CN112560543A - Information security management method and equipment based on face brushing terminal - Google Patents
Information security management method and equipment based on face brushing terminal Download PDFInfo
- Publication number
- CN112560543A CN112560543A CN201910854125.3A CN201910854125A CN112560543A CN 112560543 A CN112560543 A CN 112560543A CN 201910854125 A CN201910854125 A CN 201910854125A CN 112560543 A CN112560543 A CN 112560543A
- Authority
- CN
- China
- Prior art keywords
- face
- characteristic value
- management platform
- terminal
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 112
- 230000001680 brushing effect Effects 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 claims abstract description 23
- 239000000284 extract Substances 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 53
- 238000013135 deep learning Methods 0.000 claims description 33
- 230000008676 import Effects 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 230000001815 facial effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 210000004373 mandible Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an information security management method and equipment based on a face brushing terminal. Wherein the method comprises the following steps: the face brushing terminal comprises a background face management platform and a front-end face terminal, wherein the back-end face management platform guides a face picture, extracts a face characteristic value of the guided face picture, stores the extracted face characteristic value, and issues the stored face characteristic value to the front-end face terminal, the front-end face terminal receives the issued face characteristic value, checks and stores the received face characteristic value into a face characteristic value library, and the stored face characteristic value is sent to the front-end face terminal through the back-end face management platform on the premise of ensuring normal use of a face brushing function.
Description
Technical Field
The invention relates to the technical field of face brushing, in particular to a face brushing terminal-based information security management method and device.
Background
The brush face terminal in the existing market is face identification terminal application more and more, for example brush face entrance guard control district or unit building open the door, brush face floodgate machine can realize that the machine of passing through the floodgate of brushing face is current. The face brushing terminal can be divided into online identification or offline identification, the human face comparison is carried out after the face brushing terminal collects the human face in the online identification, the influence of the network is large, the customer experience is influenced, and the face brushing terminal cannot be used due to the fact that the network fails. Another mainstream face brushing terminal product is to run a local face comparison algorithm on a front-end face terminal to brush a face, that is, a background face management platform issues face information to the front-end face terminal, and the front-end face terminal automatically collects, compares and opens a door. However, the issue that the face information is issued from the back-end face management platform to the front-end face terminal is that the information is safe, and there may be a problem that the face information leaks, for example, the front-end face terminal is cracked into the login user and the login password, that is, the login user and the login password that are cracked through the front-end face terminal may cause the leakage of the face information of all the people.
However, the inventors found that at least the following problems exist in the prior art:
the existing face brushing terminal generally runs a local face comparison algorithm on a front-end face terminal to brush faces, namely, face information is issued to the front-end face terminal by a background face management platform, and the front-end face terminal automatically collects, contrasts and opens a door, but the problem that the face information is issued to the front-end face terminal by the background face management platform is that the information is safe and face information leakage may occur.
Disclosure of Invention
In view of this, the present invention provides an information security management method and device based on a face-brushing terminal, which can effectively ensure the security of face information and avoid the situation of face information leakage.
According to an aspect of the present invention, there is provided an information security management method based on a face brushing terminal, where the face brushing terminal includes a back-end face management platform and a front-end face terminal, and the information security management method based on the face brushing terminal includes:
the back-end face management platform imports a face picture;
the back-end face management platform extracts the face characteristic value of the imported face picture;
the back-end face management platform stores the extracted face characteristic value;
the back-end face management platform issues the stored face characteristic value to the front-end face terminal;
and the front-end face terminal receives the issued face characteristic value, and checks and stores the received face characteristic value into a face characteristic value library.
The method for extracting the face characteristic value of the imported face picture by the back-end face management platform comprises the following steps:
and the back-end face management platform adopts a deep learning face algorithm based on a convolutional neural network to extract the face characteristic value of the imported face picture.
The method comprises the following steps that a deep learning face algorithm based on a convolutional neural network is adopted by the back-end face management platform to extract the face characteristic value of the imported face picture, and the method comprises the following steps:
and the back-end face management platform adopts a convolutional neural network-based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features to extract the face feature value of the imported face picture.
Wherein, after the front-end face terminal receives the issued face characteristic value and checks and puts the received face characteristic value in storage, the method further comprises the following steps:
the face brushing terminal further comprises a face access control device, the face access control device extracts face characteristic values of the acquired face pictures through the rear-end face management platform, and the face characteristic values extracted through the rear-end face management platform and the face characteristic values in the face characteristic value library are compared and checked in real time, and the comparison and check are performed through opening the door.
According to another aspect of the present invention, there is provided a face brushing terminal including:
a background face management platform and a front-end face terminal;
the background face management platform is used for importing a face picture, extracting a face characteristic value of the imported face picture, storing the extracted face characteristic value and issuing the stored face characteristic value to the front-end face terminal;
and the front-end face terminal is used for receiving the issued face characteristic value, checking the received face characteristic value and storing the face characteristic value into a face characteristic value library.
The background face management platform is specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm based on a convolutional neural network.
The background face management platform is specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm which integrates the shallow characteristic and the deep characteristic of the end-to-end convolutional neural network and is based on the convolutional neural network.
Wherein, brush face terminal still includes:
a face access control device;
the face access control equipment is used for extracting the face characteristic value of the collected face picture through the rear-end face management platform when the face picture is collected, carrying out real-time comparison and verification on the face characteristic value extracted through the rear-end face management platform and the face characteristic value in the face characteristic value library, and opening the door if the comparison and verification is passed.
According to still another aspect of the present invention, there is provided a face brushing device including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any one of the above-mentioned information security management methods based on a face brushing terminal.
According to still another aspect of the present invention, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements any one of the above-described information security management methods based on a face brushing terminal.
It can be seen that, in the above solutions, the face brushing terminal may include a background face management platform and a front-end face terminal, the back-end face management platform can import the face picture and can extract the face characteristic value of the imported face picture, and can store the extracted face feature value, and can issue the stored face feature value to the front-end face terminal, the front-end face terminal can receive the issued face characteristic value, carry out inspection and warehouse-in of the received face characteristic value to a face characteristic value library, this brush face terminal is guaranteeing to brush under the prerequisite of face function normal use, can send out the face eigenvalue of this storage to this front end face terminal through this rear end face management platform down, because of can't restore out the people's face picture through face eigenvalue, can realize effectively guaranteeing the safety of face information, avoids appearing the condition that face information leaks.
Further, according to the scheme, the back-end face management platform can adopt a deep learning face algorithm based on a convolutional neural network to extract the face characteristic value of the imported face picture, and the deep learning face algorithm based on the convolutional neural network can support diversified face recognition services of 1:1/1: N/N: N and the like, so that high-efficiency and high-accuracy face recognition comparison can be realized, and further, the high-efficiency and high-accuracy extraction of the face characteristic value of the imported face picture can be realized.
Further, according to the above scheme, the back-end face management platform may adopt a convolutional neural network based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features to extract a face feature value of the imported face picture, and the convolutional neural network based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features has face local information such as face eyes and face nose information and face global information such as face contour and face angle information, and has a higher accuracy in classifying face features, so that high-efficiency and high-accuracy face recognition comparison can be realized, and further, the high-efficiency and high-accuracy extraction of the face feature value of the imported face picture can be realized.
Further, according to the above scheme, when the face access control device acquires a face picture, the rear-end face management platform extracts a face characteristic value of the acquired face picture, and performs real-time comparison and verification on the face characteristic value extracted by the rear-end face management platform and a face characteristic value in the face characteristic value library, and if the comparison and verification is passed, the door is opened.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of an embodiment of an information security management method based on a face brushing terminal according to the present invention;
FIG. 2 is a schematic flow chart of another embodiment of an information security management method based on a face brushing terminal according to the present invention;
FIG. 3 is a schematic structural diagram of a face brushing terminal according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of another embodiment of the face brushing terminal of the present invention;
fig. 5 is a schematic structural view of an embodiment of the face brushing device of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be noted that the following examples are only illustrative of the present invention, and do not limit the scope of the present invention. Similarly, the following examples are only some but not all examples of the present invention, and all other examples obtained by those skilled in the art without any inventive work are within the scope of the present invention.
