 (step 340). In this embodiment, it is assumed that the client communication module 190 can send the target image together with the identification data obtained by the data acquisition module 150 of the client 100 after the living body identification module 130 generates the living body identification result (step 360). Server 200.

After the server communication module 210 of the server 200 receives the target image and the identification data sent by the client 100, the image comparison module 220 of the server 200 can use the identification data received by the server communication module 210 Obtain a credible image containing the identification target (step 371). In this embodiment, it is assumed that the image comparison module 220 can transmit the identity data through the servo communication module 210. Send to the trusted host 202, and receive the credential image returned by the trusted host 202 through the servo communication module 210.

After the image comparison module 220 of the server 200 obtains the credible image, the face in the obtained credible image can be compared with the face in the target image received by the servo communication module 210, and A corresponding image comparison result can be generated after the comparison (step 373). In this embodiment, it is assumed that the image comparison module 220 can extract the facial image from the trusted image according to the credible image's credential type and calculate the image characteristics of the facial image, and after it can calculate the image characteristics of the target image, Judging the similarity between the target image and the credible image based on the calculated image features of the face image and the image features of the target image, and depending on whether the similarity exceeds a predetermined threshold, it is selected to generate a pass or fail comparison Image comparison result.

After the image comparison module 220 of the server 200 generates the image comparison result, the image detection module 230 of the server 200 can determine whether the image comparison result indicates that the image comparison is passed. If not, the image detection module 230 can After the execution is completed, the result generation module 240 of the server 200 can generate an image detection result including an image comparison result. If the image detection module 230 determines that the image comparison result indicates that the image comparison is passed, the image detection module 230 can further determine the image depth and/or image information of the target image received by the servo communication module 210 of the server 200. An image determination result can be generated based on the determined image depth and/or image information of the target image (step 375). In this embodiment, it is assumed that the image detection module 230 can use a convolutional neural network to determine the depth of the recognition target's face and its back in the target image, and can also determine whether there are moiré patterns on the recognition target's face in the target image. Abnormal areas such as reflections, and/or deformities or distortions, and the difference between the depth of the recognition target's face and the image depth behind it exceeds a certain value, and there are no moiré, reflections, and abnormal areas on the recognition target's face The image detection module 230 can generate an image judgment result indicating that the judgment is passed. On the contrary, when the judgment is When the difference between the depth of the face of the recognition target and the image behind it is lower than a certain value or there are moiré, reflection, or abnormal areas on the face of the recognition target, the image detection module 230 can generate an image judgment result indicating that the judgment is passed. .

After the image detection module 230 of the server 200 generates the image determination result, the result generation module 240 of the server 200 may generate the image detection result according to the image determination result, and may transmit the generated image detection result to the client 100 ( Step 379). In this embodiment, the hypothesis result generation module 240 can generate an image detection result indicating a pass detection when the image judgment result indicates a passing judgment, and may generate an image detection result indicating a fail detection when the image judgment result indicates a failure judgment. .

After the client communication module 190 of the client 100 receives the image detection result sent by the server 200, the result judgment module 180 of the client 100 can be based on the image detection result received by the client communication module 190 and the client 100 The living body identification result generated by the living body identification module 130 determines whether the identification target passes the living body identification (step 395). In this embodiment, the hypothesis result judgment module 180 can judge that the identification target has passed the living body recognition when the living body identification result indicates that the identification target passes the living body identification and the image detection result indicates that the target image has passed the image detection. Otherwise, it can judge that the identification target has not passed the living body identification. Identify.

In summary, it can be seen that the difference between this creation and the prior art is that it has the ability to determine multiple specified actions including facial and hand actions and identify whether the identification target in the target image completes the specified action in sequence, and recognizes according to the living body. As a result, it is determined whether the identification target is a living body technical means. This technical means can solve the problem that the previous technology cannot confirm whether the other party is a real person during online meetings, thereby achieving the technical effect of increasing the security of online meetings.

Furthermore, the actions in this creation to identify the image to determine whether the target is a device/equipment in a living body system can be implemented in hardware or a combination of hardware and software, and can also be implemented in a centralized manner in a computer system or It is realized in a decentralized manner in which different components are scattered in a number of interconnected computer systems.

Although the implementation method disclosed in this creation is as above, the content described is not used to directly limit the scope of patent protection of this creation. Any person with ordinary knowledge in the technical field to which this creation belongs, without departing from the spirit and scope of this creation, makes a little modification in the form and details of the implementation of this creation, and it belongs to the patent protection of this creation. Scope. The scope of patent protection for this creation shall still be subject to the scope of the attached patent application.

100: client

101: Processing Module

110: Image capture module

120: Action selection module

130: Living Body Recognition Module

140: display module

150: data acquisition module

160: feature acquisition module

180: result judgment module

190: Customer Communication Module

Claims (10)

A system for recognizing actions in an image to determine whether a target is a living body. The system at least includes: an image capturing module; and a processing module electrically connected to the image capturing module for executing at least one computer The instruction is generated after the execution of the at least one computer instruction: an action selection module for determining a predetermined number of specified actions, each of the specified actions includes a facial movement and a hand movement; a living body recognition module, It is used to perform a living body recognition operation and generate a corresponding living body recognition result, wherein the living body recognition operation includes capturing multiple target images including a face of a recognition target through the image capturing module, and using the The target images judge whether the recognition target completes the specified actions determined by the action selection module in sequence; and a result judgment module for judging the recognition target according to the living body recognition result generated by the living body recognition module Whether to recognize by living body. The system for identifying the action in the image to determine whether the target is a living body as described in claim 1, wherein the system further includes a client communication module for transmitting the target images to a server, and the server further includes a Servo communication module and an image detection module, the servo communication module is used to receive the target images, the image detection module is used to determine an image depth and/or an image information of the target image and based on the image depth And/or the image information generates an image judgment result, and the servo communication module transmits the image detection result including or representing the image judgment result to the client communication module, and the result judgment module is further used to base the living body The recognition result and the image detection result received by the client communication module determine whether the recognition target passes the living body recognition. The system for identifying the action in the image to determine whether the target is a living body as described in claim 1, wherein the system further includes a data acquisition module and a customer communication module, and the data acquisition module is used to obtain an identification data , The client communication module is used to send the target images and an identification data to a server, the server further includes a servo communication module and an image comparison module, the server communication module is used to receive the The target images and the identification data are used to download a credible image containing the face of the identified target from a trusted server based on the identity identification data, and the image comparison module is used to compare the credible image with The face in the target image is used to generate an image comparison result, and the servo communication module transmits the image detection result including or representing the image comparison result to the client communication module, and the result judgment module is further used Based on the living body identification result and the image detection result received by the client communication module, it is determined whether the identification target passes the living body identification. The system for recognizing the action in the image to determine whether the target is a living body as described in claim 1, wherein the action selection module randomly selects the predetermined number of facial and hand actions from the action database, and combines them one by one A facial motion and a hand motion to generate the designated motions, and the living body recognition module performs face recognition and motion detection on each target image in sequence, and based on the face recognition results and motions The detection result determines whether the human face and gesture of the recognition target in each target image are respectively consistent with each of the facial motions and each of the hand motions to generate the living body recognition result. The system for recognizing the action in the image to determine whether the target is a living body as described in claim 1, wherein the living body recognition module generates the living body recognition result indicating that the living body is recognized when the recognizing target completes the specified actions in sequence , And when the identification target does not successfully complete one of the specified actions, the living body identification result indicating that the living body identification has not passed is generated. The system for recognizing the action in the image to determine whether the target is a living body as described in claim 1, wherein the image capturing module captures the target image when it detects that the face reaches a certain proportion of the image capturing range. The system for recognizing the action in the image to determine whether the target is a living body as described in claim 1, wherein the living body recognition module is further used to determine whether the face of the recognition target is detected in the process of the living body recognition operation, The result judgment module is further used for judging that the recognition target has not passed the living body recognition when the living body recognition module judges that the face of the recognition target is not detected in the process of the living body recognition operation. The system for identifying the action in the image to determine whether the target is a living body as described in claim 1, wherein the system further includes a data acquisition module and a feature acquisition module, and the data acquisition module is used to obtain an identity data The feature obtaining module is used to obtain a human body feature according to the identity identification data, and the action selection module is further used to determine the designated actions that conform to the human body feature. A system for identifying actions in an image to determine whether a target is a living body. The system at least includes: a client, which further includes: an image capture module; an action selection module for determining a predetermined number of specified actions , Each of the specified actions includes a facial movement and a hand movement; a living body recognition module for performing a living body recognition task and generating a corresponding living body recognition result, wherein the living body recognition task includes passing through the image The capturing module captures multiple target images including the face of a recognition target, and determines from the target images whether the recognition target completes the specified actions in sequence; and A result judgment module; and a server for providing the client connection, which further includes: a server communication module for receiving at least one of the target images transmitted by the client; and an image detection module Group for determining an image depth and/or image information of the at least one target image, and generating an image determination result based on the image depth and/or the image information, and the servo communication module is further used to include or indicate The image detection result of the image judgment result is sent to the client, so that the result judgment module judges whether the identification target passes the living body identification according to the living body recognition result and the image detection result. For example, the system for identifying the action in the image to determine whether the target is a living body described in claim 9, wherein the client further includes a data acquisition module, the data acquisition module is used to obtain an identity data, and the server further Comprising an image comparison module, and the server communication module is further used for receiving the identity identification data, and used for downloading a credible image containing the face of the identification target from the credible server according to the identity identification data; The image comparison module is used for comparing the credible image with the face in the target image to generate an image comparison result, and the servo communication module is used for comparing the image containing or representing the image comparison result The detection result is transmitted to the client, so that the result judgment module judges whether the identification target passes the living body identification according to the living body recognition result and the image detection result.

Images