CN116935520A

CN116935520A - Door lock with real name authentication function

Info

Publication number: CN116935520A
Application number: CN202210865809.5A
Authority: CN
Inventors: 胡涛; 王耀民; 朱力; 吕方璐; 汪博
Original assignee: Shenzhen Guangjian Technology Co Ltd
Current assignee: Shenzhen Guangjian Technology Co Ltd
Priority date: 2022-04-08
Filing date: 2022-07-22
Publication date: 2023-10-24

Abstract

The application provides a door lock with real name authentication function, comprising: the identity acquisition module is used for acquiring the identity card information of the user to be authenticated; the infrared camera is used for acquiring an infrared image of the face of the user to be authenticated; the image processing module is used for detecting the infrared image and processing the infrared image into two-dimensional data to obtain a first processed image; the encryption sending module is used for encrypting and sending the first processed image and the identity card information to a server; the receiving control module is used for receiving a real-name authentication result and unlocking a door lock when the real-name authentication result is passed; and the warning module is used for warning the user to be authenticated when the infrared diagram does not meet the requirement or the real-name authentication result is that the user to be authenticated does not pass. The application can meet the supervision requirement without changing the prior equipment, reduces the real-name authentication cost, improves the convenience and ensures the safety.

Description

Door lock with real name authentication function

Technical Field

The application relates to face authentication, in particular to a door lock with a real-name authentication function.

Background

In recent years, the development of the people's sink is rapid, and the market acceptance is also higher and higher. The accommodation brings a brand new accommodation experience to guests, but at the same time, the novel accommodation form brings a plurality of problems. Most important points are that the check-in registration is normally handled, and the resident and the eastern of the house send out a door password in many cases, so that the tenant can directly check in. This brings about many potential safety hazards and social management problems. This problem is prominent for more and more self-service citizens. In self-help hosts, effective real-name authentication is difficult because no service personnel exist, and the self-help hosts can be easily deceived by false information provided by means of registration information.

The self-service sink needs to complete real-name authentication before entering a room, and ensures that the real-name authentication provided by the resident is consistent. In the existing real-name authentication technology, clear RGB images are often required to be collected or a video recording mode is adopted for carrying out. Which is often difficult to achieve for self-help citizens. On one hand, the door lock of the civil sink needs to complete two links of living body and comparison, the existing mature living body algorithm depends on infrared and 3D images, and the public security identity card library is RGB data, so that the RGB data is required to be obtained through the face door lock in the common comparison process. Therefore, the whole face-brushing door lock needs to be provided with the RGB camera and the infrared camera at the same time, so that the cost is greatly increased; on the other hand, RGB is greatly influenced by illumination of different environments, and misidentification is easily caused. In addition, if the RGB system is integrated in the face-brushing door lock, the starting speed of the door lock is slow, the power consumption is greatly increased, and great difficulty is brought to the integration of the whole system.

In the existing access control system, a plurality of access control devices are provided with infrared cameras. The infrared camera is low in cost, low in maintenance cost and long in service life, and can well meet the monitoring requirement. Meanwhile, the infrared camera can be applied to self-help citizens in a large quantity, and only a small amount of cost is increased. In the prior art, because the image in the real-name authentication database of the public security system is an RGB format image, it is generally considered that the real-name authentication can be completed only by collecting the RGB image. Therefore, real-name authentication through the infrared camera becomes a problem with practical significance.

Disclosure of Invention

Therefore, the application can complete real-name authentication without collecting RGB images by collecting the infrared image and the identity card information, thereby leading the self-help citizen to meet the supervision requirement without changing the prior equipment, reducing the real-name authentication cost, improving the convenience and ensuring the safety.

The application provides a door lock with real name authentication function, which is characterized by comprising:

the identity acquisition module is used for acquiring the identity card information of the user to be authenticated;

the infrared camera is used for acquiring an infrared image of the face of the user to be authenticated;

the image processing module is used for detecting the infrared image and processing the infrared image into two-dimensional data to obtain a first processed image;

the encryption sending module is used for encrypting and sending the first processed image and the identity card information to a server;

the receiving control module is used for receiving a real-name authentication result and unlocking a door lock when the real-name authentication result is passed;

and the warning module is used for warning the user to be authenticated when the infrared diagram does not meet the requirement or the real-name authentication result is that the user to be authenticated does not pass.