The invention provides an information security management method based on a face brushing terminal, which can effectively ensure the security of face information and avoid the condition of face information leakage.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of an information security management method based on a face brushing terminal according to the present invention. The face brushing terminal comprises a background face management platform and a front-end face terminal. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 1 if the results are substantially the same. As shown in fig. 1, the method comprises the steps of:
s101: the back-end face management platform imports a face picture.
In this embodiment, the back-end face management platform may import the face picture separately by adopting a single face picture import mode, or import the face picture by adopting a mode of importing multiple face pictures simultaneously, which is not limited in the present invention.
S102: and the back-end face management platform extracts the face characteristic value of the imported face picture.
The extracting, by the back-end face management platform, the face feature value of the imported face picture may include:
the back-end face management platform adopts a deep learning face algorithm based on a convolutional neural network to extract the face characteristic value of the imported face picture, and the deep learning face algorithm based on the convolutional neural network can support diversified face recognition services of 1:1/1: N/N: N and the like, so that high-efficiency and high-accuracy face recognition comparison can be realized, and further, the high-efficiency and high-accuracy extraction of the face characteristic value of the imported face picture can be realized.
The back-end face management platform adopts a deep learning face algorithm based on a convolutional neural network to extract a face characteristic value of the imported face picture, and the method can comprise the following steps:
the back-end face management platform adopts a convolutional neural network-based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features to extract face feature values of the imported face picture, the convolutional neural network-based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features has face local information such as face eyes and face nose information and face global information such as face contour and face angle information, the accuracy of face feature classification is higher, face identification comparison with high efficiency and high accuracy can be achieved, and therefore the face feature values of the imported face picture can be extracted efficiently and accurately.
In the present embodiment, the basic idea of the face feature value technology is: from the statistical point of view, the basic elements of the distribution of the face image, namely the eigenvectors of the covariance matrix of the face image sample set, are found, so as to approximately represent the face image, and these eigenvectors are called face eigenvalues. In fact, the face feature value reflects the structural relationship between the information hidden in the face sample set and the face. The eigenvectors of the covariance matrix of the sample set of the eyes, cheeks and mandible of the face may be referred to as eigeneyes, eigenjaws and eigenlips, collectively referred to as eigensub-faces. The feature sub-faces generate a sub-space in the corresponding image space, referred to as the sub-face space. And calculating the projection distance of the test image window in the sub-face space, and if the window image meets the threshold comparison condition, judging the window image to be a human face.
In this embodiment, a feature analysis-based method, that is, the relative ratio of the face reference points and other shape parameters or category parameters describing the features of the face of the person form recognition feature vectors, such recognition based on the whole face not only retains the topological relationship between the face parts, but also retains the information of each part, and recognition based on the parts designs a specific recognition algorithm by extracting local contour information and gray scale information.
In this embodiment, the process of extracting the face feature value of the imported face image is to determine the size, position, distance and other attributes of facial image such as iris, nasal wing, mouth angle and the like of the face image, and then calculate their geometric feature quantities, and these feature quantities form a feature vector describing the facial image. The core of the technology is actually a local human body feature analysis algorithm and a graph/nerve recognition algorithm, wherein the two algorithms are methods utilizing various organs and feature parts of the human face, for example, corresponding geometric relationship multiple data forming recognition parameters are compared with all original parameters in a database, judged and confirmed.
It should be noted that, because different faces have similar structures, in order to improve the distinctiveness of face features, a deep learning face algorithm based on a convolutional neural network is provided, which integrates end-to-end convolutional neural network shallow features and deep features. Generally, the shallow layer of the convolutional neural network extracts some local information of the face, such as eye information, nose information, etc., and the deep layer extracts more global information of the face, such as contour information of the face, angle information of the face, etc. In view of this, after an end-to-end convolutional neural network is constructed, the shallow features and the deep features of the constructed end-to-end convolutional neural network are integrated to obtain a new convolutional neural network-based deep learning face algorithm integrating the shallow features and the deep features of the end-to-end convolutional neural network, and the face algorithm has the local and global expression capability of a face. Experiments of construction on a standard face classification data set show that the proposed deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features based on the convolutional neural network has higher classification accuracy, and is superior to the traditional computer vision method and other deep convolutional neural network methods.
