CN111159682A - Man-machine interaction authentication method and device, electronic equipment and storage medium - Google Patents
Man-machine interaction authentication method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111159682A CN111159682A CN201911414558.3A CN201911414558A CN111159682A CN 111159682 A CN111159682 A CN 111159682A CN 201911414558 A CN201911414558 A CN 201911414558A CN 111159682 A CN111159682 A CN 111159682A
- Authority
- CN
- China
- Prior art keywords
- human body
- key point
- matched
- point group
- characteristic information
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the invention provides a man-machine interaction authentication method, a man-machine interaction authentication device, electronic equipment and a storage medium, wherein the method comprises the following steps: taking image data to be detected; detecting the key points of the human body on the image data to obtain a group of key points of the human body; calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group; matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group. And authentication is carried out through human body characteristic information matching, and the calculation amount of the human body characteristic information matching is far smaller than that of the human face characteristic information matching, so that the whole calculation amount can be reduced, and the response speed of a person determining the control right is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a human-computer interaction authentication method, apparatus, electronic device, and storage medium
Background
With the development of computer technology, man-machine interaction modes gradually develop from man-machine adaptation to computers to being adapted to humans by computers, for example, from early DOS (Disk Operating System) command man-machine interaction to GUI (Graphical User Interface) mouse man-machine interaction. With the development of computer vision technology, human-computer interaction based on image data becomes possible, but for image data including a plurality of persons, how to determine which person's instruction is executed in the process of human-computer interaction, that is, how to determine the person who controls the right, becomes a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention aims to provide a man-machine interaction authentication method, a man-machine interaction authentication device, electronic equipment and a storage medium, so as to determine a control right person in a man-machine interaction process. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a human-computer interaction authentication method, where the method includes:
acquiring image data to be detected;
detecting the key points of the human body on the image data to obtain a group of key points of the human body;
calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group;
and matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group.
In a possible implementation manner, the calculating human body feature information corresponding to the human body key point group to obtain to-be-matched human body feature information corresponding to the human body key point group includes:
and calculating the ratio of the distances among the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance among the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
In a possible implementation manner, the calculating a ratio of distances between specified human body keypoints in the human body keypoint group to obtain to-be-matched human body feature information corresponding to the human body keypoint group includes:
calculating the ratio of the distances among the specified human body key points in the human body key point group;
and calculating to obtain the human body characteristic information to be matched by utilizing the ratios corresponding to each other, wherein the key points of the human body corresponding to the two ratios corresponding to each other are symmetrically distributed along the central axis of the human body.
In a possible implementation manner, the matching the human body feature information to be matched with a pre-stored human body feature information template, and selecting a human body key point group corresponding to the successfully-matched human body feature information to be matched as an authorized human body key point group includes:
calculating the difference degree between the human body characteristic information to be matched and a pre-stored human body characteristic information template;
and selecting the human body key point group corresponding to the human body characteristic information to be matched with the difference degree smaller than the preset difference degree threshold value as an authorized human body key point group.
In a possible implementation manner, the human body feature information to be matched comprises a plurality of items to be matched; the human body characteristic information template comprises a plurality of template items;
the calculating the difference degree between the human body feature information to be matched and a pre-stored human body feature information template comprises the following steps:
respectively calculating the difference between each item to be matched and the corresponding template ratio item to obtain each difference value;
and calculating the difference between the human body feature information to be matched and the human body feature information template according to a preset weight coefficient and each difference value.
In a possible implementation manner, after the matching the human body feature information to be matched with a pre-stored human body feature information template, and selecting a human body key point group corresponding to the successfully matched human body feature information to be matched as an authorized human body key point group, the method further includes:
confirming the face position corresponding to the authorized human body key point group;
extracting face feature information based on the face position;
calculating the similarity between the face feature information corresponding to the authorized human body key point groups and a face feature information template stored in advance;
and selecting an authorized human body key point group corresponding to the face feature information with the similarity greater than a preset similarity threshold value as an authorized human body key point group which passes face verification.