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

and the comparison module is used for comparing the infrared image of the human face with the infrared image passing the authentication when the user to be authenticated brushes the face again after the user to be authenticated passes the real-name authentication.

Optionally, the door lock with real name authentication function is characterized in that the image processing module includes:

a target area unit, configured to obtain a target area of the user to be authenticated according to depth data in the infrared map;

the identification unit is used for identifying the face information in the target area;

the judging unit is used for judging whether the authentication model requirements are met according to the face information;

the first processing unit is used for processing the infrared image to generate a first processed image if the face information meets the authentication model requirement;

and the prompting unit is used for prompting the user to re-authenticate if the face information does not meet the authentication model requirement.

Optionally, the door lock with the real-name authentication function is characterized in that the authentication model requirement includes: the key points of the face can be identified, and the shielding proportion is smaller than a preset value.

Optionally, the door lock with the real name authentication function is characterized in that the judging unit includes:

a direction subunit, configured to determine a direction of the face of the user to be authenticated, and if the direction is within a preset range, perform the next step; if the range is out, judging that the requirements are not met;

the living body subunit is used for judging whether the human face pixel area is a living body human face image or not through the prosthesis attack detection model and outputting a living body detection result; the prosthesis attack detection model comprises 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 convolution processing modules, the maximum pooling layer, the first 2D convolution layer and the output layer are sequentially connected;

the convolution processing module comprises a second 2D convolution layer, a batch normalization layer and a ReLU activation layer; the second 2D convolution layer, the bulk normalization layer, and the ReLU activation layer are connected in sequence.

Optionally, the door lock with the real name authentication function is characterized in that the first processing unit includes:

a key point subunit, configured to identify a key point in the infrared map;

a preliminary image subunit, configured to map the infrared image to a two-dimensional plane, so as to obtain a preliminary image;

an angle subunit, configured to adjust an angle of the preliminary image according to the key point, so that a face orientation is perpendicular to the preliminary image;

and the size subunit is used for adjusting the size of the preliminary image to a preset size to obtain a first processed image.

Optionally, the door lock with real name authentication function is characterized in that the encryption sending module includes:

the splitting unit is used for splitting the first processed image into at least two sub-images and marking the sub-images respectively;

the identification code unit is used for encrypting the plurality of sub-images and the identity card information respectively, and the encrypted information contains identification codes; the identification code is used for identifying and matching a plurality of encrypted information;

and the sending unit is used for respectively sending the sub-images and the encrypted information of the identity card information to a server.

the key point unit is used for extracting the key points and marking the marking points in each key point;

the combination unit is used for combining the plurality of marking points to obtain a plurality of combinations;

the identification code unit is used for encrypting a plurality of combinations and the identity card information respectively, and the encrypted information contains identification codes; the identification code is used for identifying and matching a plurality of encrypted information;

and the sending unit is used for respectively sending the plurality of combinations and the encrypted information of the identity card information to the server.

the convolution unit is used for convolving the first processed image to obtain a first convolution image;

the splitting unit is used for splitting the first convolution image into at least two sub-images and marking the sub-images respectively;

a channel unit, configured to extract R, G, B three-channel data from the first processed image, and obtain an R-channel map, a G-channel map, and a B-channel map;

a marking unit for marking the R channel map, the G channel map, and the B channel map, respectively;

the identification code unit is used for encrypting the R channel diagram, the G channel diagram, the B channel diagram and the identity card information respectively, and the encrypted information contains identification codes; the identification code is used for identifying and matching a plurality of encrypted information;

Compared with the prior art, the application has the following beneficial effects:

the application overcomes the technical prejudice that the real name authentication of the face needs to acquire the RGB images the same as those in the face library, reduces the technical cost of the real name authentication, improves the stability of the real name authentication, can be fused with the existing system, greatly improves the simple and convenient degree of the real name authentication, and is beneficial to effectively falling to the ground of supervision.

According to the application, the real name authentication can be realized only by collecting the infrared image, the RGB image is not required to be additionally collected, the device can be directly integrated with an access control system, the simplification of equipment is realized, the device can be directly applied to self-help citizens, the convenience of use is improved, the popularization cost is reduced, and the supervision requirement is met.

The application makes the transmitted user information different from the original information by identifying and processing the infrared image, thereby fundamentally ensuring the safety of the user authentication information, namely, the authentication information of the user to be authenticated, which is sent by the application, can only be used in the scope of the application by proper setting, thereby greatly improving the safety of data transmission.

Meanwhile, the data are encrypted and transmitted to the server, so that real-name authentication information can be prevented from being stolen, the security of personal privacy information of a user to be authenticated is further ensured, and the method and the device can be applied to more occasions with security requirements.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art. Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:

FIG. 1 is a block diagram of a door lock with real name authentication function according to an embodiment of the present application;

FIG. 2 is a block diagram of another door lock with real-name authentication function according to an embodiment of the present application;

FIG. 3 is a block diagram illustrating an image processing module according to an embodiment of the present application;

FIG. 4 is a block diagram illustrating a judging unit according to an embodiment of the present application;

FIG. 5 is a block diagram illustrating a first processing unit according to an embodiment of the present application;

FIG. 6 is a block diagram illustrating an encryption transmission module according to an embodiment of the present application;

FIG. 7 is a block diagram illustrating another encryption transmission module according to an embodiment of the present application;

FIG. 8 is a block diagram illustrating another encryption transmission module according to an embodiment of the present application; and

fig. 9 is a block diagram of an encryption transmission module according to an embodiment of the present application.

Detailed Description

The present application will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present application, but are not intended to limit the application in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present application.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.

The embodiment of the application provides a door lock with a real-name authentication function, which aims to solve the problems in the prior art.

The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

Fig. 1 is a block diagram of a door lock with real name authentication function according to an embodiment of the present application. As shown in fig. 1, a door lock with real name authentication function provided in an embodiment of the present application includes:

the identity acquisition module 1 is used for acquiring the identity card information of the user to be authenticated.

Specifically, the identification card information can be obtained by an identification card identifier, or can be obtained by OCR image recognition, or can be manually input by a user. The infrared camera can obtain an infrared image of the user to be authenticated and is used for real-name authentication. When the identity card identifier is provided, the data of the identity card identifier can be read to obtain the identity card information. When the RGB camera exists, an image can be obtained by photographing the identity card, and the identity card information can be obtained through OCR recognition. When none of the above conditions is met, the user can provide the identification card information in the background by means of manual input. Of course, the mobile phone can also shoot an identity card photo, perform OCR recognition and upload the identity card photo through the background. When the identity card identifier is not arranged, the equipment cost can be reduced, the convenience of the user in use is improved, and the popularization and application of the application are facilitated. When the identity acquisition module 1 acquires the identity card information, a face image contained in the identity card can be obtained, at this time, other modules perform real-name authentication according to the face image acquired by the identity acquisition module 1, and the receiving control module 5 determines whether to unlock the door lock according to the real-name authentication result.

And the infrared camera 2 is used for acquiring an infrared image of the face of the user to be authenticated.

Specifically, when the infrared image of the user to be authenticated is obtained, a plurality of infrared images are continuously obtained, and the optimal infrared image is selected from the infrared images as the infrared images entering the subsequent steps, so that the repeated authentication times of the user to be authenticated are reduced, and the efficiency is improved. The infrared camera 2 may be a monocular camera or a binocular camera. The infrared camera adopts a monocular camera, so that the cost can be reduced, and the popularization is facilitated. The infrared camera adopts a binocular camera, so that the prosthesis attack can be better resisted.

The image processing module 3 is used for detecting the infrared image and processing the infrared image into two-dimensional data to obtain a first processed image;

specifically, since the data obtained by the infrared camera 3 is three-dimensional data and the data compared by real-name authentication is two-dimensional data, it is necessary to process the data by different operations such as feature extraction, compression, encryption, segmentation, and the like, and map the processed data into two-dimensional data, thereby obtaining a first processed image. The first processed image has smaller size, is convenient for data transmission, and can not influence the comparison result.

And the encryption sending module 4 is used for encrypting and sending the first processed image and the identity card information to a server.

Specifically, according to the different operations of feature extraction, compression, encryption, segmentation and the like adopted for the image in the image processing module 3, corresponding processing is adopted in the step, and the corresponding processing and the identification card information are encrypted and sent to the server. Preferably, the first processing image and the identity card information are respectively encrypted and sent to a server so as to improve data security. When the identity acquisition module 1 does not acquire the face image in the identity card, the encryption transmission module 4 transmits the first processed image and the identity card information to the server, and face comparison is carried out at the server, so that the real-name authentication function can be still completed when the user carries the identity card. And the receiving control module 5 is used for receiving the real-name authentication result and unlocking the door lock when the real-name authentication result is passed.

Specifically, the receiving control module 5 receives the real-name authentication result sent back from the server. There are only two kinds of real-name authentication results: pass and fail. When the authentication result is passed, the current authentication person is consistent with the registered person, and the door lock is opened to enable the registered person to enter a room.

And the warning module 6 is used for warning the user to be authenticated when the infrared diagram does not meet the requirement or the real-name authentication result is that the infrared diagram fails.

Specifically, when the alarm module 6 alarms, the alarm may be performed by flashing an indicator light on the door lock, or by sending a message to a terminal such as a mobile phone of the user. When the indicator lights flash, different meanings can be indicated by different flashing times, such as flashing once, so that the infrared image is not in accordance with the requirements; and continuously flashing to indicate that the real-name authentication fails. When a message is sent to a terminal such as a mobile phone of a user, a short message can be sent to the user, and an in-application message can also be sent to the user through a platform.

Fig. 2 is a block diagram of another door lock with real-name authentication function according to an embodiment of the present application. Compared with the previous embodiment, the door lock with the real-name authentication function provided by the embodiment of the application also comprises a comparison module,

and the comparison module 6 is used for comparing the infrared image of the human face with the infrared image passing the authentication when the user to be authenticated brushes the face again after the user to be authenticated passes the real-name authentication.

Specifically, when a user to be authenticated swipes a face in front of the door lock for the first time, real-name authentication is performed in the manner in the above embodiment, and an infrared image of the face passing the authentication is stored in the door lock. The stored face map will be identified at the same time as the expiration date. The door lock may delete expired face authentication data. When the same user brushes the face again, the comparison module 6 compares the infrared image obtained by the infrared camera 2 with the face image which is authenticated, is stored in the door lock in the valid period of the check-in, and if the comparison is successful, sends a message that the authentication is passed to the receiving control module 5.

Fig. 3 is a block diagram of an image processing module according to an embodiment of the present application. In contrast to the above embodiment, the image processing module 3 provided by the embodiment of the present application includes:

a target area unit 301, configured to obtain a target area of the user to be authenticated according to depth data in the ir map.

Specifically, the infrared band detected by the infrared camera is 650nm-1400nm, which is near infrared ultrashort wave and short wave range, and the detection range is relatively close, so that the method can be well applied to face recognition. Due to the working principle of the infrared camera, the opening degree of the face on the infrared image is obviously stronger than that of other objects, so that the target area of the user to be authenticated can be obtained quickly and accurately. The target area contains the face information of the user to be authenticated, and possibly other information.

And an identifying unit 302, configured to identify face information in the target area.

Specifically, the face detection model is used for detecting in a target area to obtain face information, including the size, the position and the like of the face. The data adopted in this embodiment is the original image, so the subsequent comparison is also 1:1, can compare the picture fast, and have very high degree of accuracy. The face detection model has many places, and the embodiment does not limit the specific mode, so long as the face information can be identified.

And the judging unit 303 is configured to judge whether the authentication model requirement is met according to the face information.

Specifically, since the image matched with the identity card information is a positive face photo in RGB format, in order to ensure the accuracy of comparison, it is necessary to determine whether the face information is closer to the positive face photo or is convertible. The authentication model is required to determine whether the face information can be reliably and accurately used for comparison with the front face photo. The authentication model requirements include: the key points of the face can be identified, and the shielding proportion is smaller than a preset value. And when the angle of the face information is similar to that of the front face photo or the front face photo can be obtained through certain conversion, the face information is considered to meet the requirement of an authentication model. Otherwise, the face information is not considered to meet the requirements of the authentication model. The authentication model requirements include: the key points of the face can be identified, and the shielding proportion is smaller than a preset value.

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.