In this embodiment, the deep learning of the convolutional neural network is applied to the link of face recognition, which can be divided into four steps:
the method comprises the steps of detecting a face frame, calibrating an image, turning an image and comparing vectors.
S103: the back-end face management platform stores the extracted face feature value.
In this embodiment, the stored face feature value may be a character set with a preset size, for example, a character set with a size of 2048 bytes, and the stored face feature value occupies a small space, is fast in transmission speed, is easy to transmit, and has high transmission efficiency.
S104: and the back-end face management platform sends the stored face characteristic value to the front-end face terminal.
In this embodiment, the face brushing terminal can issue the stored face feature value to the front-end face terminal through the rear-end face management platform on the premise of ensuring normal use of the face brushing function, and the face image cannot be restored through the face feature value, so that the safety of face information can be effectively ensured.
S105: and the front-end face terminal receives the issued face characteristic value, and checks and stores the received face characteristic value into a face characteristic value library.
Wherein, after receiving the issued face feature value at the front-end face terminal and checking and warehousing the received face feature value, the method may further include:
the face brushing terminal further comprises face access control equipment, when the face access control equipment collects a face picture, the face characteristic value of the collected face picture is extracted through the rear-end face management platform, the face characteristic value extracted through the rear-end face management platform and the face characteristic value in the face characteristic value library are compared and checked in real time, the door is opened after comparison and check are passed, the face access control equipment has the advantages that the face characteristic value of the collected face picture can be extracted and used for face comparison and check, the face characteristic value has irreversible attributes, namely the face picture cannot be reversely solved from the characteristic value, and the door opening action can be executed while the safety of face information is effectively ensured.
It can be seen that, in this embodiment, the face brushing terminal may include a background face management platform and a front-end face terminal, the back-end face management platform can import the face picture and can extract the face characteristic value of the imported face picture, and can store the extracted face feature value, and can issue the stored face feature value to the front-end face terminal, the front-end face terminal can receive the issued face characteristic value, carry out inspection and warehouse-in of the received face characteristic value to a face characteristic value library, this brush face terminal is guaranteeing to brush under the prerequisite of face function normal use, can send out the face eigenvalue of this storage to this front end face terminal through this rear end face management platform down, because of can't restore out the people's face picture through face eigenvalue, can realize effectively guaranteeing the safety of face information, avoids appearing the condition that face information leaks.
Further, in this embodiment, the back-end face management platform may adopt a deep learning face algorithm based on a convolutional neural network to extract the face feature value of the imported face picture, and the deep learning face algorithm based on the convolutional neural network may support diversified face recognition services such as 1:1/1: N/N: N, so that high-efficiency and high-accuracy face recognition comparison may be implemented, and further, high-efficiency and high-accuracy extraction of the face feature value of the imported face picture may be implemented.
Further, in this embodiment, the back-end face management platform may adopt a convolutional neural network based deep learning face algorithm that integrates end-to-end convolutional neural network shallow features and deep features to extract a face feature value of the imported face picture, where the convolutional neural network based deep learning face algorithm that integrates end-to-end convolutional neural network shallow features and deep features has face local information such as face eyes and face nose information and face global information such as face contour and face angle information, and has a higher accuracy in classifying face features, so that high-efficiency and high-accuracy face recognition comparison can be achieved, and further, a high-efficiency and high-accuracy extraction of the face feature value of the imported face picture can be achieved.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating another embodiment of an information security management method based on a face brushing terminal according to the present invention. The face brushing terminal comprises a background face management platform, a front-end face terminal and a face access control device. In this embodiment, the method includes the steps of:
s201: the back-end face management platform imports a face picture.
As described above in S101, further description is omitted here.
S202: and the back-end face management platform extracts the face characteristic value of the imported face picture.
As described above in S102, further description is omitted here.
S203: the back-end face management platform stores the extracted face feature value.
As described above in S103, which is not described herein.
S204: and the back-end face management platform sends the stored face characteristic value to the front-end face terminal.
As described above in S104, and will not be described herein.
S205: and the front-end face terminal receives the issued face characteristic value, and checks and stores the received face characteristic value into a face characteristic value library.
S206: when the face access control equipment collects a face picture, the face characteristic value of the collected face picture is extracted through the rear-end face management platform, the face characteristic value extracted through the rear-end face management platform and the face characteristic value in the face characteristic value library are compared and checked in real time, and if the comparison and check are passed, the door is opened.
In this embodiment, the comparison check may be a preset threshold, and when the similarity between the face feature value extracted by the back-end face management platform and the face feature value in the face feature value library for real-time comparison check is not lower than the preset threshold, the comparison check is passed, which is not limited in the present invention.
It can be found that, in this embodiment, when the face access control device collects a face picture, the face feature value of the collected face picture is extracted through the rear-end face management platform, the face feature value extracted through the rear-end face management platform and the face feature value in the face feature value library are compared and checked in real time, and if the comparison and check are passed, the door is opened.
The invention further provides a face brushing terminal, which can effectively ensure the safety of the face information and avoid the condition of face information leakage.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a face brushing terminal according to an embodiment of the present invention. In this embodiment, the face brushing terminal 30 is the face brushing terminal in the above embodiment. In this embodiment, the face brushing terminal 30 includes a background face management platform 31 and a front-end face terminal 32.
The background face management platform 31 is configured to import a face picture, extract a face feature value of the imported face picture, store the extracted face feature value, and issue the stored face feature value to the front-end face terminal 32.
The front-end face terminal 32 is configured to receive the issued face feature value, and perform inspection and store the received face feature value in a face feature value library.
Optionally, the background face management platform 31 may be specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm based on a convolutional neural network.
Optionally, the background face management platform 31 may be specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm based on the convolutional neural network and integrating the end-to-end convolutional neural network shallow characteristic and deep characteristic.
Referring to fig. 4, fig. 4 is a schematic structural diagram of another embodiment of the face brushing terminal of the present invention. Different from the previous embodiment, the face brushing terminal 40 of the present embodiment further includes a face access control device 41.
The face access control device 41 is configured to, when a face picture is collected, extract a face feature value of the collected face picture through the rear-end face management platform 31, perform real-time comparison and verification on the face feature value extracted through the rear-end face management platform 31 and a face feature value in the face feature value library, and open a door if the comparison and verification is passed.
Each unit module of the face brushing terminal 30/40 can respectively execute the corresponding steps in the above method embodiments, and therefore, the detailed description of each unit module is omitted here, please refer to the description of the corresponding steps above.
The present invention also provides a face brushing apparatus, as shown in fig. 5, including: at least one processor 51; and a memory 52 communicatively coupled to the at least one processor 51; the memory 52 stores instructions executable by the at least one processor 51, and the instructions are executed by the at least one processor 51, so that the at least one processor 51 can execute the above-mentioned information security management method based on the face brushing terminal.
Wherein the memory 52 and the processor 51 are coupled in a bus, which may comprise any number of interconnected buses and bridges, which couple one or more of the various circuits of the processor 51 and the memory 52 together. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 51 is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor 51.
The processor 51 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And the memory 52 may be used to store data used by the processor 51 in performing operations.
The present invention further provides a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
It can be seen that, in the above solutions, the face brushing terminal may include a background face management platform and a front-end face terminal, the back-end face management platform can import the face picture and can extract the face characteristic value of the imported face picture, and can store the extracted face feature value, and can issue the stored face feature value to the front-end face terminal, the front-end face terminal can receive the issued face characteristic value, carry out inspection and warehouse-in of the received face characteristic value to a face characteristic value library, this brush face terminal is guaranteeing to brush under the prerequisite of face function normal use, can send out the face eigenvalue of this storage to this front end face terminal through this rear end face management platform down, because of can't restore out the people's face picture through face eigenvalue, can realize effectively guaranteeing the safety of face information, avoids appearing the condition that face information leaks.
Further, according to the scheme, the back-end face management platform can adopt a deep learning face algorithm based on a convolutional neural network to extract the face characteristic value of the imported face picture, and the deep learning face algorithm based on the convolutional neural network can support diversified face recognition services of 1:1/1: N/N: N and the like, so that high-efficiency and high-accuracy face recognition comparison can be realized, and further, the high-efficiency and high-accuracy extraction of the face characteristic value of the imported face picture can be realized.
Further, according to the above scheme, the back-end face management platform may adopt a convolutional neural network based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features to extract a face feature value of the imported face picture, and the convolutional neural network based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features has face local information such as face eyes and face nose information and face global information such as face contour and face angle information, and has a higher accuracy in classifying face features, so that high-efficiency and high-accuracy face recognition comparison can be realized, and further, the high-efficiency and high-accuracy extraction of the face feature value of the imported face picture can be realized.
Further, according to the above scheme, when the face access control device acquires a face picture, the rear-end face management platform extracts a face characteristic value of the acquired face picture, and performs real-time comparison and verification on the face characteristic value extracted by the rear-end face management platform and a face characteristic value in the face characteristic value library, and if the comparison and verification is passed, the door is opened.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be substantially or partially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a part of the embodiments of the present invention, and not intended to limit the scope of the present invention, and all equivalent devices or equivalent processes performed by the present invention through the contents of the specification and the drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. The information security management method based on the face brushing terminal is characterized in that the face brushing terminal comprises a rear-end face management platform and a front-end face terminal, and comprises the following steps:
the back-end face management platform imports a face picture;
the back-end face management platform extracts the face characteristic value of the imported face picture;
the back-end face management platform stores the extracted face characteristic value;
the back-end face management platform issues the stored face characteristic value to the front-end face terminal;
and the front-end face terminal receives the issued face characteristic value, and checks and stores the received face characteristic value into a face characteristic value library.
2. The information security management method based on the face brushing terminal according to claim 1, wherein the extracting, by the back-end face management platform, the face feature value of the imported face picture comprises:
and the back-end face management platform adopts a deep learning face algorithm based on a convolutional neural network to extract the face characteristic value of the imported face picture.
3. The information security management method based on the face brushing terminal according to claim 2, wherein the extracting, by the back-end face management platform, the face feature value of the imported face image by using a deep learning face algorithm based on a convolutional neural network comprises:
and the back-end face management platform adopts a convolutional neural network-based deep learning face algorithm integrating end-to-end convolutional neural network shallow features and deep features to extract the face feature value of the imported face picture.
4. The information security management method based on the face-brushing terminal as claimed in claim 1, wherein after the front-end face terminal receives the delivered face feature value, and checks and stores the received face feature value, the method further comprises:
the face brushing terminal further comprises a face access control device, the face access control device extracts face characteristic values of the acquired face pictures through the rear-end face management platform, and the face characteristic values extracted through the rear-end face management platform and the face characteristic values in the face characteristic value library are compared and checked in real time, and the comparison and check are performed through opening the door.
5. A face brushing terminal, comprising:
a background face management platform and a front-end face terminal;
the background face management platform is used for importing a face picture, extracting a face characteristic value of the imported face picture, storing the extracted face characteristic value and issuing the stored face characteristic value to the front-end face terminal;
and the front-end face terminal is used for receiving the issued face characteristic value, checking the received face characteristic value and storing the face characteristic value into a face characteristic value library.
6. The face brushing terminal according to claim 5, wherein the background face management platform is specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm based on a convolutional neural network.
7. The face brushing terminal according to claim 5, wherein the background face management platform is specifically configured to:
and extracting the face characteristic value of the imported face picture by adopting a deep learning face algorithm which integrates the shallow characteristic and the deep characteristic of the end-to-end convolutional neural network and is based on the convolutional neural network.
8. The face brushing terminal according to claim 5, further comprising:
a face access control device;
the face access control equipment is used for extracting the face characteristic value of the collected face picture through the rear-end face management platform when the face picture is collected, carrying out real-time comparison and verification on the face characteristic value extracted through the rear-end face management platform and the face characteristic value in the face characteristic value library, and opening the door if the comparison and verification is passed.
9. A facial brushing device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for brush terminal based information security management of any one of claims 1 to 4.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the information security management method based on a face brushing terminal according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854125.3A CN112560543A (en) | 2019-09-10 | 2019-09-10 | Information security management method and equipment based on face brushing terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854125.3A CN112560543A (en) | 2019-09-10 | 2019-09-10 | Information security management method and equipment based on face brushing terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112560543A true CN112560543A (en) | 2021-03-26 |
Family
ID=75028908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910854125.3A Pending CN112560543A (en) | 2019-09-10 | 2019-09-10 | Information security management method and equipment based on face brushing terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560543A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590212A (en) * | 2017-08-29 | 2018-01-16 | 深圳英飞拓科技股份有限公司 | The Input System and method of a kind of face picture |
| CN108846925A (en) * | 2018-06-04 | 2018-11-20 | 深圳云天励飞技术有限公司 | Face recognition door control system |
| KR101931271B1 (en) * | 2018-05-11 | 2018-12-20 | 주식회사 다통솔루션 | Face Recognition Method and Apparatus Using Single Forward Pass |
| CN109993863A (en) * | 2019-02-20 | 2019-07-09 | 南通大学 | A kind of access control system and its control method based on recognition of face |
-
2019
- 2019-09-10 CN CN201910854125.3A patent/CN112560543A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590212A (en) * | 2017-08-29 | 2018-01-16 | 深圳英飞拓科技股份有限公司 | The Input System and method of a kind of face picture |
| KR101931271B1 (en) * | 2018-05-11 | 2018-12-20 | 주식회사 다통솔루션 | Face Recognition Method and Apparatus Using Single Forward Pass |
| CN108846925A (en) * | 2018-06-04 | 2018-11-20 | 深圳云天励飞技术有限公司 | Face recognition door control system |
| CN109993863A (en) * | 2019-02-20 | 2019-07-09 | 南通大学 | A kind of access control system and its control method based on recognition of face |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190251571A1 (en) | Transaction verification system | |
| WO2019085403A1 (en) | Intelligent face recognition comparison method, electronic device, and computer readable storage medium | |
| US9064145B2 (en) | Identity recognition based on multiple feature fusion for an eye image | |
| EP4246431A1 (en) | Face image quality assessment method and apparatus, computer device and storage medium | |
| CN112232117A (en) | Face recognition method, face recognition device and storage medium | |
| CN110287813A (en) | Personal identification method and system | |
| CN109766785A (en) | A kind of biopsy method and device of face | |
| CN110348331B (en) | Face recognition method and electronic equipment | |
| CN112016464A (en) | Method and device for detecting face shielding, electronic equipment and storage medium | |
| CN105160318A (en) | Facial expression based lie detection method and system | |
| CN106295591A (en) | Gender identification method based on facial image and device | |
| CN111476222B (en) | Image processing method, image processing device, computer equipment and computer readable storage medium | |
| EP3680794A1 (en) | Device and method for user authentication on basis of iris recognition | |
| CN107194361A (en) | Two-dimentional pose detection method and device | |
| CN113449704B (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| CN101739742A (en) | Networking type multi-channel access control and attendance system | |
| KR101174048B1 (en) | Apparatus for recognizing a subject and method using thereof | |
| CN113657195A (en) | Face image recognition method, face image recognition equipment, electronic device and storage medium | |
| Russ et al. | 3D facial recognition: a quantitative analysis | |
| CN106339698A (en) | Iris recognition-based ticket purchase method and device | |
| Lee et al. | Robust iris recognition baseline for the grand challenge | |
| CN106778491A (en) | The acquisition methods and equipment of face 3D characteristic informations | |
| Boka et al. | Person recognition for access logging | |
| CN112560543A (en) | Information security management method and equipment based on face brushing terminal | |
| CN111325173A (en) | Hair type identification method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |