Disclosure of Invention
Aiming at the displayed problems, the method generates an independent preset identification code of each user based on a carefully selected face image of the user which is collected in advance, and then compares the current identification code generated by the face image acquired by a user terminal camera through communication connection with a user terminal with the preset identification code to realize the face identification of the user.
An intelligent face recognition integrated management method comprises the following steps:
collecting a carefully selected face image of a user to generate sample data, and generating an independent preset identification code for each user according to the sample data;
connecting the communication connection with the current user terminal;
acquiring a first current face image acquired by a camera of a current user terminal, and generating a first current identification code according to the first current face image;
and comparing the difference and the similarity between the preset identification code of the current user and the first current identification code to confirm whether the first current face image passes the verification.
Preferably, the acquiring a carefully selected face image of a user to generate sample data, and generating an independent preset identification code for each user according to the sample data includes:
acquiring a first number of preset face images of each user;
preprocessing the first number of preset face images;
detecting whether the first number of preprocessed preset face images meet standard conditions serving as sample data;
acquiring a second number of preset face images meeting the standard condition as the selected face images, and generating the sample data according to the selected face images;
extracting a face characteristic value in any one of a second number of selected face images of each user to generate an initial identification code;
and continuously correcting the initial identification code by using the remaining selected face images in the second number of selected face images of each user to generate a final preset identification code.
Preferably, the switching on the communication connection with the current user terminal includes:
acquiring a connection request sent by the current user terminal;
verifying the identity information of the current user according to the connection request;
when the identity information of the current user passes verification, acquiring the current geographical position of the current user on the electronic map;
confirming whether the current geographic position is within a preset geographic position range or not;
when the current geographic position is not within the preset geographic position range, feeding back a prompt of incapability of connecting and reasons to the current user terminal;
when the current geographic position is within the preset geographic position range, confirming the current connection state of the current user terminal;
when the current connection state is 'connectable', the communication connection is realized with the current user terminal aiming at the connection request sent by the current user terminal;
when the current connection state is 'not connectable', confirming the connection state of the current user terminal once every preset time length until 'connectable' is confirmed;
and when the connection with the current user terminal is successful, acquiring the connection state in real time, and sending an error prompt when the connection state is abnormal.
Preferably, the comparing the difference between the preset identification code and the first current identification code to determine whether the first current face image passes the verification includes:
analyzing the composition of the preset identification code and the first current identification code to obtain a first analysis result and a second analysis result;
comparing the first analysis result with the second analysis result to obtain a comparison similarity;
when the contrast similarity is larger than or equal to a preset similarity, confirming that the first current face image passes verification;
when the contrast similarity is smaller than the preset similarity, confirming that the first current face image does not pass the verification;
the method further comprises the following steps:
when the difference value between the contrast similarity and the preset similarity is within a preset range, sending a prompt for re-acquiring a second current face image to the current user terminal;
when the second current face image is acquired, generating a second current identification code according to the second current face image;
confirming whether the second face image can pass the verification or not by using the second current identification code;
and when the second current identification code passes verification, associating the preset identification code with the second current identification code, and storing the preset identification code and the second current identification code in a preset identification code library.
Preferably, the verifying the identity information of the current user according to the connection request includes:
step A1, acquiring a user name and a password registered by the current user according to the connection request;
step A2, analyzing the password to obtain a third analysis result, and comparing the similarity sim (a, b) of the third analysis result and a preset result:
wherein a represents the third analysis result, b represents the preset result, N represents the total number of the password numbers in the third analysis result and the preset result, and aiExpressed as a weight value of the ith password number in the third parsing result, biA weight value expressed as the ith password number in the preset result, agExpressed as the weight value of the g-th password number in the third analysis result, bgA weight value expressed as a g-th password number in the preset result;
step A3, comparing the similarity with a preset similarity:
step A4, when G is passed, confirming that the identity information of the current user is safe and can be connected, and when G is failed, confirming that the identity information of the current user is unsafe and rejecting the connection request.
An intelligent face recognition integrated management system, the system comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a carefully selected face image of a user to generate sample data and generating an independent preset identification code for each user according to the sample data;
the connection module is used for connecting the communication connection with the current user terminal;
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first current face image acquired by a camera of a current user terminal and generating a first current identification code according to the first current face image;
and the comparison module is used for comparing the difference between the preset identification code of the current user and the first current identification code so as to confirm whether the first current face image passes the verification.