Specifically, if the face information meets the authentication model requirement, the infrared image can be processed and further used for real-name authentication. When the infrared image is processed, the image can be subjected to operations such as feature extraction, compression, encryption, segmentation and the like so as to reduce the size of the image or improve the safety. Compression refers to converting a three-dimensional image into a two-dimensional image or converting a two-dimensional pixel array into a statistically uncorrelated data set, thereby removing redundant data and achieving the effect of reducing the image size. When the infrared image is processed, various operations in the operations can be performed to achieve better effects.

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

Specifically, there are various ways to prompt the user to re-authenticate, which may be performed by the platform or by an infrared camera. When the platform prompts the user, the authentication failure message and prompt information can be sent to the user, or the authentication failure message and prompt information can be sent to the user through the APP or the applet. When the infrared camera is used for carrying out the method, the method can be carried out by means of flickering of the infrared camera or the method of ringing by being provided with a buzzer. Of course, the prompt can also be performed in a plurality of ways.

Fig. 4 is a block diagram of a judging unit according to an embodiment of the present application. In comparison with the above embodiment, the judging unit 303 provided in the embodiment of the present application includes:

an orientation subunit 401, configured to determine an orientation of the face of the user to be authenticated, and if the orientation is within a preset range, perform a next step; if the range is out, the method judges that the requirements are not met.

Specifically, by analyzing the characteristics of the infrared image, the face orientation of the user to be authenticated can be obtained. The ideal face orientation is facing the infrared camera, but for a variety of reasons the face of the user to be authenticated is not always facing the infrared camera, but may be at a variety of angles. Therefore, in step S1, a plurality of infrared images are continuously acquired, and the final infrared image with the closest angle to the opposite direction needs to be selected. When the faces are compared at the server side, the angles of the faces are not required to be identical, but the closer the angles are, the better the comparison effect is. According to different alignment models, it is necessary to have different orientation ranges of the faces.

A living body subunit 402, configured to determine whether the face pixel area is a living body face image according to the prosthesis attack detection model, and output a living body detection result; the prosthesis attack detection model comprises an input layer, a plurality of convolution processing modules, a maximum pooling layer, a first 2D convolution layer and an output layer;

The output of the output layer is an N x N matrix, and when the attack detection result is generated from the N x N matrix,

and setting a weight value for each output characteristic value in the N multiplied by N matrix, wherein the weight value of the output characteristic value positioned in the center of the matrix is larger than that of the output characteristic value positioned at the periphery of the matrix.

Performing living judgment on each output characteristic value in the matrix with the output of N multiplied by N of the output layer according to a preset first threshold value, and generating the quantity of the output characteristic values larger than the first threshold value;

generating a proportion value of the output characteristic value quantity to the total output characteristic value in the N multiplied by N matrix according to the output characteristic value quantity;

and comparing the proportion value with a preset second threshold value to determine whether the target face corresponding to the image is a living body.

To improve the accuracy of the face detection, in some embodiments, a structured light projector is further included. Acquiring an infrared image and a 3D image of the face of the user to be authenticated through an infrared camera and a structured light projector; and detecting the infrared image, processing the infrared image into two-dimensional data to obtain a first processed image, and recognizing the human face living body of the 3D image.

In the embodiment, the face living body detection is performed through the convolutional neural network, the proportion value of the output characteristic problem is compared with the preset second threshold value through the multi-layer convolutional calculation, whether the target face is a living body or not is determined, the higher anti-attack capability is achieved, and the real-name authentication quality can be guaranteed.

FIG. 5 is a block diagram illustrating a first processing unit according to an embodiment of the present application. In comparison with the above embodiment, the first processing unit 304 provided in the embodiment of the present application includes:

a keypoint subunit 501 is configured to identify a keypoint in the infrared map.

Specifically, the key points include eyebrows, eyes, nose, mouth, facial contour area, and ears. In order to ensure the accuracy of face alignment, as many key points as possible are required. The image can be further processed through the identification of the key points and can be used for face comparison.

A preliminary image subunit 502, configured to map the infrared map to a two-dimensional plane, so as to obtain a preliminary image.

Specifically, since only two-dimensional information is needed when the faces are compared, the infrared image is mapped to the two-dimensional plane in the step, adverse effects on the face comparison are avoided, and the size of the image can be reduced.

An angle subunit 503, configured to adjust an angle of the preliminary image according to the key point, so that a face is oriented perpendicular to the preliminary image.

Specifically, the angle of the image is adjusted, so that the position relationship of the image is changed to a certain extent, but the subsequent face comparison is facilitated. It should be noted that, although the angle subunit 503 is performed after the preliminary image subunit 502 in the present embodiment, a person skilled in the art may perform the angle subunit 503 before the preliminary image subunit 502 and achieve the same technical effects. Therefore, it is within the scope of the present application for the angle subunit 503 to be implemented before the preliminary image subunit 502.

A size subunit 504, configured to resize the preliminary image to a predetermined size, to obtain a first processed image.

Specifically, the size of the infrared image is different from that of the RGB image, so that this step requires that the size of the preliminary image be adjusted to a predetermined size to better perform face comparison with the images in the image library. When the size of the preliminary image is adjusted, the whole image can be uniformly reduced, and a cutting mode can be adopted, so long as the face data can be complete and clear in the image.

According to the embodiment, the infrared image is processed, the angle is adjusted, a first processed image is obtained, the angle is similar to the angle of the face in the face library, and therefore the face comparison effect can be guaranteed. Meanwhile, the data of the embodiment are three-dimensional data, the adjustment of the face angle is more accurate, and the image loss after the adjustment is smaller.

Fig. 6 is a block diagram of an encryption transmission module according to an embodiment of the present application. In contrast to the above embodiment, the encryption transmission module 4 provided in the embodiment of the present application includes:

and a splitting unit 601, configured to split the first processed image into at least two sub-images, and mark the sub-images respectively.

In particular, splitting the first processed image into at least two sub-images may make the data more diffuse during transmission, thereby making the data more secure. At the time of resolution, the resolution is performed in an average manner. The splitting mode is also marked during marking. Taking splitting the first processed image into 3 sub-images as an example, horizontally trisecting the image, and marking a as a1, a2 and a3 in turn when a represents horizontal trisecting.

An identification code unit 602, configured to encrypt the plurality of sub-images and the identification card information respectively, where the encrypted information includes an identification code; the identification code is used for identifying and matching a plurality of encrypted information.

Specifically, the identification code is used for identifying and matching a plurality of encrypted information. The same identification code of the same image can be used for distinguishing different image information at the server side. For example, if the identification code of the image is ABCDEFG, the identification code+tag of the sub-image is ABCDEFG-a1, ABCDEFG-a2 and ABCDEFG-a3, respectively.

And a sending unit 603, configured to send the sub-image and the encrypted information of the identification card information to a server respectively.

Specifically, all the sub-images and the identity card information are respectively encrypted and respectively sent to the server. When encrypting, the sub-image and the identity card information adopt the same encryption mode. And in the transmitting process, the images can be transmitted in a time-sharing manner or respectively transmitted to different servers, and the server side completes the fusion of the images.

According to the embodiment, the image is split into at least two sub-images, and the sub-images are marked, so that the data is safer in the transmission process, and the information can be sent to different servers, so that the safety is greatly improved.

Fig. 7 is a block diagram of another encryption transmission module according to an embodiment of the present application. In contrast to the above embodiment, the encryption transmission module 4 provided in the embodiment of the present application includes:

and the key point unit 701 is used for extracting the key points and marking the marking points in each key point.

Specifically, all the key points are extracted, and a plurality of marking points in each key point are marked. The tag content includes a key location and a sequence number. The characteristics of the face can be restored through all information of the key point positions and the sequence numbers, so that the face can be compared.

And the combining unit 702 is configured to combine the plurality of labeling points to obtain a plurality of combinations.

Specifically, because the labeling points are specific and unique, the labeling points can be arbitrarily combined, and deviation can not occur when the labeling points restore the face characteristic data. The combination mode is fixed, or random. For example, the combination can be performed according to the key points, and a plurality of marking points of the same key point are combined together; the serial numbers can be combined according to the serial numbers, and the serial numbers are combined in a group of 10; the combination can be carried out according to the position relation, and the marking points with similar positions are used as a combination; even a random combination of classifications is possible.

An identification code unit 703, configured to encrypt a plurality of the combinations and the identification card information, respectively, and the encrypted information includes an identification code; the identification code is used for identifying and matching a plurality of encrypted information;

and a sending unit 704, configured to send the plurality of combinations and the encrypted information of the identification card information to a server respectively.

The key point information for comparing the faces is directly obtained, the transmission data size is reduced to the greatest extent, and the security of the data is greatly improved by combining encryption measures in various combination modes. According to the embodiment, different effects can be achieved through different characteristic point information, only the characteristic point data play a role in encryption, and the data of the application are enabled to be high in safety naturally through different marking point modes.

Fig. 8 is a block diagram of another encryption transmission module according to an embodiment of the present application. In contrast to the above embodiment, the encryption transmission module 4 provided in the embodiment of the present application includes:

and a convolution unit 801, configured to convolve the first processed image to obtain a first convolved image.

Specifically, the convolution processing is performed on the image, a smaller-sized image can be obtained, and the feature information is not lost. In addition, the convolved image is only applicable to the same convolution kernel, so that the safety can be increased.

A splitting unit 802, configured to split the first convolution image into at least two sub-images, and mark the sub-images respectively.

Specifically, the first convolution image is split and marked. The splitting and marking methods are the same as the foregoing embodiments, and are not repeated here.

An identification code unit 803 for encrypting the plurality of sub-images and the identification card information, respectively, and the encrypted information contains an identification code; the identification code is used for identifying and matching a plurality of encrypted information;

and the sending unit 804 is configured to send the sub-image and the encrypted information of the identification card information to a server respectively.

The embodiment carries out convolution processing on the data, and processes and transmits the convolved data, so that the transmitted data can be better processed only under the condition of the same convolution kernel, the encryption effect is also played, and the data transmission is safer by matching with encryption measures during transmission.

Fig. 9 is a block diagram of an encryption transmission module according to an embodiment of the present application. In contrast to the above embodiment, the encryption transmission module 4 provided in the embodiment of the present application includes:

and a channel unit 901, configured to extract R, G, B data of three channels from the first processed image, and obtain an R channel map, a G channel map, and a B channel map.

Specifically, the standard photo of face comparison is considered to be an RGB image, so that face comparison can be completed only by data of R, G, B channels. Compared with the first processed image, the data of the R, G, B three channels greatly reduces the data volume of the image, and meanwhile, the data sharing is realized, so that the safety is higher.

A marking unit 902, configured to mark the R channel map, the G channel map, and the B channel map respectively.

Specifically, at the time of marking, three channel maps are marked, respectively. It should be noted that, the data of each channel may still be further split and marked, and the method of splitting and marking refers to the foregoing embodiments, which are not described herein again.

An identification code unit 903, configured to encrypt the R channel map, the G channel map, the B channel map, and the identification card information, where the encrypted information includes an identification code; the identification code is used for identifying and matching a plurality of encrypted information;

and the sending unit 904 is configured to send the sub-image and the encrypted information of the identification card information to a server respectively.

According to the embodiment, the data of the three channels R, G, B are extracted, the size of a transmission image is greatly reduced, the transmission image also has an encryption effect, only single data can be obtained, the real-name authentication data can not be broken, and the security in data transmission is greatly improved by matching with encryption information in transmission.

In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing describes specific embodiments of the present application. It is to be understood that the application is not limited to the particular embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the claims without affecting the spirit of the application.

Claims

1. A door lock with real name authentication function, comprising:

2. The door lock with real name authentication function according to claim 1, further comprising a comparison module,

3. The door lock with real name authentication function according to claim 1, wherein the image processing module comprises:

4. A door lock with real name authentication function according to claim 3, wherein the authentication model requirements include: the key points of the face can be identified, and the shielding proportion is smaller than a preset value.

5. A door lock with a real name authentication function according to claim 3, wherein the judging unit includes:

6. A door lock with real name authentication function according to claim 3, wherein the first processing unit comprises:

a key point subunit, configured to identify a key point in the infrared map;

7. The door lock with real name authentication function according to claim 1, wherein the encryption transmission module comprises:

8. The door lock with real name authentication function according to claim 1, wherein the encryption transmission module comprises:

9. The door lock with real name authentication function according to claim 1, wherein the encryption transmission module comprises:

10. The door lock with real name authentication function according to claim 1, wherein the encryption transmission module comprises: