CN114428946A

CN114428946A - Human skeleton-based verification method and device and storage medium

Info

Publication number: CN114428946A
Application number: CN202111653289.3A
Authority: CN
Inventors: 周晓晓; 李琳; 周冰; 周效军; 李东晓
Original assignee: China Mobile Communications Group Co Ltd; MIGU Culture Technology Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; MIGU Culture Technology Co Ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2022-05-03

Abstract

The embodiment of the application discloses a human skeleton-based verification method, a human skeleton-based verification device and a storage medium, which can improve the difficulty coefficient of identification and cracking so as to improve the safety and accuracy of verification. The method in the embodiment of the application comprises the following steps: acquiring verification source information, and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information; receiving first operation information sent by the visitor through a client, wherein the first operation information is used for determining a selected bone map selected by the visitor, and the selected bone map is contained in the correct bone map and a corresponding interference bone map; and verifying the visitor according to the selected skeleton map and the correct skeleton map.

Description

Human skeleton-based verification method and device and storage medium

Technical Field

The present application relates to the field of network security verification, and in particular, to a human skeleton-based verification method, device, and storage medium.

Background

In the internet era, authentication codes are certainly something people are unfamiliar with. The verification codes generated by the prior art are represented in various forms, such as numbers, letters or random combinations, characters or specific elements contained in pictures, four arithmetic operations of randomly generating two elements, pattern matching verification codes and the like. Many input schemes have many verification code elements such as numbers, letters and patterns, and in the context of random verification codes, most schemes only need one operation by a user, such as inputting numbers and letters, or sliding a slider once to a specific position.

When the verification code is popular, the times of user operation are less, such as inputting numbers and letters, or sliding the slider once to a specific position, thereby causing the cost of machine processing to be reduced; the verification codes are easy to understand and low in complexity, so that the cracking method is continuously updated, and malicious behaviors such as automatic batch registration cannot be effectively prevented.

Therefore, how to provide an authentication method to improve the complexity of the authentication code so as to more accurately identify whether the visitor is a real user or a machine is a problem that needs to be solved at present.

Disclosure of Invention

The embodiment of the application provides a human skeleton-based verification method, a human skeleton-based verification device and a storage medium, which are used for improving the difficulty coefficient of identification and cracking so as to improve the safety and accuracy of verification.

The first aspect of the present application provides, may include: acquiring verification source information, and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information; receiving first operation information sent by the visitor through a client, wherein the first operation information is used for determining a selected bone map selected by the visitor, and the selected bone map is contained in the correct bone map and a corresponding interference bone map; and verifying the visitor according to the selected skeleton map and the correct skeleton map.

In a possible design, when the verification source information is a verification source picture, after receiving first operation information sent by the visitor through a client, the method further includes: if the selected skeleton map is consistent with the correct skeleton map, receiving second operation information of the visitor, wherein the second operation information is used for moving the skeleton map to a first target position in the verification source picture; and if the first position deviation between the first target position and the corresponding position of the correct skeleton map in the verification source picture is smaller than a preset value, determining that the preset condition is met.

In a possible design, when the verification source information is a verification source picture, after the verification source information is acquired, before the first operation information sent by the visitor is received, the method further includes: identifying a human body in the verification source picture, and acquiring basic skeleton features of the human body, wherein the basic skeleton features comprise N pieces of skeleton key point information and connection line information among all skeleton key points, and N is a preset integer; establishing a correct skeleton map of the human body according to the basic skeleton features of the human body, and determining M interference skeleton maps corresponding to the correct skeleton map, wherein M is a positive integer; and randomly arranging and displaying the correct skeleton map of the human body and the M interference skeleton maps so that a visitor can check according to the checking source picture.

In a possible design, when the verification source information is a verification source picture, after the verification source information is obtained, before the first operation information sent by the client, the method further includes: identifying a human body in the verification source picture, and acquiring basic skeleton features of the human body, wherein the basic skeleton features comprise N pieces of skeleton key point information and connection line information among all skeleton key points, and N is a preset integer; establishing a correct skeleton map of the human body according to the basic skeleton features of the human body, and determining M interference skeleton maps corresponding to the correct skeleton map, wherein M is a positive integer; and randomly arranging and displaying the correct skeleton map of the human body and the M interference skeleton maps so that a visitor can check according to the checking source picture.

In one possible design, the determining M interfering bone maps corresponding to the correct bone map comprises: randomly selecting N skeleton key points from the N skeleton key points, and performing offset conversion on the coordinates of the N skeleton key points to obtain N conversion coordinates; generating the interference skeleton map according to the n conversion coordinates; or, selecting the M bone maps from a preset bone feature database as the interference bone map.

In one possible design, after the obtaining of the basic bone features of the human body, the method further comprises: and generating T skeleton line segment graphs based on the connection information among the skeleton key points, wherein the end points of the T skeleton line segments are different, and the shapes of the end points of the skeleton line segment graphs are different.

In one possible design, the method further includes:

if the correct skeleton map is a partial skeleton map, replacing skeleton lines corresponding to the partial skeleton map with corresponding skeleton line segments in the verification source picture, and displaying the rest skeleton line segments to prompt the visitor to correspondingly move the n skeleton line segments to corresponding positions in the verification source picture;

receiving third operation information sent by the visitor, wherein the third operation information is used for moving each displayed skeleton line segment to each second target position in the verification source picture;

and if the deviation between the second target position and the second position of the corresponding position of each displayed skeleton line segment in the verification source picture is smaller than a preset value, determining that the preset condition is met.

In one possible design, after replacing, in the verification source picture, the bone line corresponding to the partial bone map with the corresponding bone line segment and displaying n bone line segments of the remaining bone line segments, the method further includes:

highlighting a bone region to be replaced in the verification source picture, and prompting the visitor to select a bone line segment corresponding to the bone region to be replaced from the rest bone line segments;

receiving fourth operation information sent by the visitor, wherein the fourth operation information is used for determining a target bone line segment selected by the visitor;

and if the target bone line segment is not consistent with the bone line segment corresponding to the bone region to be replaced, determining that the preset condition is not met.

In one possible design, the acquiring the basic bone features of the human body comprises: and inputting the verification source picture into a preset skeleton recognition model, and outputting a skeleton key point result graph, wherein N pieces of skeleton key point information and connection information among all skeleton key points are marked in the skeleton key point result graph.

A second aspect of the present application provides a verification apparatus, including:

the system comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is used for acquiring verification source information, and the verification source information is used for determining that a correct skeleton diagram and M interference skeleton diagrams of a human body are randomly arranged and displayed so that a visitor can verify the correct skeleton diagram and the M interference skeleton diagrams;

the receiving and sending unit is used for receiving first operation information sent by the visitor, and the first operation information is used for selecting the skeleton map of the verification source picture;

and the determining unit is used for determining that the visitor has legal access and passes the legal access if a preset condition is met, wherein the preset condition comprises that the skeleton map is consistent with the correct skeleton map.

A third aspect of the present application provides a computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable message which causes the processor to execute the steps of the human skeleton-based verification method.

A fourth aspect of the present application provides a computer-readable storage medium having at least one executable message stored therein, which when run on a computing device, causes the computing device to perform the human bone-based verification method according to the first aspect of the present application.

A fifth aspect of the present application discloses a computer program product, which, when run on a computer, causes the computer to perform the method for human bone based verification according to the first aspect of the present application.

A sixth aspect of the present application discloses an application publishing platform for publishing a computer program product, wherein when the computer program product runs on a computer, the computer is caused to execute the human skeleton-based verification method of the first aspect of the present application.

According to the technical scheme, the embodiment of the application has the following advantages: acquiring verification source information, and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information; receiving first operation information sent by the visitor through a client, wherein the first operation information is used for determining a selected bone map selected by the visitor, and the selected bone map is contained in the correct bone map and a corresponding interference bone map; and verifying the visitor according to the selected skeleton map and the correct skeleton map. The difficulty coefficient of identifying the solution can be improved, so that the safety and the accuracy of verification are improved.

Drawings

The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1a is a schematic view of an embodiment of a human skeleton-based verification method provided in an embodiment of the present application;

fig. 1b is a possible verification source picture provided in the embodiment of the present application;

FIG. 1c is a diagram of possible human key bone point identification provided by an embodiment of the present application;

fig. 1d is another possible verification source picture provided in the embodiment of the present application;

FIG. 1e is an exemplary illustration of a skeletal map and an interfering skeletal map provided by an embodiment of the present application;

FIG. 1f is a schematic diagram of a possible skeleton line segment of a graphic block according to an embodiment of the present disclosure;

FIG. 1g is a schematic diagram of the correct selection and movement of bones provided by the embodiments of the present application;

FIG. 1h is a schematic diagram of a possible visitor verification skeleton line segment according to an embodiment of the present disclosure;

FIG. 1i is a schematic diagram of one possible method for selecting and moving all bone segments correctly according to an embodiment of the present disclosure;

fig. 2 is a schematic view of a virtual structure of a verification apparatus according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of a hardware structure of another terminal device according to an embodiment of the present application.

Detailed Description

For a person skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. The embodiments in the present application shall fall within the protection scope of the present application.

Referring to fig. 1a, fig. 1a is a schematic flow chart of a human bone-based verification method according to an embodiment of the present application:

101. and acquiring verification source information, and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information.

The verification source information is used for determining that a correct skeleton diagram and M interference skeleton diagrams of a human body are randomly arranged and displayed, so that a visitor conducts verification.

Specifically, the method comprises the following steps:

1011. acquiring verification source information, identifying a human body in the verification source information, and acquiring basic skeleton characteristics of the human body;

in the embodiments of the present application, in order to facilitate better understanding of the embodiments of the present application, a human body is taken as an example for description. Specifically, verification source information is obtained, wherein in the embodiment of the present application, the verification source information may be a verification source picture or other verification information. In the embodiment of the application, the verification source information is taken as a verification source picture for example, and the verification source picture can be randomly selected from a preset picture library or generated by combining according to a preset pattern. After the verification source picture is obtained, identifying a human body in the verification source picture to obtain basic skeleton features of the human body, wherein the basic skeleton features comprise N pieces of skeleton key point information and connection line information among all skeleton key points, N is a preset integer, and N can be set to be 9, 14, 16, 18 and the like in practical application and can be specifically determined according to practical requirements. For example, referring to fig. 1b, a possible verification source picture provided by the embodiment of the present application is identified to obtain a result graph of human skeleton key points, as shown in fig. 1c, it can be known that the identification result includes 14 human skeleton key points and a symmetric relationship between a connection line corresponding to the skeleton key point and a skeleton, where the 14 human skeleton key points are respectively: point P1 (vertex), point P2 (neck), point P3 (left shoulder), point P4 (left elbow), point P5 (left wrist), point P6 (right shoulder), point P7 (right elbow), point P8 (right wrist), point P9 (left hip), point P10 (left knee), point P11 (left ankle), point P12 (right hip), point P13 (right knee), point P14 (right ankle). The format is as follows: KeyPoi nt ═ p1: [ x1, y1], p2: [ x2, y2], p3: [ x3, y3], p4: [ x4, y4], p5: [ x5, y5], p6: [ x6, y6], p7: [ x7, y7], p8: [ x8, y8], p9: [ x9, y9], p10: [ x10, y10], p11: [ x11, y11], p12: [ x12, y12], p13: [ x13, y13], p14: [ x14, y14] }, wherein p1 is a bone point identifier, and [ x1, y1] is a coordinate point.

The connecting method of the key points of the human skeleton comprises the following steps: line L1 (vertex P1-neck P2), line L2 (neck P2-left shoulder P3), line L3 (neck P2-right shoulder P6), line L4 (neck P2-left hip P9), line L5 (neck P2-right hip P12), line L6 (left shoulder P6-left elbow P6), line L6 (left elbow P6-left wrist P6), line L6 (right shoulder P6-right elbow P6), line L6 (right elbow P6-right elbow P6), line L6 (left hip P6-right hip P6), line L6 (left hip P6-left knee P6), line L6 (left hip P6-left ankle P6-right hip P6), line L6 (right hip P6-right knee P6), line L6 (right hip P6-right ankle P6-right hip P6). The format is as follows:

SkeketonLine＝{L1:[len1,p1,p2],L2:[len2,p2,p3],L3:[len3,p2,p6],L4:[len4,p2,p9],L5:[len5,p2,p12],L6:[len6,p3,p4],L7:[len7,p4,p5],L8:[len8,p6,p7],L9:[len9,p7,p8],L10:[len10,p9,p12],L11:[len11,p9,p10],L12:[len12,p10,p11],L13:[len13,p12,p13],L14:[len14,p13,p14]}，

wherein L1 is the mark of the skeleton line, len1 is the length of the line, and p1 and p2 are the marks of the skeleton point.

In addition, in the embodiment of the present application, acquiring the basic bone features of the human body includes: and inputting the verification source picture into a preset skeleton recognition model, and outputting a skeleton key point result graph, wherein N pieces of skeleton key point information and connection line information among all skeleton key points are marked in the skeleton key point result graph.

In addition, the number of the human bodies in the verification source picture may be one or more, and the postures of the human bodies may also be different from each other, and the specific details are not limited herein.

1012. Establishing a correct skeleton map of the human body according to the basic skeleton features of the human body, and determining M interference skeleton maps corresponding to the correct skeleton map;

1013. randomly arranging and displaying the correct skeleton map and the M interference skeleton maps of the human body so that a visitor can check according to the checking source picture;

after the basic skeleton features of the human body are obtained, a correct skeleton map of the human body is established according to the basic skeleton features of the human body, and M interference skeleton maps corresponding to the correct skeleton map are determined for verification by an accessor, wherein M is a positive integer. It should be noted that the correct bone map may be a complete bone map or a partial bone map.

For example, take fig. 1d as an example. For another possible verification source picture provided by the embodiment of the present application, there are two human bodies in fig. 1d, for the convenience of distinction, the left side is human body M1, the right side is human body M2, a 14-point complete bone map is established according to the bone basic features of M1, a 5-point partial bone map is established according to the bone basic features of M2, and then 2 corresponding interference bone maps are generated respectively. The specific way of establishing the partial skeleton map of 5 points of the specific M2 may be as follows: determining the number of key points num, random, and randint (5,11) that M2 needs to display, for example, randomly selecting 5 key points, randomly selecting a starting point start, random, and randint (1,15) from 14 key points, for example, randomly selecting P2, and then selecting 4 other bone points (P2, P3, P4, P5, and P6) interconnected with P2 according to a bone connection line SkeketonLine, and then establishing a partial bone map of the 5 bone points.

The interference skeleton map is established in the following ways: 1. randomly selecting N points from a skeletal key point set KeyPoint1 in M1, and respectively carrying out offset conversion on the coordinates of the N points. For example, the coordinates of point P1 are [ x1, y1], and then the offset-converted coordinates are: [ x1- Δ x1, y1- Δ y1], wherein Δ x1, Δ y1 are coordinate offset values. And regenerating a skeleton point connecting line and a complete skeleton map based on the coordinates of the N points after conversion, wherein the skeleton point connecting line and the complete skeleton map are the interference skeleton map of M1. 2. And selecting a plurality of bone images of different human bodies from the bone feature database as interference bone images. The skeleton feature database is established by storing a large number of human body pictures and acquiring human body skeleton features through deep learning model recognition. Therefore, there are various ways to generate the interference graph, and the details are not limited herein.

Referring to fig. 1e, an exemplary diagram of a bone map and an interfering bone map is provided in the present application, which includes a complete bone map and 2 interfering bone maps of M1, and a partial bone map and 2 interfering bone maps of M2, the complete bone map and 2 interfering bone maps of M1 are randomly arranged, and the partial bone map and 2 interfering bone maps of M2 are randomly arranged and then displayed to a visitor, so that the visitor can verify the results.

102. Receiving first operation information sent by the visitor through a client, wherein the first operation information is used for determining the selected skeleton map selected by the visitor.

103. And verifying the visitor according to the selected skeleton map and the correct skeleton map.

After the display is carried out on a visitor, receiving first operation information sent by the visitor, wherein the first operation information is used for selecting a skeleton map of the verification source picture; and if a preset condition is met, wherein the preset condition comprises that the skeleton map is consistent with the correct skeleton map, determining that the visitor is legal to access and passes the visitor. And if the preset condition is not met, determining that the visitor is illegal access and refusing to pass.

Optionally, in order to increase difficulty and accuracy of verification, after receiving the first operation information sent by the visitor, before determining that the visitor is a legal visit and passes the legal visit, the method may further include:

if the selected skeleton map is consistent with the correct skeleton map, receiving second operation information of the visitor, wherein the second operation information is used for moving the skeleton map to a first target position in the verification source picture; and if the first position deviation between the first target position and the corresponding position of the correct skeleton map in the verification source picture is smaller than a preset value, determining that the preset condition is met.

Or, based on the connection information between the bone key points, generating T bone line segment graphs, where the end points of the T bone line segments are different, and the shapes of the end points of the bone line segment graphs are different. For example, 14 bone segments D1 to D14 are regenerated based on M2 in the following manner: firstly, allocating graph blocks for 14 key points, wherein the graph blocks are selected in various ways, for example, the graph blocks can be selected from the following forms, and the details are not limited herein: triangular, square, rectangular, trapezoidal, diamond, pentagonal, hexagonal, and the like. Secondly, based on a skeleton connecting mode Skeketonline in M2, connecting according to the graph blocks corresponding to the key points. In the generated 14 skeleton lines, the posture and the length of each skeleton line are unchanged, and two end points of each skeleton line are respectively graph blocks corresponding to the key points. The regenerated 14 bone line segments D are shown in fig. 1f, which is a schematic diagram of one possible bone line segment of the graphic block provided in the embodiment of the present application.

Further, the color of the bone line segment D is optionally variable. Wherein the color selection mode can be selected according to the color tuner. The selection can also be made according to the following way: for example, the skeleton line segment has a color slider, when the slider is moved, the skeleton line segment displays a plurality of color areas, when the slider is moved to a certain color area, the color of the skeleton line segment changes to the color, and in another embodiment, the color can be changed by pressing the screen with different force. And finally, randomly arranging and displaying the complete skeleton map and the interference skeleton map of the M1 below the picture of the client side, and similarly, randomly arranging and displaying the skeleton map and the interference skeleton map of the M2 below the picture of the client side to wait for the user to verify.

Optionally, if the correct skeleton map is a partial skeleton map, replacing, in the verification source picture, skeleton lines corresponding to the partial skeleton map with corresponding skeleton line segments, and displaying the remaining skeleton line segments, so as to prompt the visitor to correspondingly move the n skeleton line segments to corresponding positions in the verification source picture; receiving third operation information sent by the visitor, wherein the third operation information is used for moving each displayed skeleton line segment to each second target position in the verification source picture; and if the deviation between the second target position and the second position of the corresponding position of each displayed skeleton line segment in the verification source picture is smaller than a preset value, determining that the preset condition is met.

In the verification source picture, replacing the bone lines corresponding to the partial bone map with corresponding bone line segments, and displaying n bone line segments in the rest bone line segments, wherein the method further comprises the following steps: highlighting a bone region to be replaced in the verification source picture, and prompting the visitor to select a bone line segment corresponding to the bone region to be replaced from the rest bone line segments; receiving fourth operation information sent by the visitor, wherein the fourth operation information is used for determining a target bone line segment selected by the visitor; and if the target bone line segment is inconsistent with the bone line segment corresponding to the bone area to be replaced, determining that the preset condition is not met. It should be noted that there are various ways to highlight the bone region to be replaced, including increasing the brightness of the bone region to be replaced or marking the bone region to be replaced, and the details are not limited herein.

In order to better understand the present solution, fig. 1d is used as a calibration source diagram to perform display verification on the visitor, and the specific flow includes the following steps:

as shown in fig. 1f, there are two people in the image, and the full skeleton map of 14 key points of the left person and 2 interference items thereof are displayed below the image, and the partial skeleton map of 5 key points of the right person and 2 interference items thereof are displayed.

The first step is as follows: the visitor needs to select the correct skeleton map for each person separately and move the skeleton map to the appropriate position in the image separately so that the moved skeleton map corresponds to the skeleton points of the person in the image or the positional deviation is within a certain threshold. If the wrong skeleton map is selected, namely the selected skeleton is an interference item, or the position deviation of the moving skeleton map is large, the prompt is not passed. If the selected skeleton map is correct and the moved position is correct, as shown in fig. 1g, which is a correct selection and movement skeleton map provided by the embodiment of the present application, the next step is performed.

The second step is that: as shown in fig. 1h, all the 4 skeleton lines in the partial skeleton map of the 5 key points are replaced by the corresponding skeleton line segment D generated by the server, and the remaining 10 skeleton line segments are displayed below. The visitor judges the posture and length of the bone line segment and the graphic block of the end point according to the complete bone graph which is verified successfully on the left side in fig. 1h, selects a correct bone line segment D from the bone line segment and moves the bone line segment D to a proper position in the image, so that two end points of the moved bone line segment are correspondingly connected with the bone point of the person in the image, wherein fig. 1h is a schematic diagram of verifying the bone line segment by the visitor.

If the selected skeleton line is not consistent with the actual skeleton line D, the selected skeleton line includes the following scenes: if the length of the selected skeleton line segment is inconsistent with the actual length and the graphic block of the end point of the selected skeleton line segment is inconsistent with the actual length, the prompt is failed;

if the moving position is incorrect, the situation is included: if the two end points of the skeleton line segment are not correspondingly connected with the skeleton point, the prompt is not passed;

if the bone line selection is correct and the moving position is correct, the next bone line segment from the rest color-variable bone line segments is continuously selected and moved to the correct position until all the bone line segments pass through, the verification is passed, as shown in fig. 1i, and the next step is carried out.

Fourthly, further, randomly selecting N (N <14) bone line segments from the total 14 bone line segments as color-variable bone line segments, and keeping the colors of the rest 14-N bone line segments consistent. And (3) the visitor needs to respectively adjust the color of each variable-color skeleton line segment D, so that the colors of 14 skeleton line segments are all consistent, the verification is successful, the legal access is determined and the release is allowed, and otherwise, the release is refused due to the verification failure.

Further, the difficulty level of the verification code may be adjusted according to the number of people in the image, the number of given person skeleton points, the number of skeleton lines, the number of color-changeable skeleton line segments, and the like, and is not limited herein.

In the embodiment of the application, the difficulty of verification code cracking is increased by marking the key points and the connecting lines of the human skeleton; automatically completing verification of the verification code based on a deep learning image identification technology; meanwhile, the key points of human bones are used as verification codes, the display and the style of the existing verification codes are innovatively improved, and the update of the current verification codes is effectively solved. Through the mode of interacting with the visitor many times, the cost and the time of machine cracking have been promoted, have reached fine anti-brush purpose, increase certain interest again simultaneously. The method can be used for a plurality of scenes such as user login and payment.

The present application is described above in terms of a human skeleton-based verification method, and the present application is described below in terms of a verification device.

Referring to fig. 2, fig. 2 is a schematic view of a virtual structure of a verification apparatus according to an embodiment of the present application, where the verification apparatus 200 includes:

an obtaining unit 201, configured to obtain verification source information, and determine a correct skeleton map and a corresponding interference skeleton map according to the verification source information;

a transceiver unit 202, configured to receive first operation information sent by the visitor through a client, where the first operation information is used to determine a selected bone map selected by the visitor, and the selected bone map is included in the correct bone map and a corresponding interfering bone map;

a verification unit 203, configured to verify the visitor according to the selected bone map and the correct bone map.

The specific working process of the checking device in the embodiment of the present invention is substantially the same as that in the above method embodiment, and is not described herein again.

In the embodiment of the application, the difficulty coefficient of the cracked identification is enhanced by increasing the number of times of the operation of the visitor, so that the processing cost of the machine is promoted to be increased; 2. the method is characterized in that a human skeleton recognition mode is adopted, skeleton point features are obtained according to a deep learning algorithm, a user manually selects specific skeleton points, rule verification is completed, and then verification codes are unlocked, so that brute force hard solution of a machine algorithm is invalid, and the safety of the machine algorithm is improved; 3. rich pictures can generate multi-style verification codes, and the problem of machine learning algorithm identification is solved.

Referring to fig. 3 again, fig. 3 is a schematic diagram of a hardware structure of a computing device 300 according to an embodiment of the present disclosure, where the computing device 300 may execute the human skeleton-based verification method described above, and may be applied in the application scenario shown in fig. 1 and correspond to the verification apparatus in fig. 1. The computing device 300 may be a smartphone, a Personal Computer, a Tablet PC, a PAD, or the like.

Specifically, as shown in fig. 4, the computing device 400 includes: at least one processor 401, at least one network interface 404 or other visitor interface 403, memory 405, and at least one communication bus 402. The communication bus 402 is used to enable connection communication between these components. The terminal device 400 optionally contains a visitor interface 403 including a display (e.g., a touch screen, LCD, CTR, Holographic (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (e.g., a mouse, trackball (trackbal), touch pad or touch screen, etc.).

Memory 405 may include both read-only memory and random access memory and provides information and data to the processor. A portion of the memory 405 may also include non-volatile random access memory (NVRAM).

In some embodiments, memory 405 stores the following elements, executable modules or data structures, or a subset thereof, or an expanded set thereof:

an operating system 4051, which contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

the application module 4052 contains various applications, such as a desktop (launcher), a Media Player (Media Player), a Browser (Browser), etc., for implementing various application services.

In the embodiment of the present application, all the operations performed by the verification apparatus described above are implemented by calling a program or information stored in the memory 405.

The present application further provides a computer-readable storage medium, in which at least one executable instruction is stored, and when the executable instruction is run on a computing device, the computing device is caused to execute the verification method according to any of the above embodiments.

In the above embodiments, all or part of the implementation may be 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 application 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 can be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optics, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more 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 is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, 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, the division of the units is only one logical division, and other divisions may be realized in practice, 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.

The 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 solution of the embodiment.

In addition, functional units in the embodiments of the present application 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 may be implemented in the form of hardware, or may also be implemented in the 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 application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. 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 various media capable of storing program codes.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A human skeleton-based verification method is characterized by comprising the following steps:

acquiring verification source information, and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information;

receiving first operation information sent by the visitor through a client, wherein the first operation information is used for determining a selected bone map selected by the visitor, and the selected bone map is contained in the correct bone map and a corresponding interference bone map;

and verifying the visitor according to the selected skeleton map and the correct skeleton map.

2. The method according to claim 1, wherein when the verification source information is a verification source picture, after receiving first operation information sent by the visitor through a client, the method further comprises:

if the selected bone map is consistent with the correct bone map, receiving second operation information of the visitor, wherein the second operation information is used for moving the bone map to a first target position in the verification source picture;

and if the first position deviation between the first target position and the corresponding position of the correct skeleton map in the verification source picture is smaller than a preset value, determining that the preset condition is met.

3. The method according to claim 1, wherein when the verification source information is a verification source picture, after the verification source information is acquired, before the first operation information sent by the client, the method further comprises:

identifying a human body in the verification source picture, and acquiring basic skeleton features of the human body, wherein the basic skeleton features comprise N pieces of skeleton key point information and connection line information among all skeleton key points, and N is a preset integer;

establishing a correct skeleton map of the human body according to the basic skeleton features of the human body, and determining M interference skeleton maps corresponding to the correct skeleton map, wherein M is a positive integer;

and randomly arranging and displaying the correct skeleton map of the human body and the M interference skeleton maps so that a visitor can check according to the checking source picture.

4. The method of claim 3, wherein said determining M interfering bone maps corresponding to said correct bone map comprises:

randomly selecting N skeleton key points from the N skeleton key points, and performing offset conversion on the coordinates of the N skeleton key points to obtain N conversion coordinates;

generating the interference skeleton map according to the n conversion coordinates;

alternatively, the first and second electrodes may be,

selecting the M bone maps from a preset bone feature database as the interference bone map.

5. The method of claim 3, wherein after said obtaining of said basic bone features of said human body, said method further comprises:

and generating T skeleton line segment graphs based on the connection information among the skeleton key points, wherein the end points of the T skeleton line segments are different, and the shapes of the end points of the skeleton line segment graphs are different.

6. The method of claim 5, further comprising:

and if the deviation of the second target position and the second position of the corresponding position of each displayed skeleton line segment in the verification source picture is smaller than a preset value, determining that the preset condition is met.

7. The method of claim 6, wherein after replacing the bone line corresponding to the partial bone map with the corresponding bone line segment and displaying n bone line segments of the remaining bone line segments in the verification source picture, the method further comprises:

highlighting the bone region to be replaced in the verification source picture, and prompting the visitor to select a bone line segment corresponding to the bone region to be replaced from the rest bone line segments;

8. A verification device, comprising:

the acquisition unit is used for acquiring verification source information and determining a correct skeleton map and a corresponding interference skeleton map according to the verification source information;

the receiving and sending unit is used for receiving first operation information sent by the visitor through a client, the first operation information is used for determining a selected bone map selected by the visitor, and the selected bone map is contained in the correct bone map and a corresponding interference bone map;

and the verification unit is used for verifying the visitor according to the selected bone map and the correct bone map.

9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the human bone based verification method according to any one of claims 1-7.

10. A computer-readable storage medium having stored therein at least one executable instruction which, when run on a computing device, causes the computing device to perform the human bone-based verification method of any one of claims 1 to 7.