A door lock with real-name authentication function

Abstract

The application provides a door lock with real-name authentication function, comprising: an identity acquisition module for obtaining identity card information of a user to be authenticated; an infrared camera for obtaining an infrared image of the face of the user to be authenticated; an image processing module for detecting the infrared image and processing it into two-dimensional data to obtain a first processed image; an encrypted sending module for encrypting and sending the first processed image and the identity card information to a server; a receiving control module for receiving a real-name authentication result and opening the door lock when the real-name authentication result is passed; and a warning module for warning the user to be authenticated when the infrared image does not meet the requirements or the real-name authentication result is failed. The application can meet the regulatory requirements without changing the existing equipment, reduce the real-name authentication cost, improve the convenience, and ensure the safety.

Description

TECHNICAL FIELD

[0001] The present application relates to face authentication, in particular, to a door lock with real-name authentication function. BACKGROUND

[0002] In recent years, the development of homestays is rapid, and the market recognition is also higher and higher. Homestay brings a new experience to the guests, but at the same time, this new form of accommodation also brings many problems. The most important one is that there is no way to normally check in and register, and many times the homestay owner sends a room door password, and the guest directly checks in. This brings many security risks and social management problems. This problem is prominent for more and more self-service homestays. In self-service homestays, there is no service personnel on site, so it is difficult to perform effective real-name authentication, and relying on registration information is easy to be deceived by false information.

[0003] Self-service homestays need to complete real-name authentication before entering the room to ensure that the check-in person and the provided real-name authentication are consistent. In the existing real-name authentication technology, it is often necessary to collect clear RGB images or record videos. However, this is often difficult to achieve in self-service homestays. On the one hand, the door lock of the homestay needs to complete the two links of living body and comparison, and the existing mature living body algorithm relies on infrared and 3D images. Since the public security ID card database is RGB data, the commonly used comparison process needs to obtain RGB data through the face recognition door lock. In this way, the entire face recognition door lock needs to have both RGB cameras and infrared cameras, greatly increasing the cost. On the other hand, RGB is greatly affected by different environmental light, which can easily cause misidentification. In addition, if the RGB system is integrated into the face recognition door lock, it will slow down the starting speed of the door lock and greatly increase the power consumption, bringing great difficulties to the integration of the entire system.

[0004] In the existing access control system, many access controls are equipped with infrared cameras. Infrared cameras have low cost, low maintenance cost, and long service life, and can well meet the monitoring needs. At the same time, infrared cameras can be widely used in self-service homestays with only a small increase in cost. In the existing technology, since the images in the real-name authentication database of the public security system are RGB format images, it is generally believed that RGB images need to be collected to complete real-name authentication. Therefore, real-name authentication through infrared cameras has become a practical problem. SUMMARY

[0005] Therefore, the present application collects infrared images and ID card information, so that real-name authentication can be completed without collecting RGB images, so that self-service homestays can meet the regulatory requirements without changing the existing equipment, reducing the cost of real-name authentication, improving convenience, and also ensuring safety.

[0006] The application provides a door lock with real-name authentication function, characterized by comprising:

[0007] An identity collection module is configured to acquire identity card information of a user to be authenticated.

[0008] An infrared camera is configured to acquire an infrared image of a face of the user to be authenticated.

[0009] An image processing module is configured to detect the infrared image and process the infrared image into two-dimensional data to obtain a first processed image.

[0010] An encryption sending module is configured to encrypt and send the first processed image and the identity card information to a server.

[0011] A receiving control module is configured to receive a real-name authentication result and open the door lock when the real-name authentication result is passed.

[0012] An alarm module is configured to alarm the user to be authenticated when the infrared image does not meet the requirements or the real-name authentication result is failed.

[0013] Optionally, the door lock with real-name authentication function further comprises a comparison module.

[0014] The comparison module is configured to compare the infrared image of the face with an infrared image of a face that has passed the authentication when the user to be authenticated passes the real-name authentication and then re-flashes the face.

[0015] Optionally, the door lock with real-name authentication function further comprises an image processing module.

[0016] A target area unit is configured to acquire a target area of the user to be authenticated according to depth data in the infrared image.

[0017] An identification unit is configured to identify face information in the target area.

[0018] A judgment unit is configured to judge whether the face information meets the requirements of an authentication model.

[0019] A first processing unit is configured to process the infrared image to generate a first processed image if the face information meets the requirements of the authentication model.

[0020] A prompt unit is configured to prompt the user to re-authenticate if the face information does not meet the requirements of the authentication model.