Preferably, the acquisition module includes:
the first acquisition submodule is used for acquiring a first number of preset face images of each user;
the preprocessing submodule is used for preprocessing the first number of preset face images;
the detection submodule is used for detecting whether the preprocessed first number of preset face images meet standard conditions serving as sample data;
the second acquisition sub-module is used for acquiring a second number of preset face images meeting the standard condition as the selected face images and generating the sample data according to the selected face images;
the extraction submodule is used for extracting a face characteristic value in any one of the second quantity of carefully selected face images of each user to generate an initial identification code;
and the correction submodule is used for continuously correcting the initial identification code by utilizing the remaining selected face images in the second number of selected face images of each user to generate a final preset identification code.
Preferably, the switch-on module includes:
a third obtaining submodule, configured to obtain a connection request sent by the current user terminal;
the verification submodule is used for verifying the identity information of the current user according to the connection request;
the fourth obtaining sub-module is used for obtaining the current geographic position of the current user on the electronic map when the identity information of the current user passes verification;
the first confirming submodule is used for confirming whether the current geographic position is within a preset geographic position range or not;
the feedback submodule is used for feeding back a prompt and reasons of connection incapability to the current user terminal when the current geographic position is not within the preset geographic position range;
the second confirming submodule is used for confirming the current connection state of the current user terminal when the current geographic position is within the preset geographic position range;
a connection sub-module, configured to implement communication connection with the current user terminal in response to a connection request sent by the current user terminal when the current connection state is "connectable";
a third confirming submodule, configured to confirm the connection state of the current user terminal every preset time period until "connection is possible" is confirmed when the current connection state is "connectible";
and the fifth obtaining submodule is used for obtaining the connection state in real time when the connection with the current user terminal is successful, and sending out an error prompt when the connection state is abnormal.
Preferably, the comparison module includes:
the analysis submodule is used for analyzing the components of the preset identification code and the first current identification code to obtain a first analysis result and a second analysis result;
the comparison submodule is used for comparing the first analysis result with the second analysis result to obtain the comparison similarity;
the fourth confirming submodule is used for confirming that the first current face image passes the verification when the contrast similarity is larger than or equal to the preset similarity, and confirming that the first current face image does not pass the verification when the contrast similarity is smaller than the preset similarity;
the system further comprises:
the prompting module is used for sending a prompt for reacquiring a second current face image to the current user terminal when the difference value between the contrast similarity and the preset similarity is within a preset range;
the generating module is used for generating a second current identification code according to the second current face image when the second current face image is acquired;
the confirming module is used for confirming whether the second face image can pass the verification by utilizing the second current identification code;
and the storage module is used for associating the preset identification code with the second current identification code and storing the preset identification code and the second current identification code into a preset identification code library when the second current identification code passes verification.
Preferably, the step of verifying the identity information of the current user by the verification sub-module according to the connection request is as follows:
step A1, acquiring a user name and a password registered by the current user according to the connection request;
step A2, analyzing the password to obtain a third analysis result, and comparing the similarity sim (a, b) of the third analysis result and a preset result:
wherein a represents the third analysis result, b represents the preset result, N represents the total number of the password numbers in the third analysis result and the preset result, and aiExpressed as a weight value of the ith password number in the third parsing result, biA weight value expressed as the ith password number in the preset result, agExpressed as the weight value of the g-th password number in the third analysis result, bgA weight value expressed as a g-th password number in the preset result;
step A3, comparing the similarity with a preset similarity:
step A4, when G is passed, confirming that the identity information of the current user is safe and can be connected, and when G is failed, confirming that the identity information of the current user is unsafe and rejecting the connection request.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Face recognition is a popular research topic of computer mode recognition and biological feature identification technology, and is widely applied to the aspects of entertainment, information security, law enforcement, monitoring and the like. In general, face recognition mainly refers to a computer technology for identifying human identities in digital images or video images through human face visual information. Compared with fingerprint identification, palm print identification and the like, the face identification has the characteristics of convenience, rapidness, easy acceptance and the like.
At present, a face recognition technology is applied in various business fields, for example, employees of a company use face recognition to go in and out of the company, owners of a cell use face recognition to go in and out of the cell, and the above applications do not use a camera to collect face information of a user for recognition. In order to solve the above problem, this embodiment discloses a method for generating an independent preset identification code for each user based on a carefully selected face image of a user collected in advance, and then comparing a current identification code generated by a face image acquired by a user terminal camera through communication connection with a user terminal with the preset identification code to realize face identification of the user.
An intelligent face recognition integrated management method, as shown in fig. 1, includes the following steps:
s101, collecting selected face images of users to generate sample data, and generating an independent preset identification code for each user according to the sample data;
step S102, communication connection with the current user terminal is connected;
step S103, acquiring a first current face image acquired by a camera of a current user terminal, and generating a first current identification code according to the first current face image;
step S104, comparing the difference and the sameness of the preset identification code of the current user and a first current identification code to confirm whether the first current face image passes the verification;
in this embodiment, the above-mentioned selected face image of the user may be a high-pixel, high-quality face image, which may be obtained from the terminal of the user or directly obtained by taking a picture of the user, generating a preset identification code independent for each user according to the sample data, wherein the identification code can be an identification code consisting of numbers, letters and images, and then to connect a communication connection, either using a bluetooth connection or a wireless communication connection, then acquiring a first current face image shot by a camera of the user terminal, generating a first current identification code according to the first current face image, wherein the current identification code can be an identification code consisting of numbers, letters and images, and comparing the difference between the first current identification code and the preset identification code of the current user to identify the face of the current user, wherein the user terminal can be a mobile phone or a tablet and the like.
The working principle of the technical scheme is as follows: collecting a carefully selected face image of a user to generate sample data, and generating an independent preset identification code for each user according to the sample data; connecting the communication connection with the current user terminal; acquiring a first current face image acquired by a camera of a current user terminal, and generating a first current identification code according to the first current face image; and comparing the difference and the similarity of the preset identification code and the first current identification code to confirm whether the first current face image passes the verification.
The beneficial effects of the above technical scheme are: face identification can be accomplished to usable user terminal's camera, the fixed policy of camera among the traditional art has been broken, make face identification become more nimble and reliable, when the user needs to discern, need not to carry out face identification and then waste time on the fixed camera, can utilize the terminal to carry out face identification and then realize cominging in and going out when arriving the destination immediately, the time of discernment has been saved, furthermore, need not many people and go to waiting for discernment of lining up, disposable discernment, the work efficiency is improved, and simultaneously, great improvement user convenience and experience are felt.
In one embodiment, the acquiring a carefully chosen face image of a user to generate sample data, and generating an independent preset identification code for each user according to the sample data includes:
acquiring a first number of preset face images of each user;
preprocessing the first number of preset face images;
detecting whether the first number of preprocessed preset face images meet standard conditions serving as sample data;
acquiring a second number of preset face images meeting the standard condition as the selected face images, and generating the sample data according to the selected face images;
extracting a face characteristic value in any one of a second number of selected face images of each user to generate an initial identification code;
continuously correcting the initial identification code by using the remaining selected face images in the second number of selected face images of each user to generate a final preset identification code;
in this embodiment, the preprocessing may be noise reduction, filtering, smoothing, and the like, the first number may be a positive integer greater than or equal to 10, the standard conditions of the sample data are that the definition of the preset face image is greater than or equal to 95% and the resolution of the preset face image is greater than 768 × 576, and the second number may be a positive integer greater than or equal to 2.
The beneficial effects of the above technical scheme are: the quantity and the quality of two images of the selected person are guaranteed by obtaining a first number of preset face images, each preset face image is guaranteed to be optimized by preprocessing the first number of preset face images, the quality of the preset face images is guaranteed, a second number of preset face images meeting conditions in the first number of preset face images are extracted through condition screening and serve as the selected face images, the accuracy and the perfectness of the selected face images are guaranteed, the accuracy of identification codes is higher by continuously correcting initial identification codes generated by the selected face images, and meanwhile, the identification degree of the generated preset identification codes is more accurate.
In one embodiment, the switching on the communication connection with the current user terminal includes:
acquiring a connection request sent by the current user terminal;
verifying the identity information of the current user according to the connection request;
when the identity information of the current user passes verification, acquiring the current geographical position of the current user on the electronic map;
confirming whether the current geographic position is within a preset geographic position range or not;
when the current geographic position is not within the preset geographic position range, feeding back a prompt of incapability of connecting and reasons to the current user terminal;
when the current geographic position is within the preset geographic position range, confirming the current connection state of the current user terminal;
when the current connection state is 'connectable', the communication connection is realized with the current user terminal aiming at the connection request sent by the current user terminal;
when the current connection state is 'not connectable', confirming the connection state of the current user terminal once every preset time length until 'connectable' is confirmed;
when the connection with the current user terminal is successful, acquiring the connection state in real time, and sending an error prompt when the connection state is abnormal;
in this embodiment, the step of verifying the identity information of the current user includes: the method comprises the steps of obtaining a user name and a password registered by a current user, then confirming whether the user name and the password registered by the current user are correct, if so, passing the verification, if not, reusing voice verification, sending a prompt of obtaining verification voice to the user, after obtaining the verification voice of the current user, confirming whether the verification voice is correct, if so, passing the verification of identity information of the current user, if not, failing to pass the verification of the identity information of the current user, wherein the preset geographic position range can be a region of a destination square circle 50m, the reason of the failure in connection is failure caused by exceeding the preset range, and when the connection state is abnormal, analyzing the abnormal reason and transmitting the abnormal reason to a user terminal so that the user can know the failure reason.
The beneficial effects of the above technical scheme are: the method has the advantages that the identity information of the current user is verified to ensure that the current user is registered in real name, the screening range of the user can be initially reduced, the working efficiency is improved, whether the geographical position of the current user on the electronic map is within the preset geographical position range is judged by obtaining the geographical position of the current user, so that the user can know the precondition that the user can recognize the face at any time, the experience of the user is further improved, the user can be ensured to be normally connected with the user terminal at any time by obtaining the real-time connection state with the user terminal when the connection state is abnormal, the face image obtained by the user terminal can be accurately and infallibly received, and the accuracy and the safety are improved.
In one embodiment, as shown in fig. 2, the comparing the difference between the preset identification code and the first current identification code to determine whether the first current face image passes the verification includes:
step S201, analyzing the components of the preset identification code and the first current identification code to obtain a first analysis result and a second analysis result;
step S202, comparing the first analysis result with the second analysis result to obtain a comparison similarity;
step S203, when the contrast similarity is larger than or equal to a preset similarity, confirming that the first current face image passes verification;
step S204, when the contrast similarity is smaller than the preset similarity, determining that the first current face image does not pass the verification;
the method further comprises the following steps:
when the difference value between the contrast similarity and the preset similarity is within a preset range, sending a prompt for re-acquiring a second current face image to the current user terminal;
when the second current face image is acquired, generating a second current identification code according to the second current face image;
confirming whether the second face image can pass the verification or not by using the second current identification code;
when the second current identification code passes verification, associating the preset identification code with the second current identification code, and storing the preset identification code and the second current identification code in a preset identification code library;
in this embodiment, since there is a little error between the first current identification code generated from the first face image acquired by the camera of the user terminal and the preset identification code, for example, the user stores the facial image of the user in advance, the user terminal acquires the face image of the user, and at this time, the current identification code generated by the face image of the user and the preset identification code generated by the facial image of the user inevitably generate a little error, but both face images are of one person, so that in order to avoid the situation of face missing recognition or recognition error, when the difference between the similarity of the first current identification code and the preset identification code of the current user is within the preset range and the preset similarity, and face recognition is carried out on the current user again, the preset range can be 3% -5%, and the preset similarity is 95%.
The beneficial effects of the above technical scheme are: compared with the prior art that the contrast similarity is obtained by comparing the preset identification code with the first current identification code and then compared with the preset similarity, the contrast accuracy is higher by using the obtained face image and the face image stored in advance, and a choice is provided, when the difference value between the contrast similarity and the preset similarity is in a preset range, the second current face image of the user is obtained again to perform face recognition again, the occurrence of wrong recognition or recognition error is avoided, the accuracy is improved, and finally the identification code of the current user can be updated in real time by associating and storing the preset identification code and the second current identification code so as to deal with the current face images which are not used by various current users, so that the recognition accuracy is improved and the user experience is further improved.
In one embodiment, the verifying the identity information of the current user according to the connection request includes:
step A1, acquiring a user name and a password registered by the current user according to the connection request;
step A2, analyzing the password to obtain a third analysis result, and comparing the similarity sim (a, b) of the third analysis result and a preset result:
wherein a represents the third analysis result, b represents the preset result, N represents the total number of the password numbers in the third analysis result and the preset result, and aiExpressed as a weight value of the ith password number in the third parsing result, biA weight value expressed as the ith password number in the preset result, agExpressed as the weight value of the g-th password number in the third analysis result, bgA weight value expressed as a g-th password number in the preset result;
step A3, comparing the similarity with a preset similarity:
step A4, when G is passed, confirming that the identity information of the current user is safe and can be connected, and when G is failed, confirming that the identity information of the current user is unsafe and rejecting the connection request.
The beneficial effects of the above technical scheme are: the user name and the password of the current user are acquired for analysis to acquire a third analysis result, and the similarity between the third analysis result and the preset result is calculated according to the weighted value of the number of the password words in the third analysis result, so that the identity of the user is more accurately and safely verified, and the reliability of subsequent connection with the user terminal is ensured.
The embodiment also discloses an intelligent face recognition integrated management system, as shown in fig. 3, the system includes:
the acquisition module 301 is configured to acquire a carefully selected face image of a user to generate sample data, and generate an independent preset identification code for each user according to the sample data;
a connection module 302, configured to connect a communication connection with a current user terminal;
an obtaining module 303, configured to obtain a first current face image acquired by a camera of a current user terminal, and generate a first current identification code according to the first current face image;
a comparing module 304, configured to compare similarities and differences between the preset identification code of the current user and the first current identification code to determine whether the first current face image passes verification.
The working principle and the advantageous effects of the above technical solution have been explained in the method claims, and are not described herein again.
In one embodiment, the acquisition module includes:
the first acquisition submodule is used for acquiring a first number of preset face images of each user;
the preprocessing submodule is used for preprocessing the first number of preset face images;
the detection submodule is used for detecting whether the preprocessed first number of preset face images meet standard conditions serving as sample data;
the second acquisition sub-module is used for acquiring a second number of preset face images meeting the standard condition as the selected face images and generating the sample data according to the selected face images;
the extraction submodule is used for extracting a face characteristic value in any one of the second quantity of carefully selected face images of each user to generate an initial identification code;
and the correction submodule is used for continuously correcting the initial identification code by utilizing the remaining selected face images in the second number of selected face images of each user to generate a final preset identification code.
In one embodiment, the switch-on module includes:
a third obtaining submodule, configured to obtain a connection request sent by the current user terminal;
the verification submodule is used for verifying the identity information of the current user according to the connection request;
the fourth obtaining sub-module is used for obtaining the current geographic position of the current user on the electronic map when the identity information of the current user passes verification;
the first confirming submodule is used for confirming whether the current geographic position is within a preset geographic position range or not;
the feedback submodule is used for feeding back a prompt and reasons of connection incapability to the current user terminal when the current geographic position is not within the preset geographic position range;
the second confirming submodule is used for confirming the current connection state of the current user terminal when the current geographic position is within the preset geographic position range;
a connection sub-module, configured to implement communication connection with the current user terminal in response to a connection request sent by the current user terminal when the current connection state is "connectable";
a third confirming submodule, configured to confirm the connection state of the current user terminal every preset time period until "connection is possible" is confirmed when the current connection state is "connectible";
and the fifth obtaining submodule is used for obtaining the connection state in real time when the connection with the current user terminal is successful, and sending out an error prompt when the connection state is abnormal.
In one embodiment, the comparison module includes:
the analysis submodule is used for analyzing the components of the preset identification code and the first current identification code to obtain a first analysis result and a second analysis result;
the comparison submodule is used for comparing the first analysis result with the second analysis result to obtain the comparison similarity;
the fourth confirming submodule is used for confirming that the first current face image passes the verification when the contrast similarity is larger than or equal to the preset similarity, and confirming that the first current face image does not pass the verification when the contrast similarity is smaller than the preset similarity;
as shown in fig. 4, the system further includes:
a prompt module 401, configured to send a prompt to the current user terminal to reacquire a second current face image when a difference between the contrast similarity and the preset similarity is within a preset range;
a generating module 402, configured to generate a second current identification code according to the second current face image when the second current face image is acquired;
a confirming module 403, configured to confirm whether the second face image can pass verification by using the second current identification code;
a storage module 404, configured to associate the preset identification code with the second current identification code when the second current identification code passes verification, and store the preset identification code and the second current identification code in a preset identification code library.
11. In one embodiment, the step of verifying, by the verification sub-module, the identity information of the current user according to the connection request is as follows:
step A1, acquiring a user name and a password registered by the current user according to the connection request;
step A2, analyzing the password to obtain a third analysis result, and comparing the similarity sim (a, b) of the third analysis result and a preset result:
wherein a represents the third analysis result, b represents the preset result, N represents the total number of the password numbers in the third analysis result and the preset result, and aiExpressed as a weight value of the ith password number in the third parsing result, biExpressed as the ith password numberThe weight value of the preset result, agExpressed as the weight value of the g-th password number in the third analysis result, bgA weight value expressed as a g-th password number in the preset result;
step A3, comparing the similarity with a preset similarity:
step A4, when G is passed, confirming that the identity information of the current user is safe and can be connected, and when G is failed, confirming that the identity information of the current user is unsafe and rejecting the connection request.
It will be understood by those skilled in the art that the first and second terms of the present invention refer to different stages of application.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.