TWI786438B - System for identification based on comparing id photo and live photo and method thereof - Google Patents

Abstract

A system for identification based on comparing an ID photo and a live photo and a method thereof are provided. By obtaining a ID photo from a certificate, capturing a face photo of a living target, determining a similarity between the ID photo and the face photo, perform live body recognition to generate a recognition result, and determining whether the living target passes identification of body and certificate based on the similarity, the system and the method can determining whether certificate provider is certificate holder according to photo obtained from certificate, and can achieve the effect of identifying identify of certificate provider effectively.

Description

System and method for identifying identity by comparing certificate images with multi-face images

An identity identification system and method thereof, in particular a system and method for identifying identity by comparing certificate images with multi-face images.

With the advancement of the Internet and related technologies, many services that used to be handled by document providers in person can also be completed through the Internet. However, some services, such as account opening and insurance application, are still restricted by relevant domestic laws and regulations due to the insufficient rigor of identity verification through the Internet, and the certificate provider cannot complete account opening and insurance application online.

As far as opening an account is concerned, although digital accounts can also be opened online through Internet banking or mobile banking, the relevant laws and regulations stipulate that the level of the digital account opened is also different according to the method of identity verification, that is, the lower level Compared with digital accounts opened with more complete identity confirmation, digital accounts have many restrictions, for example, some transactions cannot be executed or the amount available for transactions is relatively low. If you want to open a digital account with more complete functions, it is still the same as opening a general account. You need to go to the counter or through video, and the bank's service personnel will confirm the identity of the account holder. Usually, it is to confirm whether the certificate provided by the account holder is indeed owned by the account holder.

In addition, there are similar situations in the process of applying for insurance, that is, the relevant laws and regulations stipulate that the applicant needs to meet the salesperson face to face, and the salesperson will explain the insurance content to the applicant and confirm the identity of the applicant based on the certificate provided by the applicant. , Wait for the insurance company to complete the insurance.

However, since the photo printed on the ID card is usually taken by the ID holder many years ago, there may be a certain degree of discrepancy between the ID holder and the photo printed on the ID card, making it impossible for insurance agents or bank service personnel to identify the policyholder /Whether the account holder is the certificate holder himself. Insurance salespersons or bank service personnel may relax the results of confirmation in some cases, such as when performance is required. In this way, it may result in the situation that someone who does not apply for insurance or opens an account.

To sum up, it can be seen that there has been a problem in the prior art for a long time that it may not be possible to judge whether the certificate provider is the certificate holder from the photo on the certificate. Therefore, it is necessary to propose improved technical means to solve this problem.

In view of the problem in the prior art that it is impossible to determine whether the provider of the certificate is the holder of the certificate from the photo on the certificate, the present invention discloses a system and method for identifying identity by comparing the certificate image and the multi-face image, wherein:

The identity recognition system for comparing certificate images and multi-modal facial images disclosed in the present invention at least includes: an image capture module for capturing facial images; an image acquisition module for obtaining certificates from target certificates Image; image comparison module, used to compare certificate images and facial images and generate similarity; live body recognition module, used to generate multiple specified actions, and used to determine whether the recognition target completes the specified actions in sequence and generates The corresponding identification result; the result judgment module, which is used to judge whether the identification target has passed the identification of the witness according to the similarity and the identification result.

The method disclosed in the present invention for identifying an identity by comparing a certificate image with a multi-face image, the steps at least include: obtaining a certificate image from a target certificate; capturing a facial image; comparing the certificate image and a facial image and generating a similar degree; when it is judged that the similarity is greater than or equal to the threshold value, multiple specified actions are generated, and it is judged whether the recognition target completes the specified actions in order to generate a corresponding recognition result; according to the recognition result, it is judged whether the recognition target has passed the human card identification.

The system and method disclosed in the present invention are as above. The difference between the present invention and the prior art is that the present invention obtains the certificate image from the target certificate and captures the face image of the target for recognition, then compares the similarity between the certificate image and the face image. Degree, live body recognition to generate recognition results, and judge whether the recognition target has passed the identification of witnesses according to the similarity and recognition results, so as to solve the problems existing in the previous technology, and can achieve the identity recognition based on the certificate provided by the certificate provider Technical efficacy.

The features and implementation methods of the present invention will be described in detail below in conjunction with the drawings and embodiments, the content is enough to enable anyone familiar with the relevant art to easily and fully understand the technical means used to solve the technical problems of the present invention and implement them accordingly, thereby realizing The effect that the present invention can achieve.

The present invention can compare the photo on the identity certificate (also called the certificate image in the present invention) with the photo containing the face (also called the facial image in the present invention) taken by the provider of the identity certificate in real time. Determine whether the provider of the identity certificate is the holder of the identity certificate.

In the following, the system structure of the present invention will be described by using the "Fig. 1" system structure diagram of the identity recognition system for comparing certificate images and polymorphic facial images proposed by the present invention. As shown in "Fig. 1", the system of the present invention is applied in a device 100, which includes a processing module 101, an image capture module 110, and may also include an additional chip reading module 130, a display module 140, Enter module 180 . Wherein, the apparatus 100 may be a computing device.

The computing device mentioned in the present invention includes but is not limited to one or more processing modules, one or more memory modules, and hardware such as buses connecting different hardware components (including memory modules and processing modules). body element. Through the included multiple hardware components, the computing device can load and execute the operating system, so that the operating system can run on the computing device, and can also execute software or programs. In addition, the computing device also includes a casing, and the above-mentioned hardware components are arranged in the casing.

The bus of the computing device mentioned in the present invention can include one or more types, such as data bus (data bus), address bus (address bus), control bus (control bus), expansion function bus ( expansion bus), and/or local bus (local bus) and other types of bus. Buses for computing devices include, but are not limited to, Industry Standard Architecture (ISA) buses, Peripheral Component Interconnect (PCI) buses, Video Electronics Standards Association (VESA) boards Domain bus, and 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 the present invention is coupled to the bus bar. The processing module includes a register group or register space, which can be completely set on the processing chip of the processing module, or all or part of it is set outside the processing chip and coupled to the handle wafer via dedicated electrical connections and/or via bus bars. 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 are coupled and communicated through a bus. A processing module can interpret a computer instruction or a series of multiple computer instructions to perform specific calculations or operations, such as mathematical operations, logical operations, data comparison, copying/moving data, etc., to drive other hardware in the computing device components or run the operating system or execute various programs and/or modules.

Computing devices usually also contain one or more chipsets (Chipsets). The processing module of the computing device can be coupled to the chip set or electrically connected to the chip set through a bus bar. The chipset is composed of one or more integrated circuits (Integrated Circuit, IC), including memory controllers and peripheral input/output (I/O) controllers, etc., that is, memory controllers and peripheral I/O controllers A circuit breaker can be contained in one integrated circuit or implemented using two or more integrated circuits. Chipsets usually provide input/output and memory management functions, and provide multiple general and/or special registers, timers, etc., wherein the above general and/or special registers and timers can be coupled or Accessed or used by one or more processing modules electrically connected to the chipset.

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 (non-volatile memory, NVRAM) memory, such as static random access memory (Static Random Access Memory, SRAM) , Dynamic Random Access Memory (Dynamic Random Access Memory, DRAM), Read-Only Memory (Read-Only Memory, ROM), Flash memory (Flash memory), etc. The above-mentioned large-capacity storage area can include any type of storage device or storage medium, such as hard disk drive, optical disc (optical disc), flash drive (flash drive), memory card (memory card), solid state hard disk (Solid State Disk) , SSD), or any other storage device, etc. That is to say, the memory controller can access data in SRAM, DRAM, flash memory, hard disk drive, and solid-state hard disk.

The processing module of the computing device can also be connected and communicated with peripheral devices or interfaces such as peripheral output devices, peripheral input devices, communication interfaces, and GPS receivers 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 keyboard, mouse, trackball, touch pad, joystick, etc., and the peripheral output device can be any type of output device, such as display, printer, etc., peripheral input device It can also be the same device as the peripheral output device, such as a touch screen. The communication interface may include a wireless communication interface and/or a wired communication interface, and the wireless communication interface may include support for a wireless local area network (such as Wi-Fi, Zigbee, etc.), Bluetooth, infrared, near-field communication (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 (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 (polling) various peripheral devices and interfaces, so that the computing device can input and output data through various peripheral devices and interfaces, and can also communicate with another computing device with the hardware components described above to communicate.

In the present invention, the processing module 101 can load and execute one or a set of computer instructions stored in the memory module (not shown in the figure) through the bus, and can generate the image acquisition module 120 after executing the computer instructions. , an image comparison module 150 , a living body recognition module 160 , and a result judging module 170 .

The image capture module 110 may include elements such as a lens and a photosensitive element (not shown in the figure). Wherein, the lens can let the light pass through and let the passed light irradiate on 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 facial images. The facial image captured by the image capture module 110 includes a complete front face. Wherein, when the image capture module 110 is driven by the image comparison module 150 or receives a coordination message sent by the image comparison module 150, it can continuously use the image signal output by the photosensitive element as the face image.

The image capture module 110 can also capture data images. Generally speaking, the data image captured by the image capture module 110 includes a complete character string or a barcode sufficient to identify the represented content, but the present invention is not limited thereto. When the image capture module 110 is driven by the image capture module 120 or receives a cooperative message from the image capture module 120 , it can continuously use the image signal output by the photosensitive element as a data image.

The image capture module 110 can also capture the instruction image. The instruction image captured by the image capture module 110 includes the face of the person performing the specified action. Wherein, when the image capture module 110 is driven by the biometric identification module 160 or receives a cooperative message sent by the biometric identification module 160, it can continuously use the image signal output by the photosensitive element as the instruction image.

The specified actions mentioned in the present invention include but are not limited to turning a certain angle in a specific direction (such as left and right), nodding, blinking, smiling, and the like.

The image obtaining module 120 is responsible for obtaining the certificate image from the target certificate. For example, the image acquisition module 120 can capture the certificate image printed on the target certificate through the image capture module 110, and can also read the image stored in the target chip set in the target certificate through the chip reading module 130. Document image. Wherein, the target certificate is a certificate printed with a photo of the certificate holder and capable of identifying the identity of the certificate holder, such as an ID card, a passport, and the like.

The image acquisition module 120 can set the range of the target certificate or certificate image in the data image captured by the image capture module 110 through the display module 140 and the input module 180. For example, the image acquisition module 120 can display The module 140 displays a rectangular indicator frame on the display screen, and can provide the user with the input module 180 to rotate the indicator frame and move the four sides of the displayed indicator frame, so that the indicator frame can frame the target certificate or document in the data image. The image of the certificate, so that the image acquisition module 120 can use the area framed by the indicator frame as the range of the target certificate or the certificate image in the data image; the image acquisition module 120 can also prompt the target certificate through the display module 140 or The placement area of the certificate image, for example, the image acquisition module 120 can generate an instruction frame representing the placement area, and display the generated instruction frame through the display module 140 and prompt the user to adjust the position of the device 100 or the target certificate so that the target The certificate or certificate image is placed in the instruction frame, so that the target certificate or certificate image is at a specified position in the data image captured by the image capture module 110 .

The image acquisition module 120 can also set or detect the target certificate in the data image captured by the image capture module 110, so as to obtain the certificate type of the target certificate. For example, the image acquisition module 120 can provide the certificate type of the target certificate set by the user through the input module 180; the image acquisition module 120 can also perform image processing on the range of the target certificate in the data image, so as to obtain the image of the target certificate features, and can judge the type of the target certificate based on the image features of the obtained target certificate. Wherein, the certificate type may indicate that the target certificate is an ID card or a passport.

The image obtaining module 120 can also determine the capture range of the certificate image in the data image according to the type of certificate obtained. The image acquisition module 120 can pre-store the position information of the printed document images on various types of documents, and can determine the capture range according to the position information. The location information can indicate the position of the document image in the data image, for example, the coordinates of the upper left corner and the lower right corner of the document image in the data image, or the coordinates of any of the four corners of the document image in the data image and the document image The length and width of the image, but the present invention is not limited thereto.

The chip reading module 130 can connect to a target chip (not shown in the figure) when receiving the cooperation message generated by the image capturing module 120 , and can read the certificate image from the connected target chip. In general, a target wafer is typically disposed on a target document.

The chip reading module 130 can connect to the target chip through Near-Field Communication (NFC), so as to communicate with the target chip, but the present invention is not limited thereto. For example, the chip reading module 130 can also be Connect to the target chip through the connecting wire.

The wafer reading module 130 can also read the document image stored in the target wafer. Generally speaking, the image acquisition module 120 can transmit the reading instruction of the certificate image to the target chip, and the target chip can read the certificate image according to the received reading instruction, and can transmit the read certificate image back to the chip. Read module 130 .

The display module 140 can display the data image, facial image, and instruction image captured by the image capture module 110 on the display screen of the device 100 . The display module 140 can also display prompt messages such as instruction boxes and text generated by the image acquisition module 120 on the display screen of the device 100 . The display module 140 can also display the judgment result generated by the result judgment module 170 on the display screen of the device 100 .

The image comparison module 150 is responsible for comparing the certificate image obtained by the image acquisition module 120 and the facial image captured by the image capture module 110, and generates the face in the certificate image and the person in the facial image face similarity. In more detail, the image comparison module 150 can use the known face detection technology to determine whether the facial image captured by the image capture module 110 contains a complete frontal face, and can include a face image in the facial image. When the face is complete, the facial image and the face in the ID image are analyzed to generate the features of the ID image and the face in the facial image, and the facial features in the ID image and facial image can be compared. The feature is used to judge the similarity between the ID image and the face in the facial image, but the way the image comparison module 150 generates the similarity between the ID image and the facial image is not limited to the above.

The living body recognition module 160 is responsible for generating multiple specified actions, and performing living body identification according to the generated specified actions. Wherein, the number of specified actions generated by the living body recognition module 160 can be recognized as a predetermined value or set through the input module 180, and the present invention is not particularly limited. In some embodiments, the living body recognition module 160 can only perform the living body recognition when the result judging module 170 judges that the similarity generated by the image comparison module 150 is higher than (or equal to) the threshold value, but the present invention does not This is not the limit.

The process of the living body identification performed by the living body identification module 160 is, for example: First randomly generate a plurality of specified actions in sequence, and prompt the identification target through the display module 140 to complete the generated first one in front of the image capture module 110 Specify the action, and continue to analyze the face in the instruction image captured by the image capture module 110 that includes the completion of the first specified action to obtain the features of the face in the instruction image, and according to the image comparison model The feature of the face in the facial image obtained by group 150 and the feature of the face in the instruction image are judged whether the face in the instruction image has completed the specified action, and if so, the display module 140 prompts that the recognition target is completed The second specified action is generated and the above comparison process is repeated until the identification target completes all the generated specified actions correctly, so as to perform living body identification. However, the living body recognition method mentioned in the present invention is not limited to the above. Wherein, the biometric identification module 160 may randomly select a plurality of specified actions from a pre-established action database.

The living body recognition module 160 is also responsible for generating corresponding recognition results after the living body recognition is performed. The activity recognition module 160 can judge that the living body recognition is passed and generate a recognition result indicating that the living body recognition is passed when the generated specified actions are all completed correctly or the number of times of continuously and correctly completing the specified actions reaches the parameter value; When any one of the specified actions generated is not completed correctly or the number of specified actions not completed correctly reaches a predetermined value, it is judged that the living body recognition has failed and an identification result indicating that the living body recognition has not passed is generated.

The living body recognition module 160 may also accumulate the number of failed passes when determining that the living body recognition fails, and re-perform the living body recognition. The biometric identification module 160 may generate an identification result indicating that the biometric identification has failed when the accumulated failed times reach a predetermined value.

The result judging module 170 is in charge of judging whether the recognition target has passed the identification of the human certificate according to the similarity generated by the image comparison module 150 and the recognition result generated by the living body recognition module 160 . In more detail, in some embodiments, the result judging module 170 can generate a judgment result indicating that the recognition target has passed the identification of a person when the similarity is higher than (or equal to) the threshold value and the recognition result indicates that the recognition target has passed the identification of a living body; On the contrary, the result judging module 170 can generate a judging result indicating that the recognition target has not passed the identification of the human body when the similarity is lower than the threshold value, or the recognition result indicates that the recognition target has not passed the identification of the living body. In another preferred embodiment, the result judging module 170 can first judge whether the similarity is higher than (or equal to) the threshold value, and provide the judgment result to the living body recognition module 160, and can be used in the living body recognition module After the identification result is generated by 160, it is judged whether the identification target has passed the identity identification according to the identification result generated by the living body identification module 160.

The input module 180 can set the range of the target certificate or the certificate image in the data image captured by the image capture module 110 . In more detail, the input module 180 may allow the user to rotate the indicator frame displayed by the display module 140 and/or move the four sides of the indicator frame displayed by the display module 140 on the display screen, so that the user can Set the target certificate or the range of the certificate image in the data image; the input module 180 can also set the certificate type of the target certificate, for example, provide a drop-down menu or a check box to provide the user with a set certificate type.

The input module 180 can also set the threshold used by the result judging module 170 . It should be noted that the threshold value can be set according to the requirements of the present invention. For example, when the present invention is applied in the access control system, a lower threshold value can be set through the input module 180, making the access control system less difficult. Deny the user's access; and when the present invention is applied in the transaction system, the threshold value can be set higher through the input module 180, so as to prevent non-users from successfully conducting transactions.

The input module 180 can also set the number of specified actions generated by the biometric identification module 160 for biometric identification, and can also set the number of times the biometric identification module 160 needs to continuously and correctly complete the specified actions through the biometric identification (i.e., the biometric identification module 160 The parameter value used for judgment).

Next, an embodiment is used to explain the operating system and method of the present invention, and please refer to "FIG. 2A" for the flow chart of the method for identifying identity by comparing document images and polymorphic facial images proposed by the present invention.

Firstly, the image obtaining module 120 may obtain the certificate image from the target certificate prepared by the certificate provider (step 210 ). In this embodiment, assuming that the target certificate is an ID card, the image acquisition module 120 can read the certificate image from the target chip set on the target certificate through the chip reading module 130, or can be as shown in "Fig. 2B". As shown in the process, the image capture module 110 captures the image of the certificate containing the ID card held by the certificate provider, that is to say, the image acquisition module 120 can provide the user with a set target certificate or certificate The range of the image on the display screen can also prompt the user to place the target certificate or certificate image in the placement area of the display screen through the display module 140 (step 211), so that the image capture module 110 can capture the image containing the target The data image of the document. Afterwards, the image acquisition module 120 can provide the user with the certificate type of the target certificate through the input module 180, or perform image processing on the target certificate in the data image to generate the image features of the target certificate and detect the target certificate according to the image features. ID type, and the range of ID image capture can be determined according to the type of ID obtained (step 213). Next, the image acquisition module 120 can extract the certificate image from the data image according to the capture range (step 215 ).

Returning to the process of "Fig. 2A", after the image acquisition module 120 acquires the target data (step 210), the image acquisition module 110 can capture the face image (step 220), and the image comparison module 150 can compare The image acquisition module 120 generates a similarity between the ID image and the facial image from the ID image acquired on the target ID and the face image captured by the image capture module 110 (step 230 ). In this embodiment, it is assumed that the image comparison module 150 can generate a prompt message to the display module 140, and the display module 140 can prompt the certificate provider in the prompt area 312 of the display screen 310 as shown in "Fig. 3". Aim the camera of the mobile phone (device 100 ) at the front of the face and adjust the position of the mobile phone so that the credential provider can press the shutter when the front of the face is placed in the indicated area 311 of the display screen 310 and the proportion of the face is similar to the indicated area 311 The image capture module 110 is triggered to capture a facial image including the front face of the certificate provider, and then the image comparison module 150 can perform image analysis on the certificate image and the facial image to obtain the certificate image and the facial image. facial features, and can judge the similarity between the ID image and the facial image based on the facial features extracted from the ID image and the facial image; as another example, the image comparison module 150 can continuously judge the image capture module 110 Whether the captured facial image contains a sufficient proportion and a front face, when the face image contains a front face and the ratio of the face to the indication area 311 is similar (such as the height or width of the face to the indication area 311 When the difference is within 10%), the image comparison module 150 can perform feature analysis on the face in the ID image and facial image to obtain the facial features in the ID image and facial image, and can and the facial features extracted from the facial image to determine the similarity between the ID image and the facial image.

Similarly, after the image capture module 110 captures the facial image (step 220), the life recognition module 160 can generate multiple specified actions and judge whether the recognition target completes the generated specified actions in sequence for live body recognition, and can A corresponding identification result is generated after the living body identification (step 250 ). In this embodiment, assuming that the certificate provider needs to complete three specified actions in a row, the biometric recognition module 160 can first randomly generate three specified actions (for example, turn the head 30 degrees to the right, blink, and nod in sequence), and then The prompt area 312 prompts the certificate provider to align the device 100 with the face so that the face is placed in the indication area 311 of the display screen 310 and the proportion of the face is similar to the indication area 311, so that the certificate provider completes three specified actions in sequence according to the prompts, In this way, the biometric identification module 160 can generate an identification result that passes the biometric identification when the credential provider successfully completes three specified actions in a row; otherwise, the biometric identification module 160 can generate an identification result that fails the biometric identification.

In more detail, the biometric recognition module 160 can first prompt the certificate provider to complete the first specified action. When the certificate provider turns his head to the right, the image capture module 110 captures the image that includes the certificate provider turning right. After the indication image of the head, the biometric recognition module 160 can perform face feature analysis on the indication image, so as to determine the rotation direction of the face in the indication image. When the rotation direction is different from the specified direction, the biometric identification module 160 can judge that the biometric identification has not passed; and when the rotational direction is the same as the specified direction, the biometric identification module 160 can prompt the certificate provider to complete the second specified action again. The certificate provider blinks according to the prompt, so that after the image capture module 110 captures the instruction image containing the certificate provider's blink, the biometric recognition module 160 can analyze the facial features of the instruction image, so as to judge the face in the instruction image Whether to blink. If not, the biometric identification module 160 can judge that the biometric identification has not passed; if so, the biometric identification module 160 can remind the certificate provider to complete the third specified action again, when the certificate provider nods according to the prompt, the image capture module After 110 captures the instruction image including the nodding of the certificate provider, the biometric recognition module 160 can perform face feature analysis on the instruction image to determine whether the face in the instruction image is nodding. If not, the biometric identification module 160 can judge that the biometric identification has not passed; If the module 160 judges that the biometric identification has failed, the biometric identification module 160 can accumulate the number of times of failures, and can provide the certificate provider for biometrics identification again before the number of failures reaches the predetermined value, that is, regenerate three specified actions , and the credential provider completes three designated actions according to the prompts until the accumulated number of failures reaches a predetermined value, the biometric identification module 160 can generate an identification result indicating that the biometric identification has not passed.

After the image comparison module 150 generates the similarity between the certificate image obtained by the image acquisition module 120 and the facial image captured by the image capture module 110, and the living body recognition module 160 produces the recognition result, the result judgment module The group 170 can determine whether the identification target has passed the identification of the witness according to the similarity generated by the image comparison module 150 and the identification result generated by the living body identification module 160 (step 260 ). In this embodiment, the hypothetical result judging module 170 can judge whether the similarity is higher than (or equal to) a threshold value, and judge whether the recognition result indicates that the recognition target has been recognized by a living body. If both are, that is, the similarity is higher than ( or equal to) the threshold value and the identification result indicates that the identification target has passed the identification of the living body, then the result judging module 170 can determine that the identification target has passed the identification of the witness, which means that the identification target should be the certificate holder, otherwise, if the similarity is lower than the threshold If the value or the identification result indicates that the identification target has not passed the biometric identification, the result judging module 170 can determine that the identification target has not passed the identification of a person certificate, which means that the identification target may not be the certificate holder.

In the present invention, the result judging module 170 is not limited to judging whether the recognition target has passed the identification of the witness (step 260) after the image comparison module 150 generates similarity and the living body recognition module 160 generates the recognition result (step 260). Above, the result judging module 170 can also compare the certificate image obtained by the image acquisition module 120 and the facial image captured by the image capturing module 110 in the image comparison module 150 to generate the certificate image and facial image After the similarity (step 230), first judge whether the similarity generated by the image comparison module 150 is higher than (or equal to) the threshold value, so that the living body recognition module 160 can judge the similarity higher than (or equal to) the threshold value, generate multiple designated actions and judge whether the recognition target completes the generated designated actions in order to perform living body recognition and generate corresponding recognition results (step 250), after that, the result judgment module 170 can Then, according to the identification result generated by the living body identification module 160, it is judged whether the identification target has passed the identification of the witness.

In this way, through the present invention, it is possible to judge whether the provider of the identity certificate is the holder by comparing the image of the certificate obtained from the identity certificate with the facial image of the certificate provider in real time, so as to confirm the identity of the provider of the identity certificate identity.

In the above-mentioned embodiment, the result judging module 170 can also be shown in the process of "Fig. The group 170 can accumulate the number of failures, and judge whether the accumulated number of failures is higher than the preset value (step 271), if yes, it means that the identification target has not passed the identification of the witness, if not, the result judgment module 170 generates a comparison failure A reminder message is displayed by the display module 140 to prompt the certificate provider to point the lens of the device 100 at the front of the certificate provider's face again, so that the image capture module 110 can capture the certificate provider's face image again (step 220), and the image comparison module 150 can compare the certificate image and the face image again, and generate the similarity between the certificate image and the face image (step 230), and the living body recognition module 160 can also judge the image comparison When the similarity generated by the module 150 is higher than the threshold value (step 240), multiple designated actions are generated and it is judged whether the recognition target completes the generated designated actions in order for live body recognition, and a corresponding action can be generated after live body recognition. Corresponding to the recognition result (step 250 ), the result judging module 170 can judge whether the recognition target has passed the identification according to the similarity generated by the image comparison module 150 and the recognition result generated by the living body recognition module 160 (step 260 ).

To sum up, it can be seen that the difference between the present invention and the prior art lies in the fact that the document image is obtained from the target document, and after the face image is captured, the similarity between the document image and the face image is compared, and biometric identification is performed to It is a technical means to generate the identification result and judge whether the identification object has passed the identification of the identification according to the similarity, that is, the identification result. This technical means can solve the problem in the previous technology that it is impossible to judge whether the document provider is a document holder based on the photo on the document. The problem of someone, and then achieve the technical effect of identifying the identity of the certificate provider based on the certificate provided by the certificate provider.

Moreover, the method for identifying identity by comparing certificate images and multi-face images of the present invention can be implemented in hardware, software, or a combination of hardware and software, and can also be implemented in a centralized manner in a computer system or in a computer system. A distributed implementation in which different components are spread across several interconnected computer systems.

Although the embodiments disclosed in the present invention are as above, the content described is not intended to directly limit the scope of protection of the present invention. Anyone with ordinary knowledge in the technical field of the present invention, without departing from the spirit and scope disclosed in the present invention, makes some changes and modifications to the form and details of the implementation of the present invention, all of which belong to the patent protection of the present invention scope. The scope of patent protection of the present invention shall still be defined by the scope of the attached patent application.

100: device 110:Image capture module 120: Image acquisition module 130: Chip reading module 140: display module 150: Image comparison module 160: Live body recognition module 170: Result Judgment Module 180: input module 310: display screen 311: indicating area 312: Prompt area Step 210: Obtain target data from target certificate Step 211: Set the range of the target certificate or certificate image or prompt the placement area of the target certificate or certificate image Step 213: Set or detect the certificate type of the target certificate, and determine the capture range of the certificate image according to the certificate type Step 215: Capture the ID image printed on the target ID Step 220: Capture the facial image of the recognition target Step 230: Compare the ID image and facial image and generate similarity Step 240: determine whether the similarity is higher than the threshold Step 250: Generate multiple designated actions, and judge whether the recognition target completes the designated actions in order to generate corresponding recognition results Step 260: Judging whether the identification target has passed the identification of the witness according to the similarity and the identification result Step 265: Judging whether the identification target has passed the identification of witnesses according to the identification result Step 271: Determine whether the number of failures reaches a preset value

Figure 1 is a system architecture diagram of the identity recognition system for comparing certificate images and multi-modal facial images proposed by the present invention. FIG. 2A is a flowchart of a method for identifying identity by comparing certificate images and multi-face images according to the present invention. FIG. 2B is a flow chart of the method for capturing the document image on the target document proposed by the present invention. FIG. 2C is a flowchart of an additional method for identifying identity by comparing the certificate image and the multi-face image according to the present invention. FIG. 3 is a schematic diagram of a user interface for capturing facial images proposed by an embodiment of the present invention.

Step 210: Obtain target data from target certificate

Step 220: Capture the facial image of the recognition target

Step 230: Compare the ID image and facial image and generate similarity

Step 250: Generate multiple designated actions, and judge whether the recognition target completes the designated actions in order to generate corresponding recognition results

Step 260: Judging whether the identification target has passed the identification of the witness according to the similarity and the identification result

Claims (10)

A system for identifying identity by comparing certificate images with multi-face images, the system at least includes: an image capture module for capturing multiple facial images of a recognition target; an image capture module for To set or detect a certificate type of a target certificate, determine a capture range according to the certificate type, and obtain a certificate image from a target certificate according to the capture range; an image comparison module for comparison The ID image and a facial image generate a similarity; a biometric recognition module is used to generate multiple specified actions, and to sequentially follow the facial features in the instruction image of each specified action and the The facial features in these facial images determine whether the number of times the recognition target has correctly completed the specified actions reaches the parameter value and whether the cumulative number of failed recognition reaches the predetermined value to generate a corresponding recognition result, wherein , each of the specified actions is turning a certain angle in a specific direction, nodding, blinking, or smiling; and a result judging module, which is used to determine whether the similarity is greater than or equal to a threshold and whether the similarity is lower than the threshold Whether the number of failures is higher than a preset value, and the identification result determine whether the identification target passes the identification of the witness. The system for identifying identity by comparing certificate images and multi-face images as described in claim 1, wherein the living body recognition module randomly extracts the specified actions from the action database to generate the specified actions. The system for identifying identity by comparing certificate images and multi-face images as described in Claim 1, wherein the living body recognition module generates an indication when the recognition target completes the specified actions in sequence Pass the recognition result of the living body recognition, and when the recognition target fails to complete one of the specified actions, generate the recognition result indicating that the living body recognition has not passed. The system for identifying identity by comparing ID images and multi-face images as described in claim 1, wherein the image acquisition module is further used to set the range of the target ID or the ID image or prompt the target ID or the ID Placement area for the ID image. The identity recognition system for comparing ID images and multi-faceted facial images as described in Claim 1, wherein the image acquisition module captures the ID image printed on the target ID or is set on the target when reading An image of the document stored in a target chip in the document. A method for identifying identity by comparing a certificate image with a multi-face image, the method at least includes the following steps: setting or detecting a certificate type of a target certificate, and determining an extraction range according to the certificate type, and according to the The capture scope is to obtain a certificate image from a target certificate; capture a facial image of a recognition target; compare the certificate image and the facial image to generate a similarity; generate multiple specified actions, and sequentially according to each 1. The facial features in the instruction image of the specified action and the facial features in the facial image to determine whether the number of consecutive and correct completions of the specified actions by the recognition target reaches the parameter value and determine whether the cumulative number of failures in the identification is not passed Reaching a predetermined value to generate a corresponding recognition result, wherein each specified action is turning a certain angle in a specific direction, nodding, blinking, or smiling; and based on whether the similarity is greater than or equal to a threshold value, the similarity is low Whether the number of failures at the threshold is higher than a preset value, and the identification result determines whether the identification target has passed the identification of the witness. The method for identifying identity by comparing the certificate image and the multi-face image as described in Claim 6, wherein the step of generating the specified actions is to randomly extract the specified actions from the action database. The method for identifying the identity by comparing the ID image and the multi-face image as described in claim 6, wherein the step of generating the corresponding identification result is to generate an indication of passing through the living body when the identification target completes the specified actions in sequence The recognition result of the recognition, and when the recognition target fails to successfully complete one of the specified actions, the recognition result indicating that the recognition of the living body has not passed is generated. The method for identifying the identity by comparing the image of the certificate and the multi-face image as described in claim 6, wherein the step of obtaining the image of the certificate from the target certificate is to capture the image of the certificate printed on the target certificate or read it Get the certificate image stored in a target chip set in the target certificate. The method for identifying the identity by comparing the image of the certificate and the multi-face image as described in claim 9, wherein the method further includes setting the target certificate or before the step of capturing the image of the certificate printed on the target certificate The step of presenting the range of the image of the certificate or prompting the location of the target certificate or the image of the certificate.

Images