[0021] Optionally, the authentication model requirements comprise that all key points of the face are identifiable and the occlusion ratio is less than a preset value.

[0022] Optionally, the door lock with a real-name authentication function has the following characteristics: the judgment unit includes:

[0023] a direction subunit, which is configured to judge the direction of the face of the user to be authenticated, and if the direction is within a preset range, the next step is performed; if the direction is out of the range, the user is determined to be not qualified.

[0024] a living body subunit, which is configured to determine whether the face pixel region is a living face image by using the prosthesis attack detection model, and output a living body detection result; the prosthesis attack detection model includes an input layer, a plurality of convolution processing modules, a maximum pooling layer, a first 2D convolution layer, and an output layer.

[0025] The input layer, the plurality of convolution processing modules, the maximum pooling layer, the first 2D convolution layer, and the output layer are sequentially connected.

[0026] The convolution processing module includes a second 2D convolution layer, a batch normalization layer, and a ReLU activation layer; the second 2D convolution layer, the batch normalization layer, and the ReLU activation layer are sequentially connected.

[0027] Optionally, the door lock with a real-name authentication function has the following characteristics: the first processing unit includes:

[0028] a key point subunit, which is configured to identify key points in the infrared image.

[0029] a preliminary image subunit, which is configured to map the infrared image to a two-dimensional plane to obtain a preliminary image.

[0030] an angle subunit, which is configured to adjust the angle of the preliminary image according to the key points, so that the face is perpendicular to the preliminary image.

[0031] a size subunit, which is configured to adjust the size of the preliminary image to a predetermined size to obtain a first processing image.

[0032] Optionally, the door lock with a real-name authentication function has the following characteristics: the encryption sending module includes:

[0033] a splitting unit, which is configured to split the first processing image into at least two sub-images and mark them respectively.

[0034] an identification code unit, which is configured to encrypt the plurality of sub-images and the identity card information respectively, and the encrypted information contains an identification code; the identification code is used to identify and match the plurality of encrypted information.

[0035] a sending unit, which is configured to send the encrypted information of the sub-images and the identity card information to a server respectively.

[0036] Optionally, the door lock with the real-name authentication function has the encryption and sending module, which includes:

[0037] The key point unit is configured to extract the key points and mark the labeled points in each key point.

[0038] The combination unit is configured to combine the multiple labeled points to obtain multiple combinations.

[0039] The identification code unit is configured to encrypt the multiple combinations and the ID card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the multiple encrypted information.

[0040] The sending unit is configured to send the encrypted information of the multiple combinations and the ID card information to a server respectively.

[0041] Optionally, the door lock with the real-name authentication function has the encryption and sending module, which includes:

[0042] The convolution unit is configured to convolve the first processed image to obtain a first convolution image.

[0043] The splitting unit is configured to split the first convolution image into at least two sub-images and mark them respectively.

[0044] The identification code unit is configured to encrypt the multiple sub-images and the ID card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the multiple encrypted information.

[0045] The sending unit is configured to send the encrypted information of the sub-images and the ID card information to a server respectively.

[0046] Optionally, the door lock with the real-name authentication function has the encryption and sending module, which includes:

[0047] The channel unit is configured to extract data of R, G and B channels of the first processed image to obtain an R channel image, a G channel image and a B channel image.

[0048] The marking unit is configured to mark the R channel image, the G channel image and the B channel image respectively.

[0049] The identification code unit is configured to encrypt the R channel image, the G channel image, the B channel image and the ID card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the multiple encrypted information.

[0050] The sending unit is configured to send the sub-image and the encrypted information of the identity certificate information to a server respectively.

[0051] Compared with the prior art, the present application has the following advantages:

[0052] The present application overcomes the technical prejudice that the face real-name authentication needs to collect the same RGB image as in the face database, reduces the technical cost of real-name authentication, improves the stability of real-name authentication, and can be integrated with the existing system, greatly improving the simplicity of real-name authentication, and being conducive to the effective landing of supervision.

[0053] In the present application, only the infrared image needs to be collected to realize real-name authentication, without the need for additional collection of RGB images, which can be directly integrated with the access control system, realizing the simplification of equipment, and can be directly applied to self-service homestays, improving the convenience of use, reducing the promotion cost, and meeting the regulatory requirements.

[0054] In the present application, the infrared image is recognized and processed, so that the user information transmitted is different from the original information, which fundamentally ensures the security of user authentication information, i.e. through appropriate setting, the authentication information of the user to be authenticated sent by the present application can only be used within the scope of the present application, thereby greatly improving the security of data transmission.

[0055] Meanwhile, in the present application, the data is encrypted and transmitted to the server, which can ensure that the real-name authentication information is not stolen, further ensuring the security of the personal privacy information of the user to be authenticated, and can be applied to more occasions with security requirements. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on the provided drawings. Other features, objects and advantages of the present application will become more apparent through reading the following detailed description of the non-limiting embodiments with reference to the accompanying drawings:

[0057] Figure 1 is a structural block diagram of a door lock with a real-name authentication function in an embodiment of the present application;

[0058] Figure 2 is a structural block diagram of another door lock with a real-name authentication function in an embodiment of the present application;

[0059] Figure 3 is a structural block diagram of an image processing module in an embodiment of the present application;

[0060] Figure 4 is a structure block diagram of a judging unit in an embodiment of the present application;

[0061] Figure 5 is a structure block diagram of a first processing unit in an embodiment of the present application;

[0062] Figure 6 is a structure block diagram of an encryption sending module in an embodiment of the present application;

[0063] Figure 7 is a structure block diagram of another encryption sending module in an embodiment of the present application;

[0064] Figure 8 is a structure block diagram of still another encryption sending module in an embodiment of the present application; and

[0065] Figure 9 is a structure block diagram of yet another encryption sending module in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The present application will be described in detail below with specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made. These are within the scope of the present application.

[0067] The terms "first", "second", "third", "fourth" and the like in the description, claims, and above-described drawings of the present application (if any) are used to distinguish similar objects, and do not necessarily have to be described in a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0068] The technical solutions of the present application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in some embodiments.

[0069] The door lock with real-name authentication function provided by the embodiment of the present application aims to solve the problems in the prior art.

[0070] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described again in some examples. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0071] Figure 1 The structure block diagram of a door lock with real-name authentication function in an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the door lock with real-name authentication function provided by the embodiment of the present application comprises: Figure 1

[0072] An identity collection module 1 is configured to obtain the identity card information of a user to be authenticated.

[0073] Specifically, the identity card information can be obtained by an identity card recognizer, by OCR image recognition, or by manual input by the user. An infrared camera can obtain an infrared image of the user to be authenticated for real-name authentication. When the identity card recognizer is provided, the data of the identity card recognizer can be read to obtain the identity card information. When the RGB camera is provided, the image can be obtained by taking a photo of the identity card, and the identity card information can be obtained by OCR recognition. When none of the above conditions is met, the user can provide the identity card information by manual input in the background. Of course, the identity card information can also be obtained by taking a photo of the identity card by a mobile phone, by OCR recognition, and by uploading in the background. When the identity card recognizer is not provided, the cost of the device can be reduced, the convenience of use of the user can be improved, and the application of the present application can be promoted. When the identity collection module 1 collects the identity card information, the face image contained in the identity card can be obtained. At this time, other modules perform real-name authentication based on the face image collected by the identity collection module 1, and the receiving control module 5 determines whether to open the door lock based on the result of the real-name authentication.

[0074] An infrared camera 2 is configured to obtain an infrared image of the face of the user to be authenticated.

[0075] Specifically, the infrared image of the user to be authenticated is obtained, a plurality of infrared images are continuously obtained, and the best one is selected as the infrared image for the next step to reduce the number of repeated authentications of the user to be authenticated and improve the efficiency. The infrared camera 2 can be a monocular camera or a binocular camera. The use of a monocular camera for the infrared camera can reduce the cost and facilitate promotion. The use of a binocular camera for the infrared camera can better resist attacks by artificial bodies.

[0076] An image processing module 3 is configured to detect the infrared image and process it into two-dimensional data to obtain a first processed image.

[0077] ​Specifically, since the data obtained by the infrared camera 3 is three-dimensional data, and the data compared by the real-name authentication is two-dimensional data, the data needs to be processed through different operations such as feature extraction, compression, encryption, segmentation, and mapped into two-dimensional data to obtain the first processed image. The first processed image has a smaller size, which facilitates data transmission and also does not affect the comparison result.

[0078] The encryption sending module 4 is configured to encrypt and send the first processed image and the identity card information to the server.

[0079] Specifically, according to the different operations such as feature extraction, compression, encryption, segmentation, and the like adopted on the image in the image processing module 3, corresponding processing is adopted in this step, and the identity card information is encrypted and sent to the server. Preferably, the first processed image and the identity card information are respectively encrypted and sent to the server to improve data security. When the face image of the person in the identity card is not collected by the identity collection module 1, the first processed image and the identity card information are sent to the server by the encryption sending module 4, and face comparison is performed at the server end, so that the real-name authentication function can still be completed when the user carries the identity card. The receiving control module 5 is configured to receive the real-name authentication result, and open the door lock when the real-name authentication result is passed.