In a second aspect, an embodiment of the present application provides a human-computer interaction authentication apparatus, where the apparatus includes:
the image data acquisition module is used for acquiring image data to be detected;
the human body key point detection module is used for detecting human body key points of the image data to obtain a human body key point group;
the human body feature calculation module is used for calculating human body feature information corresponding to the human body key point group to obtain human body feature information to be matched corresponding to the human body key point group;
and the human body characteristic matching module is used for matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched, and taking the selected human body key point group as an authorized human body key point group.
In a possible implementation manner, the human body feature calculation module is specifically configured to: and calculating the ratio of the distances among the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance among the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
In a possible implementation manner, the human body feature calculation module is specifically configured to: calculating the ratio of the distances among the specified human body key points in the human body key point group; and calculating to obtain the human body characteristic information to be matched by utilizing the ratios corresponding to each other, wherein the key points of the human body corresponding to the two ratios corresponding to each other are symmetrically distributed along the central axis of the human body.
In one possible embodiment, the human body feature matching module includes:
the difference degree calculation operator module is used for calculating the difference degree between the human body characteristic information to be matched and a pre-stored human body characteristic information template;
and the difference threshold value comparison submodule is used for selecting the human body key point group corresponding to the human body characteristic information to be matched, of which the difference is smaller than the preset difference threshold value, as the authorized human body key point group.
In a possible implementation manner, the human body feature information to be matched comprises a plurality of items to be matched; the human body characteristic information template comprises a plurality of template items;
the disparity degree operator module is specifically configured to: respectively calculating the difference between each item to be matched and the corresponding template ratio item to obtain each difference value; and calculating the difference between the human body feature information to be matched and the human body feature information template according to a preset weight coefficient and each difference value.
In a possible embodiment, the apparatus further comprises: a face feature matching module for: confirming the face position corresponding to the authorized human body key point group; extracting face feature information based on the face position; calculating the similarity between the face feature information corresponding to the authorized human body key point groups and a face feature information template stored in advance; and selecting an authorized human body key point group corresponding to the face feature information with the similarity greater than a preset similarity threshold value as an authorized human body key point group which passes face verification.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the man-machine interaction authentication method of any one of the first aspect when executing the program stored in the memory.
In another aspect of the present invention, there is also provided a computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to execute the human-computer interaction authentication method according to any one of the first aspect.
In another aspect of the present invention, an embodiment of the present invention further provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the human-computer interaction authentication method according to any one of the first aspect.
The man-machine interaction authentication method, the man-machine interaction authentication device, the electronic equipment and the storage medium provided by the embodiment of the invention are used for acquiring image data to be detected; detecting the key points of the human body on the image data to obtain a group of key points of the human body; calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group; matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group. And authentication is carried out through human body characteristic information matching, and the calculation amount of the human body characteristic information matching is far smaller than that of the human face characteristic information matching, so that the whole calculation amount can be reduced, and the response speed of a person determining the control right is improved. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
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.
Fig. 1a is a first schematic diagram of a human-computer interaction authentication method according to an embodiment of the present application;
fig. 1b is a second schematic diagram of a man-machine interaction authentication method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a human body key point according to an embodiment of the present application;
FIG. 3a is a third schematic diagram of a human-computer interaction authentication method according to an embodiment of the present application;
FIG. 3b is a fourth schematic diagram illustrating a man-machine interaction authentication method according to an embodiment of the present application;
fig. 3c is a fifth schematic diagram of a human-computer interaction authentication method according to an embodiment of the present application;
fig. 4 is a sixth schematic diagram of a human-computer interaction authentication method according to an embodiment of the present application;
FIG. 5 is a diagram illustrating a method for determining control authority human body key point groups according to an embodiment of the present disclosure;
FIG. 6 is a diagram illustrating a method for adding authorized person information according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a human-computer interaction method according to an embodiment of the present application;
FIG. 8 is a diagram illustrating an exemplary embodiment of a human-computer interaction authentication device;
fig. 9 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
In order to determine a person with control right in a human-computer interaction process in a human-computer interaction scene including a plurality of persons, an embodiment of the application provides a human-computer interaction authentication method, which includes:
acquiring image data to be detected;
detecting the key points of the human body on the image data to obtain a group of key points of the human body;
calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group;
matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group.
In the embodiment of the application, the authentication is performed through the human body characteristic information matching, and the calculation amount of the human body characteristic information matching is far smaller than that of the human face characteristic information matching, so that the overall calculation amount can be reduced, and the response speed of a person who determines the control right is improved.
The following is a detailed description:
the embodiment of the application provides a man-machine interaction authentication method, and referring to fig. 1a, the method comprises the following steps:
s101, image data to be detected are obtained.
The man-machine interaction authentication method is applied to electronic equipment, and specifically, the electronic equipment can be a server, a personal computer or a smart phone.
The image data to be detected can be acquired by image acquisition equipment in real time, and the image acquisition equipment can be a built-in camera of electronic equipment, such as a built-in camera of a smart phone or a built-in camera of a notebook computer; the image acquisition equipment can also be a camera and the like which are connected with the electronic equipment through external equipment. The electronic device acquires image data acquired by the image acquisition device, wherein the image data can be a section of video or a video frame currently sent by the acquisition device.
And S102, detecting the key points of the human body on the image data to obtain the key point groups of the human body.
And detecting the human body key points in the image data by using a computer vision technology to obtain a human body key point group. The obtained human body key points can be grouped into one group or a plurality of groups, one group of human body key points corresponds to one person, and the human body key points are grouped into a set of human body key points of the corresponding person. The method for detecting human body keypoints can be referred to the method for detecting human body keypoints in the related art, for example, by using a human body keypoint detection framework based on a CPN (Cascaded Pyramid Network) architecture, a human body keypoint detection framework based on a CPM (Convolutional Pose Machines) architecture, or a human body keypoint detection framework based on an Open position architectureA detection frame, etc. The human body key points can be selected in a self-defined manner according to actual conditions, and in one possible implementation, as shown in fig. 2, the human body key points include: head key point p0＝(x0,y0) Neck key point p1＝(x1,y1) Right shoulder keypoint p2＝(x2,y2) Left shoulder keypoint p3＝(x3,y3) Right elbow key point p4＝(x4,y4) Left hand elbow Key Point p5＝(x5,y5) Right wrist key point p6＝(x6,y6) Key point p of the left wrist7＝(x7,y7) Key point p of right hip bone8＝(x8,y8) Key point p of left hip bone9＝(x9,y9) Right Knee Key Point p10＝(x10,y10) Left knee Key Point p11＝(x11,y11) Right ankle key point p12＝(x12,y12) Left ankle key point p13＝(x13,y13). The human body keypoint group includes a plurality or all of the above keypoints.
S103, calculating the human body characteristic information corresponding to the human body key point group to obtain the human body characteristic information to be matched corresponding to the human body key point group.
After the human body key point groups are obtained, the human body key point groups need to be converted into information which can be used for calculation, namely human body feature information. The human body feature information is used for representing the features of the persons represented by the human body key point groups, and specifically, the human body feature information may be the size, the length, the human body proportion and the like of the specified part.
And S104, matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group.
The electronic equipment stores the human body characteristic information of authorized users in advance, the human body characteristic information is called as a human body characteristic information template, the human body characteristic information to be matched in the image data is matched with the human body characteristic information template, the human body characteristic information to be matched, which is not matched with the human body characteristic information templates, is filtered, and the human body key points corresponding to the residual human body characteristic information to be matched are grouped to be used as authorized human body key point groups.
In the embodiment of the application, the authentication is performed through the human body characteristic information matching, and the calculation amount of the human body characteristic information matching is far smaller than that of the human face characteristic information matching, so that the overall calculation amount can be reduced, and the response speed of a person who determines the control right is improved.
In a possible implementation manner, referring to fig. 1b, after the matching of the human body feature information to be matched with the pre-stored human body feature information template, and selecting the human body key point group corresponding to the successfully matched human body feature information to be matched as the authorized human body key point group, the method further includes:
and S105, confirming the face position corresponding to the authorized human body key point group.
According to the distribution of the human body structure, the human face area of the person can be calculated through the key points of the human body. The corresponding face position can be determined by the positions of key points such as head key points, neck key points and the like in the authorized human body key point group. E.g. based on the head key point p of a person0＝(x0,y0) And neck keypoint p1＝(x1,y1) The coordinates (x) of the upper left corner of the rectangular area of the face of the person can be calculatedlp,ylp) And the coordinates of the lower right corner (x)rd,yrd) And then the face area of the person is obtained.
Wherein:
ylp＝y0，
yrd＝y1。
and the position of the face region is calculated based on the human body key point information, and compared with the position of the face region detected by a face detection algorithm, the method has the advantages of small calculation amount, low calculation load and high response speed.
And S106, extracting the face feature information based on the face position.
And detecting the face position by using a preset face detection technology, and extracting face characteristic information.
And S107, calculating the similarity between the face feature information corresponding to the authorized human body key point group and a face feature information template stored in advance.
The electronic equipment also stores face feature information of each authorized user, which is called a face feature information template below, and the human feature information of each human feature authorized person is matched with the face feature information of the authorized user, so that the human feature authorized persons which are not matched with the face feature information of each authorized user are filtered out, and the human face feature authorized persons are obtained.
And S108, selecting an authorized human body key point group corresponding to the face feature information with the similarity larger than a preset similarity threshold value as an authorized human body key point group which passes face verification.
Each face feature information template corresponds to a unique authorized user, and the authorized human body key points passing the face verification are grouped into corresponding personnel to serve as authentication passing personnel.
In the embodiment of the application, firstly, the personnel are filtered based on the human body characteristic information of the authorized user, the number of personnel matched with the human face characteristic information can be reduced, and the overall calculated amount can be reduced due to the fact that the calculated amount of the human body characteristic information matching is far smaller than that of the human face characteristic information matching, and therefore the response speed of the personnel for determining the control right is improved.
In a possible implementation manner, referring to fig. 3a, the calculating human body feature information corresponding to the human body key point group to obtain to-be-matched human body feature information corresponding to the human body key point group includes:
s301, calculating the ratio of the distances between the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance between the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
And aiming at each human body key point group, calculating the ratio of the distances between the specified human body key points of the human body key point group to obtain the human body characteristic information of the human body key point group.
In view of the fact that the distance between a person and the camera cannot be fixed, the human body characteristic information may be relative information, such as the proportion of the body morphology, and specifically, the ratio of one or more specified human body parts may be used as the human body characteristic information; the human body feature information can be expressed in the form of a vector or a matrix, and each element in the vector or the matrix is the ratio of the distance between the specified human body key points.
For example, in the human keypoint grouping shown in FIG. 2, the distance d between the left shoulder keypoint and the left elbow keypoint is calculated3-5＝|p3-p5Calculating the distance d between the key point of the left elbow and the key point of the left wrist5-7＝|p5-p7L. Calculating d3-5And d5-7And obtaining the human body feature information to be matched corresponding to the human body key point groups. Certainly, the to-be-matched human body feature information corresponding to the human body key point group may include a plurality of ratios, and the calculation methods of the ratios are similar and will not be described herein again.
In a possible implementation manner, referring to fig. 3b, the calculating a ratio of distances between specified human body keypoints in the human body keypoint group to obtain to-be-matched human body feature information corresponding to the human body keypoint group includes:
s3011, calculating the ratio of the distances among the specified human body key points in the human body key point group.
And S3012, calculating to-be-matched human body characteristic information by using the ratios corresponding to each other, wherein the human body key points corresponding to the two ratios corresponding to each other are symmetrically distributed along the central axis of the human body.
For example, when the human key points are as shown in fig. 2, the human feature information may be expressed as: f. ofbody＝[f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11]Wherein f is1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11Respectively the ratio of the distances between different specified human key points.
For example,
wherein d isn-mIs a key point PnAnd a key point PmN and m are integers, n is more than or equal to 0 and less than or equal to 13, and m is more than or equal to 0 and less than or equal to 13. Of course, each element in the human body feature information may also be set in other proportional forms, which are not described herein again.
In a possible implementation manner, referring to fig. 3c, the matching the human characteristic information to be matched with the pre-stored human characteristic information template, and selecting the human key point group corresponding to the successfully matched human characteristic information to be matched as the authorized human key point group includes:
and S1041, calculating the difference between the human body feature information to be matched and a pre-stored human body feature information template.
S1042, selecting a human body key point group corresponding to the human body feature information to be matched, of which the difference degree is smaller than a preset difference degree threshold value, as an authorized human body key point group.
And respectively calculating the difference between the human body characteristic information to be matched and the human body characteristic information template corresponding to different human body key point groups. And comparing the difference degree with a preset difference degree threshold value, and grouping the human body key points corresponding to the difference degree smaller than the preset difference degree threshold value as authorized human body key point groups.
In one possible implementation, referring to fig. 4, the human feature information to be matched includes a plurality of items to be matched; the human body characteristic information template comprises a plurality of template items; the calculating the difference between the human body feature information to be matched and the pre-stored human body feature information template comprises the following steps:
s401, respectively calculating the difference between each item to be matched and the corresponding template ratio item to obtain each difference value.
S402, calculating the difference degree between the human body feature information to be matched and the human body feature information template according to the preset weight coefficient and each difference value.
Specifically, the difference degree formula can be preset: s ═ WBT|fBT-fbodyAnd calculating the difference between the human body characteristic information to be matched and the human body characteristic information template. s is the degree of difference; wBTFor a predetermined weight vector, for a set of weight coefficients, WBT＝[w1,w2,w3,w4,w5,w6,w7,w8,w9,w10,w11]T，w1,w2,w3,w4,w5,w6,w7,w8,w9,w10,w11Weighting each preset weight coefficient; f. ofBTA human body characteristic information template; f. ofbodyIs the human body characteristic information to be matched.
In a possible implementation manner, referring to fig. 5, after the authorized human body keypoint group corresponding to the face feature information with the similarity greater than the preset similarity threshold is selected as the authorized human body keypoint group for which the face verification passes, the method further includes:
s501, determining the authorized users corresponding to the authorized human body key point groups respectively based on the face feature information corresponding to the authorized human body key point groups and the face matching result of the face feature information template.
And S502, selecting the authorized human body key point group corresponding to the authorized user with the highest authorization level from the authorized human body key point groups according to the authorization level of each authorized user, and taking the selected authorized human body key point group as the human body key point group of the control authority personnel.
The authorization level of each authorized user is prestored in the electronic equipment, and the higher the authorization level of the user is, the greater the authority of the user is. In the embodiment of the application, the authorized human body key point group corresponding to the authorized user with the highest authorization level is selected as the human body key point group of the control right personnel. Can ensure that the personnel with high authority preferentially has the control right.
In one possible embodiment, referring to fig. 6, the method further comprises:
s601, when an authorized person is added, acquiring a target image of the person to be authorized and the authorization level of the person to be authorized.
In the embodiment of the application, an authorized person can be added to the electronic device, and the user inputs an image (hereinafter referred to as a target image) of a person to be authorized in the electronic device and sets the authorization level of the person to be authorized. Of course, before adding authorized personnel, the authority of the current user can be identified, so that whether the current user has the authority to add the authorized personnel is determined.
And S602, extracting the human body characteristic information template and the human face characteristic information template of the person to be authorized based on the target image.
And analyzing the target image by using a computer vision technology, extracting human body key point groups and human face feature information of the personnel to be authorized in the target image, and calculating by using the human body key point groups to obtain a human body feature information template.
And S603, storing the authorization level of the person to be authorized, the human body characteristic information template and the human face characteristic information template in an associated manner.
The authorization level, the human body characteristic information template, and the human face characteristic information template of the person to be authorized need to be stored in an associated manner, for example, a unique user ID may be set for each authorized person, and the user ID is associated with the name, the authorization level, the human body characteristic information template, the human face characteristic information template, and the like of the authorized person. In a possible embodiment, an authorization limit or the like for authorized personnel may also be set and associated.
In the implementation of the application, the method for adding the authorized personnel is provided, and the user can add the authorized personnel in a user-defined mode according to the actual situation.
In a possible implementation manner, referring to fig. 7, after selecting, according to the authorization level of each authorized user, an authorized human body key point group corresponding to an authorized user with the highest authorization level from among the authorized human body key point groups, as a control right human body key point group, the method further includes:
and S701, analyzing the human body key point groups of the control right personnel to obtain a control action as a target control action.
The control action of the control right personnel can be a gesture, and the gesture of the control right personnel can be detected through relevant gesture key point recognition and gesture detection technologies and serves as a target control action. Of course, the control action of the control right person can also be head action or mouth type, etc.
And S702, executing the machine instruction corresponding to the target control action based on the corresponding relation between the preset control action and the machine instruction.
The electronic device is pre-stored with the corresponding relation between the control action and the machine instruction, the corresponding relation can be set by the user in a user-defined way, the machine instruction corresponding to the target control action is determined, and the machine instruction is executed.
In the embodiment of the application, the corresponding machine instruction is executed through the control action of the control right personnel, and the purpose of controlling the operation of the electronic equipment by using the control action can be achieved.
An embodiment of the present application further provides a human-computer interaction authentication apparatus, referring to fig. 8, the apparatus includes:
an image data acquiring module 801, configured to acquire image data to be detected;
a human body key point detection module 802, configured to perform human body key point detection on the image data to obtain a human body key point group;
a human body feature calculating module 803, configured to calculate human body feature information corresponding to the human body key point group, to obtain to-be-matched human body feature information corresponding to the human body key point group;
and the human body feature matching module 804 is configured to match the human body feature information to be matched with a pre-stored human body feature information template, and select a human body key point group corresponding to the successfully matched human body feature information to be matched as an authorized human body key point group.
In a possible implementation manner, the human body feature calculation module 803 is specifically configured to: and calculating the ratio of the distances between the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance between the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
In a possible implementation manner, the human body feature calculation module 803 is specifically configured to: calculating the ratio of the distances among the specified human body key points in the human body key point group; and calculating to obtain the human body characteristic information to be matched by utilizing the ratios corresponding to each other, wherein the key points of the human body corresponding to the two ratios corresponding to each other are symmetrically distributed along the central axis of the human body.
In a possible implementation manner, the human body feature matching module 804 includes:
the difference degree calculation operator module is used for calculating the difference degree between the human body characteristic information to be matched and a pre-stored human body characteristic information template;
and the difference threshold value comparison submodule is used for selecting the human body key point group corresponding to the human body characteristic information to be matched, of which the difference is smaller than the preset difference threshold value, as the authorized human body key point group.
In a possible implementation manner, the human body feature information to be matched includes a plurality of items to be matched; the human body characteristic information template comprises a plurality of template items;
the disparity degree operator module is specifically configured to: respectively calculating the difference between each item to be matched and the corresponding template ratio item to obtain each difference value; and calculating the difference between the human body feature information to be matched and the human body feature information template according to a preset weight coefficient and each difference value.
In a possible embodiment, the above apparatus further comprises: a face feature matching module for: confirming the face position corresponding to the authorized human body key point group; extracting face feature information based on the face position; calculating the similarity between the face feature information corresponding to the authorized human body key point groups and a face feature information template stored in advance; and selecting an authorized human body key point group corresponding to the face feature information with the similarity greater than a preset similarity threshold value as an authorized human body key point group which passes face verification.
An embodiment of the present invention further provides an electronic device, as shown in fig. 9, which includes a processor 901, a communication interface 902, a memory 903, and a communication bus 904, where the processor 901, the communication interface 902, and the memory 903 complete mutual communication through the communication bus 904,
a memory 903 for storing computer programs;
the processor 901 is configured to implement the following steps when executing the program stored in the memory 903:
acquiring image data to be detected;
detecting the key points of the human body on the image data to obtain a group of key points of the human body;
calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group;
matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group.
Optionally, when the processor is used to execute the computer program stored in the memory, any one of the above human-computer interaction authentication methods can also be implemented.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In another embodiment of the present invention, a computer-readable storage medium is further provided, in which instructions are stored, and when the instructions are executed on a computer, the computer is enabled to execute the human-computer interaction authentication method in any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the human-computer interaction authentication method as described in any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, the technical features in the various alternatives can be combined to form the scheme as long as the technical features are not contradictory, and the scheme is within the scope of the disclosure of the present application. Relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A man-machine interaction authentication method is characterized by comprising the following steps:
acquiring image data to be detected;
detecting the key points of the human body on the image data to obtain a group of key points of the human body;
calculating human body characteristic information corresponding to the human body key point group to obtain human body characteristic information to be matched corresponding to the human body key point group;
and matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group.
2. The method according to claim 1, wherein the calculating the human body feature information corresponding to the human body key point group to obtain the human body feature information to be matched corresponding to the human body key point group comprises:
and calculating the ratio of the distances among the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance among the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
3. The method according to claim 2, wherein the calculating a ratio of distances between specified human body key points in the human body key point groups to obtain human body feature information to be matched corresponding to the human body key point groups comprises:
calculating the ratio of the distances among the specified human body key points in the human body key point group;
and calculating to obtain the human body characteristic information to be matched by utilizing the ratios corresponding to each other, wherein the key points of the human body corresponding to the two ratios corresponding to each other are symmetrically distributed along the central axis of the human body.
4. The method according to claim 1, wherein the matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, and selecting the human body key point group corresponding to the successfully matched human body characteristic information to be matched as an authorized human body key point group comprises:
calculating the difference degree between the human body characteristic information to be matched and a pre-stored human body characteristic information template;
and selecting the human body key point group corresponding to the human body characteristic information to be matched with the difference degree smaller than the preset difference degree threshold value as an authorized human body key point group.
5. The method according to claim 4, wherein the human body feature information to be matched comprises a plurality of items to be matched; the human body characteristic information template comprises a plurality of template items;
the calculating the difference degree between the human body feature information to be matched and a pre-stored human body feature information template comprises the following steps:
respectively calculating the difference between each item to be matched and the corresponding template ratio item to obtain each difference value;
and calculating the difference between the human body feature information to be matched and the human body feature information template according to a preset weight coefficient and each difference value.
6. The method according to claim 1, wherein after matching the human body feature information to be matched with a pre-stored human body feature information template, selecting a human body key point group corresponding to the successfully matched human body feature information to be matched as an authorized human body key point group, the method further comprises:
confirming the face position corresponding to the authorized human body key point group;
extracting face feature information based on the face position;
calculating the similarity between the face feature information corresponding to the authorized human body key point groups and a face feature information template stored in advance;
and selecting an authorized human body key point group corresponding to the face feature information with the similarity greater than a preset similarity threshold value as an authorized human body key point group which passes face verification.
7. A human-computer interaction authentication apparatus, characterized in that the apparatus comprises:
the image data acquisition module is used for acquiring image data to be detected;
the human body key point detection module is used for detecting human body key points of the image data to obtain a human body key point group;
the human body feature calculation module is used for calculating human body feature information corresponding to the human body key point group to obtain human body feature information to be matched corresponding to the human body key point group;
and the human body characteristic matching module is used for matching the human body characteristic information to be matched with a pre-stored human body characteristic information template, selecting a human body key point group corresponding to the successfully matched human body characteristic information to be matched, and taking the selected human body key point group as an authorized human body key point group.
8. The apparatus of claim 7, wherein the human body feature calculation module is specifically configured to: and calculating the ratio of the distances among the specified human body key points in the human body key point groups to obtain the human body feature information to be matched corresponding to the human body key point groups, wherein each human body key point corresponding to the distance among the specified human body key points used for calculating the ratio is positioned on one side of the central axis of the human body.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1-6 when executing a program stored in the memory.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911414558.3A CN111159682B (en) | 2019-12-31 | 2019-12-31 | Man-machine interaction authentication method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911414558.3A CN111159682B (en) | 2019-12-31 | 2019-12-31 | Man-machine interaction authentication method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111159682A true CN111159682A (en) | 2020-05-15 |
| CN111159682B CN111159682B (en) | 2023-03-10 |
Family
ID=70560051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911414558.3A Active CN111159682B (en) | 2019-12-31 | 2019-12-31 | Man-machine interaction authentication method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159682B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334863A (en) * | 2018-03-09 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Identity identifying method, system, terminal and computer readable storage medium |
| CN110222566A (en) * | 2019-04-30 | 2019-09-10 | 北京迈格威科技有限公司 | A kind of acquisition methods of face characteristic, device, terminal and storage medium |
| CN110363067A (en) * | 2019-05-24 | 2019-10-22 | 深圳壹账通智能科技有限公司 | Auth method and device, electronic equipment and storage medium |
-
2019
- 2019-12-31 CN CN201911414558.3A patent/CN111159682B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334863A (en) * | 2018-03-09 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Identity identifying method, system, terminal and computer readable storage medium |
| CN110222566A (en) * | 2019-04-30 | 2019-09-10 | 北京迈格威科技有限公司 | A kind of acquisition methods of face characteristic, device, terminal and storage medium |
| CN110363067A (en) * | 2019-05-24 | 2019-10-22 | 深圳壹账通智能科技有限公司 | Auth method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111159682B (en) | 2023-03-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9977952B2 (en) | Organizing images by correlating faces | |
| KR20170025802A (en) | Method and apparatus for authentication based on fingerprint recognition | |
| CN102365645A (en) | Organizing digital images by correlating faces | |
| US8260060B2 (en) | Comparison method, comparison system, computer, and program | |
| US10586031B2 (en) | Biometric authentication of a user | |
| JP2010146073A (en) | Biometric authentication device, biometric authentication method, computer program for biometric authentication and computer system | |
| CN108154099B (en) | Figure identification method and device and electronic equipment | |
| CN106228054A (en) | Auth method and device | |
| US9183430B2 (en) | Portable electronic apparatus and interactive human face login method | |
| US9292752B2 (en) | Image processing device and image processing method | |
| CN104598792A (en) | Terminal | |
| JP5659777B2 (en) | Authentication processing apparatus, authentication processing method, and program | |
| WO2018198500A1 (en) | Collation device, collation method and collation program | |
| CN111103981B (en) | Control instruction generation method and device | |
| TWI795930B (en) | Fingerprint-based authentication using touch inputs | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN111159682B (en) | Man-machine interaction authentication method and device, electronic equipment and storage medium | |
| KR20140049705A (en) | Fingerprint locking system | |
| KR20170045944A (en) | Method for unlocking security status of security processed object and apparatus thereof | |
| KR102337217B1 (en) | Electric apparatus and operation method thereof | |
| CN107516024B (en) | Method and device for unlocking electronic equipment and electronic equipment | |
| JP4270842B2 (en) | Fingerprint verification device | |
| WO2018018787A1 (en) | Password authentication method and device, mobile terminal, and computer storage medium | |
| CN115497146B (en) | Model training method and device and identity verification method and device | |
| US20230237131A1 (en) | Information processing device, information processing method, and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |