Passenger identity verification method, device, system and equipment
By performing motion inspection and matching visual distinctive feature after face contour authentication, the problem of misidentification of identity caused by similar appearances is solved, and the accuracy and security of identity verification are improved.
Patent Information
- Application Number
- CN202411029496.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-12-03
AI Technical Summary
Because there are similarities in the facial contour feature vectors extracted by people with similar appearances, it is easy to have misidentification and risk of using identity in passengers.
After face contour authentication, action verification instructions are pushed to passengers, real-time action information is obtained, and visually significant feature information is used to match, and verification is carried out through preset reference tag groups to improve the accuracy of identity verification.
By increasing motion inspection and visual distinctive feature matching, the complexity of identity verification is improved, the risk of single contour feature being counterfeited, and the possibility of identity misidentification is reduced.
Smart Images

Figure CN119068523A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of liveness detection technology, and in particular to a passenger identity verification method, device, system and equipment. Background Art
[0002] Before boarding, passengers need to undergo a live identity verification through a camera, such as facial identity verification (i.e., "face scanning"). The principle of face scanning is to extract key feature points or feature vectors from the detected face image, and compare the extracted feature vectors with known vectors stored in the database to identify the corresponding individual. Among them, feature points may include the outline of the face, the position of eyebrows, the distance between eyes, etc., and feature vectors are the result of numerical representation of these feature points.
[0003] However, since the feature vectors of facial contours extracted from similar-looking people also have similarities, it is easy to misidentify the identity of the similar-looking person during the verification process, which in turn brings the risk of passenger identity fraud. Summary of the invention
[0004] The main purpose of this application is to provide a passenger identity verification method, device, system and equipment, aiming to solve the technical problem that identity misrecognition is easily caused due to the similarities in facial contour feature vectors extracted from people with similar looks.
[0005] To achieve the above purpose, the present application proposes a passenger identity verification method, which includes:
[0006] When the current passenger passes the facial contour authentication, a motion verification instruction is pushed to the current passenger so that the current passenger can feedback real-time motion information based on the motion verification instruction;
[0007] Performing a motion check according to the real-time motion information, and obtaining visually significant feature information of the current passenger when the motion check passes;
[0008] When the visually significant feature information meets the matching condition of the preset reference tag group, it is determined that the current passenger has passed the identity authentication.
[0009] In one embodiment, before the step of pushing a motion verification instruction to the current passenger when the current passenger passes the face contour authentication so that the current passenger can feedback real-time motion information based on the motion verification instruction, the step includes:
[0010] Acquire a real-time facial image of the current passenger, and extract contour feature information corresponding to the real-time facial image;
[0011] The facial contour of the current passenger is authenticated based on the contour feature information.
[0012] In one embodiment, before the step of performing action verification according to the real-time action information, the method further includes:
[0013] An identity information database corresponding to the current passenger is obtained according to the face contour authentication result, wherein the identity information database includes: a passenger ID of the target passenger, a standard key action corresponding to the passenger ID, and a preset reference tag group, wherein the standard key action is pre-set by the target passenger during the passenger identity registration process, and the preset reference tag group includes a number of reference significant features corresponding to the target passenger extracted from the passenger identity registration process.
[0014] In one embodiment, the step of performing action verification according to the real-time action information includes:
[0015] Obtaining a standard key action in the identity information repository;
[0016] Acquire the real-time action of the current passenger, and compare the real-time action with the standard key action;
[0017] When the real-time action is consistent with the standard key action, determining that the current passenger has passed the action inspection;
[0018] When the real-time action is inconsistent with the standard key action, the current passenger is not the target passenger, and it is determined that the current passenger action inspection has failed.
[0019] In one embodiment, when the visually significant feature information meets the matching condition of the preset reference tag group, before the step of determining that the current passenger has passed the identity authentication, the step includes:
[0020] Obtaining a preset reference tag group in the identity information database;
[0021] Matching the visually salient characteristic information with a plurality of reference salient features in the preset reference tag group;
[0022] It is determined whether the visually significant feature information meets the matching condition of the preset reference tag group according to the matching result.
[0023] In one embodiment, the matching result includes the number of matching items, and when the visually significant feature information meets the matching condition of the preset reference tag group, the step of determining that the current passenger has passed the identity authentication includes:
[0024] When the number of matching items meets a preset matching item threshold, the current passenger is the target passenger, and it is determined that the identity verification of the current passenger is passed.
[0025] In one embodiment, after the step of judging whether the visually significant feature information satisfies the matching condition of the preset reference tag group according to the matching result, the method further includes:
[0026] When the number of matching items does not meet the preset matching item threshold, the current passenger is not the target passenger, and it is determined that the identity verification of the current passenger has failed.
[0027] In addition, to achieve the above purpose, the present application also proposes a passenger identity verification device, the device comprising:
[0028] A motion inspection module is used to push a motion inspection instruction to the current passenger when the current passenger passes the face contour authentication so that the current passenger can feedback real-time motion information based on the motion inspection instruction; and perform motion inspection according to the real-time motion information;
[0029] The tag matching module is used to obtain the visually significant feature information of the current passenger when the action inspection is passed; when the visually significant feature information meets the matching conditions of the preset reference tag group, determine that the current passenger has passed the identity authentication.
[0030] In addition, to achieve the above purpose, the present application also proposes a passenger identity authentication system, the system comprising the passenger identity authentication device and the passenger identity registration device as described above, the passenger identity registration device comprising:
[0031] A registration initialization module, configured to obtain real-time image information of the current passenger in response to a triggered registration instruction, wherein the real-time image information includes facial contour information and reference significant feature information; and generate a passenger ID corresponding to the current passenger according to the facial contour information;
[0032] A label extraction module, used to determine a preset reference label group according to a number of reference significant features in the reference significant feature information;
[0033] An action setting module, used to push an action key setting prompt to the current passenger and receive a standard key action set by the current passenger;
[0034] The information storage module is used to associate and store the preset reference tag group, the standard key action and the passenger ID to obtain the identity information library of the current passenger.
[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a passenger identity authentication device, which includes: a memory, a processor, and a passenger identity authentication program stored on the memory and executable on the processor, and the passenger identity authentication program is configured to implement the steps of the passenger identity authentication generation method described above.
[0036] The present application provides a passenger identity verification method, which pushes a motion verification instruction to the current passenger when the current passenger passes the facial contour authentication so that the current passenger can feedback real-time motion information based on the motion verification instruction; performs motion verification according to the real-time motion information, and obtains the visually significant feature information of the current passenger when the motion verification passes; and determines that the current passenger has passed the identity verification when the visually significant feature information meets the matching conditions of the preset reference tag group. Since the present application can perform motion verification and visually significant feature matching on the current passenger after facial contour authentication, the complexity of identity verification is increased, and the risk of a single contour feature being counterfeited is greatly reduced, which is conducive to reducing the risk of misidentification. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0039] Figure 1 This is a flow chart of the first embodiment of the passenger identity verification method for this application;
[0040] Figure 2 This is a flow chart of the second embodiment of the passenger identity verification method for this application;
[0041] Figure 3 This is a flow chart of the third embodiment of the passenger identity verification method for this application;
[0042] Figure 4 This is a schematic diagram of the entire process of applying for passenger identity verification;
[0043] Figure 5 This is a schematic diagram of the module structure of the first embodiment of the passenger identity verification device of the present application;
[0044] Figure 6 This is a schematic diagram of the module structure of the first embodiment of the passenger identity verification system of the present application;
[0045] Figure 7 This is a schematic diagram of the structure of the passenger identity verification device for this application.
[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0049] The present application embodiment provides a passenger identity verification method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the passenger identity verification method of the present application. In this embodiment, the method includes: Steps S10 to S30:
[0050] Step S10: When the current passenger passes the face contour authentication, a motion verification instruction is pushed to the current passenger so that the current passenger can feedback real-time motion information based on the motion verification instruction.
[0051] It should be understood that the method of this embodiment can be applied in civil aviation scenarios to implement identity verification of passengers before boarding, and can also be applied in other scenarios where user identity verification is required. The execution subject of the method of this embodiment can be a computer service device with data processing, program running and network communication, such as a security self-service verification gate, a civil aviation security access control device, a liveness detection system, etc., and can also be other electronic devices that implement the passenger identity verification method of this embodiment and implement the same or similar functions. The following takes the security self-service verification gate (hereinafter referred to as the "verification gate") as an example to illustrate this embodiment and the following embodiments.
[0052] It should be noted that when the current passenger triggers an identity authentication request at the verification gate, the verification gate can obtain the real-time facial image of the current passenger and extract the contour feature information corresponding to the real-time facial image, and then perform preliminary facial contour verification based on the contour feature information of the current passenger.
[0053] It is understandable that when the verification gate recognizes the presence of a user in the verification area based on infrared detection or receives a verification request instruction triggered by the user on the verification gate panel, the user can be regarded as the current passenger whose identity is to be verified.
[0054] It should be understood that the real-time facial image of the current passenger is first collected by the camera installed on the verification gate, and then the facial area is identified and located in the real-time facial image based on image processing technology, and then key feature points are extracted from the facial area, such as the location of the eyes, nose, and mouth, as well as contour features such as eyebrows and cheeks. Finally, the key feature points of the current user are matched with the key feature points of the facial contours of different passengers pre-stored in the verification gate association database, so as to make a facial contour authentication decision based on the result of feature matching and determine whether the current passenger has passed the facial contour authentication.
[0055] It is understandable that the action verification instruction may be an instruction displayed on the verification gate panel or an instruction broadcast by the verification gate voice when the current passenger passes the authentication profile authentication. The current passenger may perform relevant actions for verification in the verification area upon receiving the action verification instruction, so that the verification gate obtains real-time action information and performs subsequent action verification.
[0056] Step S20: performing a motion check according to the real-time motion information, and obtaining visually significant feature information of the current passenger when the motion check passes.
[0057] It should be understood that the database associated with the verification gate can also include pre-set standard key actions for different passengers, and the standard key actions are stored corresponding to the pre-stored key feature points of different passengers. The verification gate compares the acquired real-time action information with the standard key action corresponding to the current passenger in the database, and makes an action inspection decision based on the action result to determine whether the current passenger has passed the action inspection.
[0058] It is understandable that when the current passenger passes the motion inspection, the verification gate can output a significant feature acquisition prompt instruction, and the prompt instruction can also be implemented based on a panel display or voice broadcast.
[0059] It should be noted that the above-mentioned contour feature information is the basic feature in face recognition, focusing on the overall shape and general features of the face, and is used for preliminary face positioning and authentication. Different from the contour feature information, the visually significant feature information focuses on the obvious features of the face, such as ear piercing, number of marks, nose contour, mouth shape and other more detailed features, which can provide higher recognition accuracy.
[0060] It is understandable that the verification gate can prompt the user to get closer to the camera on the verification gate through the above-mentioned significant feature acquisition prompt instructions, and prompt the user to perform actions such as "turning" and "blinking" to obtain more complete visual significant feature information; the second camera with higher resolution on the verification gate can also be turned on to obtain a higher resolution real-time facial image of the current passenger in order to obtain more accurate visual significant feature information.
[0061] Step S30: When the visually significant feature information meets the matching condition of the preset reference tag group, it is determined that the current passenger has passed the identity authentication.
[0062] It should be understood that the preset reference tag group can also be stored in a database summary associated with the verification gate, and stored corresponding to the standard key actions and key point features of the above-mentioned different passengers.
[0063] It can be understood that when the verification gate obtains the visually significant feature information of the current passenger, it extracts a preset reference tag group corresponding to the current passenger from the database for comparison. The preset reference tag group includes several pre-stored visually significant feature points of the current passenger. The above-mentioned visual absorption feature information includes several visually significant feature points of the current passenger obtained in real time. These visually significant features are matched, and then the final identity authentication decision is made based on the matching results.
[0064] In a specific implementation, when the visually significant feature information of the current passenger obtained in real time meets the matching conditions of the reference tag group pre-stored in the database, it can be determined that the current passenger has passed the face verification of the visually significant features, that is, the identity verification of the current passenger has passed.
[0065] This embodiment pushes a motion check instruction to the current passenger when the current passenger passes the facial contour authentication so that the current passenger can feedback real-time motion information based on the motion check instruction; performs motion check according to the real-time motion information, and obtains the visually significant feature information of the current passenger when the motion check passes; and determines that the current passenger has passed the identity authentication when the visually significant feature information meets the matching conditions of the preset reference tag group. Since this embodiment can perform motion check and visually significant feature matching on the current passenger after facial contour authentication, the complexity of identity authentication is improved, and the risk of a single contour feature being counterfeited is greatly reduced, which is conducive to reducing the risk of misidentification.
[0066] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the passenger identity verification method of the present application.
[0067] In this embodiment, before step S20, the method further includes:
[0068] Step S01: Acquire the identity information database corresponding to the current passenger according to the face contour authentication result.
[0069] It should be noted that the identity information database includes: the passenger ID of the target passenger, the standard key action corresponding to the passenger ID, and a preset reference tag group. The standard key action is pre-set by the target passenger during the passenger identity registration process, and the preset reference tag group includes several reference significant features corresponding to the target passenger extracted from the passenger identity registration process.
[0070] It should be understood that when the current passenger passes the facial profile authentication, the verification gate determines the current passenger as a passenger in the database, namely the target passenger. Two passenger tags for further verification, namely the standard key action of the target passenger and the preset reference tag group, are stored under the passenger ID of the target passenger.
[0071] It is understandable that the verification information (key feature points of face contour, standard key actions and reference significant features) of different passengers pre-stored in the database can be generated by different passengers when they register. Passengers can register their identity in advance based on the passenger identity registration system associated with the verification gate to obtain a passenger ID, so that the above verification information is collected during the passenger identity registration process and stored in conjunction with the above passenger ID.
[0072] It should be understood that in order to further confirm whether the current passenger is the target passenger determined by the facial contour authentication, the current passenger's action can be checked according to the standard key action in the identity information library of the target passenger, and the current passenger's visual significant features can be matched according to the preset reference tag group in the identity information library of the target passenger.
[0073] Further, in order to illustrate the specific process of the action inspection, step S20 specifically includes steps S201 to S204:
[0074] Step S201: Acquire the standard key action in the identity information database.
[0075] It should be noted that the standard key action can be a combination of actions involving only the hands and face, such as touching the ears, holding the chin, etc.; it can also be a whole body action, such as standing on one foot, putting both hands together, etc. This embodiment does not limit this.
[0076] Step S202: Acquire the real-time action of the current passenger, and compare the real-time action with the standard key action.
[0077] It is understandable that when the verification gate outputs the motion verification instruction, it can obtain the real-time motion image of the current passenger through the camera in real time, and the motion verification instruction prompts the current passenger to maintain the current motion for a period of time to obtain accurate real-time motion.
[0078] It should be understood that several key points of the standard key action can be extracted, such as finger positions, foot positions, etc. Then, the corresponding positions of the key points of the action are located on the real-time action image to obtain the action state of each key point of the real-time action, thereby realizing the comparison between the real-time action and the standard key action.
[0079] Step S203: When the real-time action is consistent with the standard key action, it is determined that the current passenger has passed the action verification.
[0080] It should be understood that when the action states of the real-time action corresponding to each action key point satisfy the corresponding states of each action key point in the standard key action, the real-time action is deemed to be consistent with the standard key action, and the current passenger is determined to have passed the action inspection.
[0081] Step S204: When the real-time action is inconsistent with the standard key action, the current passenger is not the target passenger, and it is determined that the current passenger action verification fails.
[0082] It should be understood that when the action state of each action key point corresponding to the real-time action does not meet the corresponding state of one or more action key points in the standard key action, the real-time action is deemed inconsistent with the standard key action, and the current passenger is judged to have failed the action inspection, and then directly judged to have failed the identity verification of the current passenger. The verification gate issues a warning to notify relevant staff to handle it manually.
[0083] This embodiment obtains the standard key action in the identity information database; obtains the real-time action of the current passenger, and compares the real-time action with the standard key action; when the real-time action is consistent with the standard key action, the current passenger is determined to have passed the action inspection; when the real-time action is inconsistent with the standard key action, the current passenger is not the target passenger, and the current passenger is determined to have failed the action inspection. Since the current passenger is action-verified when the current passenger passes the face contour authentication in this embodiment, the action state of each action key point corresponding to the real-time action of the current passenger can be compared with the corresponding state of each action key point in the standard key action, preventing the use of static photos or videos for deception, ensuring that the verification object is alive and currently present, and realizing dynamic verification.
[0084] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the first and second embodiments can be referred to the above description, and will not be described in detail later. Figure 3 , Figure 3 This is a flow chart of the third embodiment of the passenger identity verification method of the present application.
[0085] In this embodiment, in order to illustrate the specific process of visually significant feature matching, before step S30, steps S001 to S003 are also included:
[0086] Step S001: Acquire a preset reference tag group in the identity information database.
[0087] It should be understood that the reference significant features in the preset reference tag group may be, for example, the number of ear holes, scar locations, and tattoo locations.
[0088] Step S002: Matching the visually salient characteristic information with a plurality of reference salient features in the preset reference tag group.
[0089] It is understandable that while the verification gate outputs the prompt instruction for obtaining the significant feature, it can turn on another camera installed on the verification gate, thereby assisting the aforementioned camera used for facial contour authentication to obtain a clearer real-time image of the current passenger, which contains visual significant feature information.
[0090] It should be understood that, in the above-mentioned real-time image containing visually significant feature information, each reference significant feature in the preset reference tag group may be matched item by item to determine whether the reference significant feature exists in the real-time image.
[0091] Step S003: judging whether the visually significant feature information satisfies the matching condition of the preset reference tag group according to the matching result.
[0092] It is understandable that the above matching result can be the number of matching items between the visually significant feature information in the real-time image and the preset reference tag group. A minimum matching threshold can be preset as the matching condition of the preset reference tag group. Therefore, step S30 specifically includes:
[0093] Step S301: When the number of matching items meets a preset matching item threshold, the current passenger is the target passenger, and it is determined that the identity authentication of the current passenger has passed.
[0094] It is understandable that the matching threshold may be a numerical threshold set based on the number of reference significant features in a preset reference tag group, or a percentage threshold set in a personalized manner. When the number of matching items between the visual significant feature information in the real-time image and the preset reference tag group reaches the preset matching threshold, that is, the visual significant feature information meets the matching condition of the preset reference tag group, the current passenger passes the visual significant feature matching, and the current passenger's identity verification can be deemed to have passed.
[0095] It should be understood that, on the contrary, when the number of matching items does not meet the preset matching item threshold, the current passenger is not the target passenger, and it is determined that the identity verification of the current passenger has failed.
[0096] It should be noted that when the visually significant feature information does not meet the matching conditions of the preset reference tag group, it means that the visually significant feature of the current passenger cannot match the preset reference tag group of the target passenger, so the current passenger is not the target passenger determined by the aforementioned face contour authentication. That is, the current passenger's identity verification fails, and the verification gate can also issue a warning to notify relevant staff to manually handle it.
[0097] It should also be noted that the order of the action inspection performed by the gate and the visual salient feature matching after the above-mentioned facial contour authentication can also be switched in a customized order.
[0098] In addition, you can refer to Figure 4 Explain the process of passengers passing the verification based on this application passenger identity verification method, Figure 4 This is a schematic diagram of the entire process of applying for passenger identity verification method.
[0099] exist Figure 4 In the verification gate located at the customs clearance, the real-time facial image of the current passenger is obtained based on the camera, and then the facial contour authentication is performed to realize the preliminary identity verification; if the facial contour authentication fails, the current passenger is directly rejected to pass through the customs, and if it passes, the current passenger is prompted to make a key action; the real-time action of the current passenger is compared with the standard key action to realize the action verification; if the action verification fails, the current passenger is rejected to pass through the customs or the relevant security personnel are notified, and if it passes, the visual significant features of the current passenger are obtained; the visual significant information of the current passenger is compared with the preset reference tag group to realize the visual significant feature matching; if the matching threshold is not reached, the current passenger is rejected to pass through the customs or the relevant security personnel are notified, and if it passes, the current passenger identity authentication is passed, and the verification gate is opened to allow the current passenger to pass through the customs. This passenger identity authentication method applied to the passenger clearance scenario combines multiple biometric recognition technologies for verification, ensuring the accuracy of identity authentication while taking into account the customs clearance efficiency.
[0100] In this embodiment, a preset reference tag group in the identity information database is obtained; the visually significant characteristic information is matched with a number of reference significant features in the preset reference tag group; and it is determined whether the visually significant feature information meets the matching conditions of the preset reference tag group based on the matching results. Since this embodiment further introduces visually significant feature matching after the motion test, it can effectively reduce misidentification caused by the similarity of a single feature, ensuring that only passengers who meet all verification conditions (face contour authentication, motion test, and visually significant feature matching) can pass identity authentication, further improving the accuracy of the verification results.
[0101] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the passenger identity verification method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0102] The present application also provides a passenger identity verification device, referring to Figure 5 , Figure 5 This is a schematic diagram of the module structure of the first embodiment of the passenger identity verification device of the present application, the device comprises:
[0103] The motion verification module 501 is used to push a motion verification instruction to the current passenger when the current passenger passes the face contour authentication so that the current passenger can feedback real-time motion information based on the motion verification instruction; and perform motion verification according to the real-time motion information;
[0104] The tag matching module 502 is used to obtain the visually significant feature information of the current passenger when the action check is passed; when the visually significant feature information meets the matching conditions of the preset reference tag group, determine that the current passenger has passed the identity authentication.
[0105] Furthermore, the device further includes: a profile authentication module 500 .
[0106] The contour authentication module 500 is used to obtain a real-time facial image of the current passenger and extract contour feature information corresponding to the real-time facial image; and perform facial contour authentication of the current passenger based on the contour feature information.
[0107] Furthermore, the action verification module 501 is also used to obtain an identity information database corresponding to the current passenger based on the face contour authentication result, the identity information database including: the passenger ID of the target passenger, the standard key action corresponding to the passenger ID, and a preset reference tag group, the standard key action is pre-set by the target passenger during the passenger identity registration process, and the preset reference tag group includes several reference significant features corresponding to the target passenger extracted from the passenger identity registration process.
[0108] Furthermore, the action verification module 501 is also used to obtain the standard key action in the identity information database; obtain the real-time action of the current passenger, and compare the real-time action with the standard key action; when the real-time action is consistent with the standard key action, it is determined that the current passenger has passed the action verification; when the real-time action is inconsistent with the standard key action, the current passenger is not the target passenger, and it is determined that the current passenger has failed the action verification.
[0109] Furthermore, the label matching module 502 is also used to obtain a preset reference label group in the identity information library; match the visually significant feature information with a number of reference significant features in the preset reference label group; and determine whether the visually significant feature information meets the matching conditions of the preset reference label group based on the matching result, and the matching result includes the number of matching items.
[0110] Furthermore, the tag matching module 502 is further configured to determine that, when the number of matching items meets a preset matching item threshold, the current passenger is the target passenger and that the identity verification of the current passenger is passed.
[0111] Furthermore, the tag matching module 502 is further configured to determine that, when the number of matching items does not meet a preset matching item threshold, the current passenger is not the target passenger and that the identity verification of the current passenger has failed.
[0112] This embodiment can perform motion inspection and visual salient feature matching on the current passenger after facial contour authentication, thereby increasing the complexity of identity authentication, greatly reducing the risk of a single contour feature being counterfeited, and helping to reduce the risk of misidentification.
[0113] The present application also provides a passenger identity verification system. Figure 6 , Figure 6 This is a schematic diagram of the module structure of the first embodiment of the passenger identity verification system of the present application. The system includes: the passenger identity verification device 50 and the passenger identity registration device 60 as described above. The passenger identity registration device 60 includes:
[0114] The registration initialization module 601 is used to obtain the real-time image information of the current passenger in response to the triggered registration instruction, wherein the real-time image information includes the facial contour information and the reference significant feature information; and generate the passenger ID corresponding to the current passenger according to the facial contour information;
[0115] A label extraction module 602 is used to determine a preset reference label group according to a number of reference significant features in the reference significant feature information;
[0116] An action setting module 603 is used to push an action key setting prompt to the current passenger and receive a standard key action set by the current passenger;
[0117] The information storage module 604 is used to associate and store the preset reference tag group, the standard key action and the passenger ID to obtain the identity information database of the current passenger.
[0118] In this embodiment, the passenger identity registration device can register identities for different passengers, collect verification information such as key feature points of facial contour, standard key actions, and reference significant features, and bind and store it with the generated passenger ID. After encryption algorithm, it is encrypted and stored in the database so that the passenger identity verification device can call it during verification, thereby ensuring the reliability of the passenger identity verification results.
[0119] The present application also provides a passenger identity authentication device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the passenger identity authentication method in the above-mentioned embodiment one.
[0120] Reference below Figure 7 , Figure 7 The schematic diagram of the structure of the passenger identity verification device of the present application. The passenger identity verification device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The passenger identity verification device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0121] like Figure 7As shown, the passenger identity verification device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the passenger identity verification device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the passenger identity verification device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a passenger identity verification device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0122] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0123] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0125] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A passenger identity verification method, It is characterized in that The method comprises: When the current passenger passes the facial contour authentication, a motion verification instruction is pushed to the current passenger so that the current passenger can feedback real-time motion information based on the motion verification instruction; Performing a motion check according to the real-time motion information, and obtaining visually significant feature information of the current passenger when the motion check passes; When the visually significant feature information meets the matching condition of the preset reference tag group, it is determined that the current passenger has passed the identity authentication.
2. The method according to claim 1, It is characterized in that Before the step of pushing a motion verification instruction to the current passenger when the current passenger passes the face contour authentication so that the current passenger can feedback real-time motion information based on the motion verification instruction, the method includes: Acquire a real-time facial image of the current passenger, and extract contour feature information corresponding to the real-time facial image; The facial contour of the current passenger is authenticated based on the contour feature information.
3. The method according to claim 1, It is characterized in that Before the step of performing action verification according to the real-time action information, the method further includes: An identity information database corresponding to the current passenger is obtained according to the face contour authentication result, wherein the identity information database includes: a passenger ID of the target passenger, a standard key action corresponding to the passenger ID, and a preset reference tag group, wherein the standard key action is pre-set by the target passenger during the passenger identity registration process, and the preset reference tag group includes a number of reference significant features corresponding to the target passenger extracted from the passenger identity registration process.
4. The method according to claim 3, It is characterized in that The step of performing action verification according to the real-time action information comprises: Obtaining a standard key action in the identity information repository; Acquire the real-time action of the current passenger, and compare the real-time action with the standard key action; When the real-time action is consistent with the standard key action, determining that the current passenger has passed the action verification; When the real-time action is inconsistent with the standard key action, the current passenger is not the target passenger, and it is determined that the current passenger action inspection has failed.
5. The method according to claim 3, It is characterized in that Before the step of determining that the current passenger has passed identity authentication when the visually significant feature information meets the matching condition of the preset reference tag group, the method includes: Obtaining a preset reference tag group in the identity information database; Matching the visually salient characteristic information with a plurality of reference salient features in the preset reference tag group; It is determined whether the visually significant feature information meets the matching condition of the preset reference tag group according to the matching result.
6. The method according to claim 5, It is characterized in that The matching result includes the number of matching items. When the visually significant feature information meets the matching condition of the preset reference tag group, the step of determining that the current passenger has passed the identity authentication includes: When the number of matching items meets a preset matching item threshold, the current passenger is the target passenger, and it is determined that the identity verification of the current passenger is passed.
7. The method according to claim 5, It is characterized in that After the step of judging whether the visually significant feature information meets the matching condition of the preset reference tag group according to the matching result, the method further includes: When the number of matching items does not meet the preset matching item threshold, the current passenger is not the target passenger, and it is determined that the identity verification of the current passenger has failed.
8. A passenger identity verification device, It is characterized in that The device comprises: A motion inspection module is used to push a motion inspection instruction to the current passenger when the current passenger passes the face contour authentication so that the current passenger can feedback real-time motion information based on the motion inspection instruction; and perform motion inspection according to the real-time motion information; The tag matching module is used to obtain the visually significant feature information of the current passenger when the action inspection is passed; when the visually significant feature information meets the matching conditions of the preset reference tag group, determine that the current passenger has passed the identity authentication.
9. A passenger identity verification system, It is characterized in that The system comprises a passenger identity verification device and a passenger identity registration device as claimed in claim 8, wherein the passenger identity registration device comprises: A registration initialization module, configured to obtain real-time image information of the current passenger in response to a triggered registration instruction, wherein the real-time image information includes facial contour information and reference significant feature information; and generate a passenger ID corresponding to the current passenger according to the facial contour information; A label extraction module, used to determine a preset reference label group according to a number of reference significant features in the reference significant feature information; An action setting module, used to push an action key setting prompt to the current passenger and receive a standard key action set by the current passenger; The information storage module is used to associate and store the preset reference tag group, the standard key action and the passenger ID to obtain the identity information library of the current passenger.
10. A passenger identity verification device, It is characterized in that The device comprises: a memory, a processor, and a passenger identity verification program stored in the memory and executable on the processor, wherein the passenger identity verification program is configured to implement the steps of the passenger identity verification method according to any one of claims 1 to 7.