[0080] Specifically, the receiving control module 5 receives the real-name authentication result sent back by the server. The real-name authentication result has only two kinds: pass and fail. When the authentication result is pass, it means that the current authentication personnel is consistent with the registered personnel, and the door lock is opened to allow the registered personnel to enter the room.

[0081] The warning module 6 is configured to alarm the user to be authenticated when the infrared image does not meet the requirements or the real-name authentication result is fail.

[0082] Specifically, when the warning module 6 alarms, it can be performed in the form of flashing of the indicator light on the door lock, or in the form of sending a message to the terminal such as the user's mobile phone. When it is performed in the form of flashing of the indicator light, different meanings can be represented by different flashing times, such as flashing once, indicating that the infrared image does not meet the requirements, and continuously flashing, indicating that the real-name authentication fails. When it is performed in the form of sending a message to the terminal such as the user's mobile phone, a short message can be sent to the user, or an in-application message can be sent to the user through the platform.

[0083] Figure 2 The figure is a structural block diagram of another door lock with a real-name authentication function in the embodiment of the present application. Compared with the previous embodiment, the door lock with a real-name authentication function provided by the embodiment of the present application further comprises a comparison module,

[0084] The comparison module 6 is configured to compare the infrared image of the face with the infrared image of the face that has passed the authentication when the user to be authenticated passes the face again after the real-name authentication.

[0085] Specifically, when the user to be authenticated passes the face in front of the door lock for the first time, the real-name authentication is performed in the manner of the previous embodiment, and the infrared image of the face that has passed the authentication is stored in the door lock. The stored face image is marked with the check-in validity period at the same time. The door lock deletes the face authentication data that is expired. When the same user passes the face again, the comparison module 6 first compares the infrared image obtained by the infrared camera 2 with the face image that has passed the authentication, is within the check-in validity period, and is stored in the door lock, and if the comparison is successful, sends a message that the authentication is passed to the receiving control module 5.

[0086] Figure 3 The figure processing module structure diagram in the embodiment of the present application is shown in FIG. 3. Compared with the previous embodiment, the image processing module 3 provided by the embodiment of the present application comprises:

[0087] The target area unit 301 is configured to obtain the target area of the user to be authenticated according to the depth data in the infrared image.

[0088] Specifically, since the infrared wave band detected by the infrared camera is generally 650nm-1400nm, which is in the near-infrared ultrashort wave and short wave range, the detection range is relatively close, and it can be well applied to face recognition. Due to the working principle of the infrared camera, the intensity of the face on the infrared image is obviously stronger than that of other objects, so the target area of the user to be authenticated can be quickly and accurately obtained. The target area contains the face information of the user to be authenticated, and can also contain other information.

[0089] The recognition unit 302 is configured to recognize the face information in the target area.

[0090] Specifically, the face information is obtained by detecting the target area through the face detection model, including the size, position and other information of the face. The data used in the embodiment is the original image, so the subsequent comparison is also 1:1 comparison, which can quickly compare the images and has high accuracy. The face detection model has many places, and the embodiment does not limit the specific way as long as the face information can be recognized.

[0091] The judgment unit 303 is configured to judge whether the face information meets the requirements of the authentication model.

[0092] Specifically, since the image matched with the ID information is a RGB format front face photo, in order to ensure the accuracy of the comparison, it is necessary to determine whether the face information is relatively close to the front face photo or can be converted. The requirement of the authentication model is to determine whether the face information can be reliably and accurately used for comparison with the front face photo. The authentication model requirement includes that the key points of the face can be recognized, and the occlusion ratio is less than a preset value. When the angle of the face information and the front face photo is similar, or the front face photo can be obtained through certain conversion, it is considered that the face information meets the requirements of the authentication model. Otherwise, it is considered that the face information does not meet the requirements of the authentication model. The authentication model requirement includes that the key points of the face can be recognized, and the occlusion ratio is less than a preset value.

[0093] The first processing unit 304 is configured to process the infrared image to generate a first processed image if the face information meets the authentication model requirement.

[0094] Specifically, if the face information meets the authentication model requirement, the infrared image can be processed and further used for real-name authentication. When processing the infrared image, feature extraction, compression, encryption, segmentation and other operations can be performed on the image to reduce the image size or improve security. Compression refers to converting a three-dimensional image into a two-dimensional image, or transforming a two-dimensional pixel array into a statistically unrelated data set, thereby removing redundant data and achieving the effect of reducing the image size. When processing the infrared image, multiple operations among the above operations can also be performed to achieve better results.

[0095] The prompting unit 305 is configured to prompt the user to re-authenticate if the face information does not meet the authentication model requirement.

[0096] Specifically, there are multiple ways to prompt the user to re-authenticate, which can be performed through the platform or through the infrared camera. When prompting the user through the platform, the user can be sent a message and prompt information indicating authentication failure, or the user can be sent a message and prompt information indicating authentication failure through the APP or the mini program. When performed through the infrared camera, the infrared camera can be blinked or equipped with a buzzer to make a sound, etc. Of course, multiple ways can be used to prompt at the same time.

[0097] Figure 4 The structure block diagram of the judging unit in the embodiment of the application is provided. Compared with the previous embodiment, the judging unit 303 provided by the embodiment of the application includes:

[0098] The orientation sub-unit 401 is configured to determine the orientation of the face of the user to be authenticated. If the orientation is within a preset range, the next step is performed; if the orientation is out of the range, it is determined that the requirement is not met.

[0099] Specifically, by analyzing the features of the infrared image, the face orientation of the user to be authenticated can be obtained. The ideal face orientation is directly facing the infrared camera, but due to various reasons, the face of the user to be authenticated is not always directly facing the infrared camera, but can have various angles. Therefore, in step S1, multiple infrared images are continuously acquired, and the angle closest to the direct angle is selected as the final infrared image. When performing face comparison on the server side, the angles of the faces do not need to be exactly the same, but the closer the angles, the better the comparison result. According to different comparison models, different face orientation ranges are required.

[0100] The living body subunit 402 is configured to determine whether the face pixel region is a living face image by using the prosthesis attack detection model, and output a living body detection result. The prosthesis attack detection model includes an input layer, a plurality of convolution processing modules, a maximum pooling layer, a first 2D convolution layer, and an output layer.

[0101] The input layer, the plurality of convolution processing modules, the maximum pooling layer, the first 2D convolution layer, and the output layer are sequentially connected.

[0102] The convolution processing module includes a second 2D convolution layer, a batch normalization layer, and a ReLU activation layer. The second 2D convolution layer, the batch normalization layer, and the ReLU activation layer are sequentially connected.

[0103] The output of the output layer is an N×N matrix. When the attack detection result is generated according to the N×N matrix,

[0104] Each output feature value in the N×N matrix is set with a weight value, and the weight value of the output feature value located at the center of the matrix is greater than the weight value of the output feature value located at the periphery of the matrix.

[0105] Each output feature value in the N×N matrix output by the output layer is subjected to living body judgment according to a pre-set first threshold value, and the number of output feature values greater than the first threshold value is generated.

[0106] According to the number of output feature values, a proportion value of the number of output feature values to the total number of output feature values in the N×N matrix is generated.

[0107] According to the comparison between the proportion value and a pre-set second threshold value, it is determined whether the target face corresponding to the image is a living body.

[0108] To improve the accuracy of face liveness detection, in some embodiments, a structured light projector is further included. Through the infrared camera and the structured light projector, an infrared image and a 3D image of the face of the user to be authenticated are obtained; the infrared image is detected and processed into two-dimensional data to obtain a first processed image, and face liveness recognition is performed on the 3D image.

[0109] The face liveness detection in this embodiment is performed through a convolutional neural network, and the ratio value of the output feature problem is compared with a pre-set second threshold value through multi-layer convolution calculation to determine whether the target face is a live body, which has higher attack resistance and can ensure the quality of real-name authentication.

[0110] Figure 5 The first processing unit structure diagram in the embodiment of the present application is shown in FIG. 3. Compared with the previous embodiment, the first processing unit 304 provided in the embodiment of the present application includes:

[0111] The key point subunit 501 is configured to identify key points in the infrared image.

[0112] Specifically, the key points include eyebrows, eyes, nose, mouth, facial contour area, and ears. To ensure the accuracy of face comparison, as many key points as possible need to be obtained. Through the identification of key points, the image can be further processed, and can be used for face comparison.

[0113] The preliminary image subunit 502 is configured to map the infrared image to a two-dimensional plane to obtain a preliminary image.

[0114] Specifically, since only two-dimensional information is needed for face comparison, the infrared image is mapped to a two-dimensional plane in this step, which will not adversely affect face comparison, and can reduce the size of the image.

[0115] The angle subunit 503 is configured to adjust the angle of the preliminary image according to the key points, so that the face is perpendicular to the preliminary image.

[0116] Specifically, adjusting the angle of the image will cause certain changes in the positional relationship of the image, but it is beneficial for subsequent face comparison. It should be noted that although the angle subunit 503 in this embodiment is executed after the preliminary image subunit 502, a person skilled in the art can also execute the angle subunit 503 before the preliminary image subunit 502, and the same technical effect can be achieved. Therefore, the scheme in which the angle subunit 503 is executed before the preliminary image subunit 502 is also within the protection scope of the present application.

[0117] The size subunit 504 is configured to adjust the size of the preliminary image to a predetermined size to obtain a first processed image.

[0118] Specifically, the size of the infrared image is different from that of the RGB image, so the size of the preliminary image needs to be adjusted to a predetermined size to better perform face comparison with the images in the image library. When adjusting the size of the preliminary image, uniform reduction of the entire image can be used, or a cropping method can be used, as long as the face data is complete and clear in the image.

[0119] The embodiment processes the infrared image and adjusts the angle to obtain a first processed image, which has an angle close to that of the face in the face library, thereby ensuring the effect of face comparison. Meanwhile, the data of the embodiment is three-dimensional data, and the adjustment of the face angle is more accurate, and the loss of the adjusted image is smaller.

[0120] Figure 6 A structure block diagram of an encryption sending module in an embodiment of the present application is provided. Compared with the previous embodiment, the encryption sending module 4 provided by the embodiment of the present application comprises:

[0121] The splitting unit 601 is configured to split the first processed image into at least two sub-images and mark them respectively.

[0122] Specifically, splitting the first processed image into at least two sub-images can make the data more dispersed during transmission, thereby making the data more secure. During splitting, an average splitting method is used. During marking, the splitting method is also marked. Taking the case of splitting the first processed image into three sub-images as an example, the image is equally divided horizontally, a represents horizontal equal division, and the sub-images are sequentially marked as a1, a2 and a3.

[0123] The identification code unit 602 is configured to encrypt the plurality of sub-images and the identity card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the plurality of encrypted information.

[0124] Specifically, the identification code is used for identifying and matching the plurality of encrypted information. The identification codes of the same image are the same, which can be used to distinguish different image information on the server side. Taking the previous example, if the identification code of the image is ABCDEFG, the identification codes of the sub-images are ABCDEFG-a1, ABCDEFG-a2 and ABCDEFG-a3.

[0125] The sending unit 603 is configured to send the encrypted information of the sub-images and the identity card information to the server respectively.

[0126] Specifically, all the sub-images and the identity card information are encrypted respectively and sent to the server. During encryption, the sub-images and the identity card information use the same encryption method. During sending, the sub-images and the identity card information can be sent at different times or sent to different servers, and the image fusion is completed by the server side.

[0127] The embodiment splits the image into at least two sub-images, and marks them, so that the data is safer during transmission, and information can be sent to different servers, so that the security is greatly improved.

[0128] Figure 7 Another encryption sending module structure block diagram in the embodiment of the application. Compared with the previous embodiment, the encryption sending module 4 provided by the embodiment of the application comprises:

[0129] The key point unit 701 is configured to extract the key points and mark the marked points in each of the key points.

[0130] Specifically, all the key points are extracted, and a plurality of marked points in each key point are marked. The marking content includes the key point position and the serial number. Through all the information of the key point position and the serial number, the features of the face can be restored, so that face comparison can be performed.

[0131] The combination unit 702 is configured to combine the plurality of marked points to obtain a plurality of combinations.

[0132] Specifically, since the marked points are specific and unique, the marked points can be combined arbitrarily, and deviation will not occur when the marked points restore the face feature data. The combination mode is fixed, and can also be random. For example, the key points can be combined, and a plurality of marked points of the same key point can be combined together; the serial numbers can be combined, and the serial numbers can be combined in groups of 10; the position relationship can be combined, and the marked points with similar positions can be combined as a group; or random classification combination can be performed.

[0133] The identification code unit 703 is configured to encrypt the plurality of combinations and the identity card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the plurality of encrypted information.

[0134] The sending unit 704 is configured to send the encrypted information of the plurality of combinations and the identity card information to the server respectively.

[0135] The embodiment directly acquires the key point information used for comparing the face, greatly reduces the amount of transmission data, and can greatly improve the security of the data through a plurality of combination modes and encryption measures. Different feature point information can achieve different effects, and only the feature point data itself also plays an encryption role. Through different marked point modes, the data of the application naturally has high security.

[0136] Figure 8It is another encryption sending module structure block diagram in the embodiment of the present application. Compared with the previous embodiment, the encryption sending module 4 provided by the embodiment of the present application comprises:

[0137] The convolution unit 801 is configured to perform convolution on the first processed image to obtain a first convolution image.

[0138] Specifically, the convolution processing of the image can obtain a smaller size image without losing feature information. In addition, the image after convolution is only applicable to the same convolution kernel, which can increase the security.

[0139] The splitting unit 802 is configured to split the first convolution image into at least two sub-images and mark them respectively.

[0140] Specifically, the first convolution image is split and marked. The splitting and marking method is the same as the previous embodiment, which will not be described here.

[0141] The identification code unit 803 is configured to encrypt the plurality of sub-images and the identity information respectively, and the encrypted information contains an identification code; the identification code is used to identify and match the plurality of encrypted information.

[0142] The sending unit 804 is configured to send the encrypted information of the sub-images and the identity information to the server respectively.

[0143] In this embodiment, the data is processed by convolution, and the data after convolution is processed and sent, so that the data sent can be better processed only in the case of the same convolution kernel, which also plays an encryption role. In combination with the encryption measures during transmission, the data transmission is more secure.

[0144] Figure 9 It is another encryption sending module structure block diagram in the embodiment of the present application. Compared with the previous embodiment, the encryption sending module 4 provided by the embodiment of the present application comprises:

[0145] The channel unit 901 is configured to extract R, G and B channel data of the first processed image to obtain an R channel image, a G channel image and a B channel image.

[0146] Specifically, considering that the standard photo for face comparison is an RGB image, only R, G and B channel data are needed to complete face comparison. Compared with the first processed image, the R, G and B channel data greatly reduces the data amount of the image, and at the same time enables data sharing with higher security.

[0147] The marking unit 902 is configured to mark the R channel image, the G channel image and the B channel image respectively.

[0148] Specifically, at the time of marking, the three channel graphs are marked respectively. It should be noted that the data of each channel can still be further split and marked, and the splitting and marking method is referred to the foregoing embodiments, which will not be described here.

[0149] The identification code unit 903 is configured to encrypt the R channel graph, the G channel graph, the B channel graph and the ID card information respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching the plurality of encrypted information.

[0150] The sending unit 904 is configured to send the sub-image and the encrypted information of the ID card information to a server respectively.

[0151] The embodiment extracts the data of R, G and B three channels, greatly reduces the size of the transmitted image, and the separate transmission also plays an encryption role. Only single data cannot crack the real-name authentication data, and the encrypted information during transmission greatly increases the security of data transmission.

[0152] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts of each embodiment can be referred to each other. The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications of the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0153] The specific embodiments of the present application are described above. It should be understood that the present application is not limited to the above specific embodiments, and those skilled in the art can make various modifications or changes within the scope of the claims, which does not affect the essential content of the present application.

Claims

1. A door lock with a real name authentication function, characterized by, The application relates to a real-name authentication system and method. An identity collection module is arranged to obtain identity card information of a user to be authenticated. An infrared camera is arranged to obtain an infrared image of a face of the user to be authenticated. An image processing module is arranged to detect the infrared image and process the infrared image into two-dimensional data to obtain a first processed image. An encryption sending module is arranged to encrypt and send the first processed image and the identity card information to a server. A receiving control module is arranged to receive a real-name authentication result and open a door lock when the real-name authentication result is passed. An alarm module is arranged to alarm the user to be authenticated when the infrared image does not meet requirements or the real-name authentication result is failed. The encryption sending module comprises: A key point unit is arranged to extract key points and mark each key point. A combination unit is arranged to combine a plurality of marked points to obtain a plurality of combinations. An identification code unit is arranged to encrypt the combinations and the identity card information respectively, and identification codes are contained in the encrypted information; the identification codes are used to identify and match a plurality of encrypted information. A sending unit is arranged to send the encrypted information of the combinations and the identity card information to the server respectively.

2. A door lock with a real name authentication function, characterized by, The application relates to a real-name authentication system and method. An identity collection module is arranged to obtain identity card information of a user to be authenticated. An infrared camera is arranged to obtain an infrared image of a face of the user to be authenticated. An image processing module is arranged to detect the infrared image and process the infrared image into two-dimensional data to obtain a first processed image. An encryption sending module is arranged to encrypt and send the first processed image and the identity card information to a server. A receiving control module is arranged to receive a real-name authentication result and open a door lock when the real-name authentication result is passed. An alarm module is arranged to alarm the user to be authenticated when the infrared image does not meet requirements or the real-name authentication result is failed. The encryption sending module comprises: A convolution unit is arranged to convolve the first processed image to obtain a first convolution image. A splitting unit is arranged to split the first convolution image into at least two sub-images and mark the sub-images respectively. An identification code unit is arranged to encrypt the sub-images and the identity card information respectively, and identification codes are contained in the encrypted information; the identification codes are used to identify and match a plurality of encrypted information. A sending unit is arranged to send the encrypted information of the sub-images and the identity card information to the server respectively.

3. A door lock with a real name authentication function, characterized by comprising: The application relates to a real-name authentication system and method. An identity collection module is arranged to obtain identity card information of a user to be authenticated. An infrared camera is arranged to obtain an infrared image of a face of the user to be authenticated. An image processing module is arranged to detect the infrared image and process the infrared image into two-dimensional data to obtain a first processed image. An encryption sending module is arranged to encrypt and send the first processed image and the identity card information to a server. A receiving control module is arranged to receive a real-name authentication result and open a door lock when the real-name authentication result is passed. An alarm module is arranged to alarm the user to be authenticated when the infrared image does not meet requirements or the real-name authentication result is failed. The encryption sending module comprises: A channel unit is configured to extract R, G and B channel data of the first processed image to obtain an R channel image, a G channel image and a B channel image. A marking unit is configured to mark the R channel image, the G channel image and the B channel image respectively. An identification code unit is configured to encrypt the R channel image, the G channel image, the B channel image and the identity information respectively, and the encrypted information contains an identification code. A sending unit is configured to send the sub-image and the encrypted information of the identity information to a server respectively.

4. The door lock with a real name authentication function according to claim 1, 2 or 3, characterized in that, The comparison module is further configured to compare the infrared image of the face with the infrared image of the passed authentication when the user to be authenticated passes the real-name authentication and then brushes the face again. The image processing module includes:

5. The door lock with a real name authentication function according to claim 1, 2 or 3, characterized in that, A target area unit is configured to obtain a target area of the user to be authenticated according to the depth data in the infrared image. An identification unit is configured to identify face information in the target area. A judgment unit is configured to judge whether the face information meets the requirements of an authentication model. A first processing unit is configured to process the infrared image to generate a first processed image if the face information meets the requirements of the authentication model. A prompt unit is configured to prompt the user to re-authenticate if the face information does not meet the requirements of the authentication model. The authentication model requirements include that all key points of the face are identifiable and the occlusion ratio is less than a preset value.

6. The door lock with a real name authentication function according to claim 5, characterized in that, The judgment unit includes:

7. The door lock with a real name authentication function according to claim 5, characterized in that, An orientation sub-unit is configured to judge the orientation of the face of the user to be authenticated, and if the orientation is within a preset range, the next step is performed; if the orientation is beyond the range, it is judged that the requirements are not met. A live sub-unit is configured to judge whether a face pixel area is a live face image by a prosthesis attack detection model and output a live detection result; the prosthesis attack detection model includes an input layer, a plurality of convolution processing modules, a maximum pooling layer, a first 2D convolution layer and an output layer. The input layer, the plurality of convolution processing modules, the maximum pooling layer, the first 2D convolution layer and the output layer are sequentially connected. The convolution processing module includes a second 2D convolution layer, a batch normalization layer and a ReLU activation layer; the second 2D convolution layer, the batch normalization layer and the ReLU activation layer are sequentially connected. The first processing unit includes:

8. The door lock with a real name authentication function according to claim 5, characterized in that, A key point sub-unit is configured to identify key points in the infrared image. A preliminary image sub-unit is configured to map the infrared image to a two-dimensional plane to obtain a preliminary image. An angle sub-unit is configured to adjust the angle of the preliminary image according to the key points so that the face is perpendicular to the preliminary image. A size sub-unit is configured to adjust the size of the preliminary image to a predetermined size to obtain a first processed image. The encryption sending module includes:

9. The door lock with a real name authentication function according to claim 1, 2 or 3, characterized in that, A splitting unit is configured to split the first processed image into at least two sub-images and mark them respectively. An identification code unit is configured to encrypt the plurality of sub-images and the identity information respectively, and the encrypted information contains an identification code; the identification code is used to identify and match the plurality of encrypted information. ​ The sending unit is configured to send the sub-image and the encrypted information of the identity certificate information to a server respectively.

Images