A verification method, device and storage medium based on human skeleton

Abstract

The embodiment of the present application discloses a verification method, device, and storage medium based on the human skeleton, which can increase the difficulty coefficient of identifying cracking to improve the security and accuracy of verification. The method of the embodiment of the present application includes: obtaining verification source information, and determining the correct skeleton diagram and the corresponding interference skeleton diagram based on the verification source information; receiving first operation information sent by the visitor through the client, the first operation information is used to determine the selected skeleton diagram selected by the visitor, and the selected skeleton diagram is included in the correct skeleton diagram and the corresponding interference skeleton diagram; and verifying the visitor based on the selected skeleton diagram and the correct skeleton diagram.

Description

Technical Field

[0001] The present application relates to the field of network security verification, and in particular to a verification method, device and storage medium based on human skeleton. Background Art

[0002] In the internet age, verification codes are undoubtedly familiar to everyone. Current technologies generate verification codes in a variety of forms, including numbers, letters, or random combinations; images containing text or specific elements; randomly generated binary arithmetic operations; and pattern matching verification codes. Verification code elements in many input schemes are mostly numbers, letters, or patterns. Given the randomness of verification codes, most schemes require only a single user action, such as entering numbers and letters or sliding a slider to a specific position.

[0003] The currently popular verification codes require fewer user operations, such as entering numbers and letters, or sliding a slider to a specific position, which reduces the cost of machine processing. These verification codes are easy to understand and have low complexity, resulting in constant updates in cracking methods, which cannot effectively prevent malicious behaviors such as automatic batch registration.

[0004] Therefore, how to provide a verification method that can increase the complexity of the verification 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 urgently. Summary of the Invention

[0005] The embodiments of the present application provide a verification method, device and storage medium based on human skeleton, which are used to increase the difficulty coefficient of identification cracking to improve the security and accuracy of verification.

[0006] The first aspect of the present application provides, which may include: obtaining verification source information, and determining the correct skeletal diagram and the corresponding interference skeletal diagram based on the verification source information; receiving first operation information sent by the visitor through the client, the first operation information being used to determine the selected skeletal diagram selected by the visitor, the selected skeletal diagram being included in the correct skeletal diagram and the corresponding interference skeletal diagram; and verifying the visitor based on the selected skeletal diagram and the correct skeletal diagram.

[0007] In one possible design, when the verification source information is a verification source image, after receiving the first operation information sent by the visitor through the client, the method also includes: if the selected skeleton image is consistent with the correct skeleton image, receiving the visitor's second operation information, the second operation information being used to move the skeleton image to a first target position in the verification source image; if the first position deviation between the first target position and the corresponding position of the correct skeleton image in the verification source image is less than a preset value, it is determined that the preset condition is met.

[0008] In a possible design, when the verification source information is a verification source picture, after obtaining the verification source information and before receiving the first operation information sent by the visitor, the method also includes: identifying the human body in the verification source picture and obtaining the basic skeletal features of the human body, the basic skeletal features including N skeletal key point information and connection information between each skeletal key point, where N is a preset integer; establishing a correct skeletal map of the human body based on the basic skeletal features of the human body, and determining M interference skeletal maps corresponding to the correct skeletal map, where M is a positive integer; and randomly arranging and displaying the correct skeletal map of the human body and the M interference skeletal maps, so that the visitor can perform verification based on the verification source picture.

[0009] In a possible design, when the verification source information is a verification source picture, after obtaining the verification source information and before sending the first operation information through the client, the method also includes: identifying the human body in the verification source picture and obtaining the basic skeletal features of the human body, the basic skeletal features including N skeletal key point information and connection information between each skeletal key point, where N is a preset integer; establishing a correct skeletal map of the human body according to the basic skeletal features of the human body, and determining M interference skeletal maps corresponding to the correct skeletal map, where M is a positive integer; and randomly arranging and displaying the correct skeletal map of the human body and the M interference skeletal maps, so that visitors can perform verification according to the verification source picture.

[0010] In one possible design, determining M interfering skeletal graphs corresponding to the correct skeletal graph includes: randomly selecting n skeletal key points from the N skeletal key points, offsetting and transforming the coordinates of the n skeletal key points to obtain n transformed coordinates; generating the interfering skeletal graph based on the n transformed coordinates; or, selecting the M skeletal graphs as the interfering skeletal graph from a preset skeletal feature database.

[0011] In one possible design, after obtaining the basic skeletal features of the human body, the method further includes: generating T skeletal line segment graphs based on the connection information between the key points of the skeleton, the endpoints of the T skeletal line segments are different, and the shapes of the endpoints of the skeletal line segment graphs are different.

[0012] In one possible design, the method further includes:

[0013] If the correct skeleton diagram is a partial skeleton diagram, then in the verification source image, the skeleton line corresponding to the partial skeleton diagram is replaced with the corresponding skeleton line segment, and the remaining skeleton line segments are displayed to prompt the visitor to move the n skeleton line segments to the corresponding positions in the verification source image;

[0014] receiving third operation information sent by the visitor, wherein the third operation information is used to move each displayed skeleton line segment to each second target position in the verification source image;

[0015] If a second position deviation between the second target position and the corresponding position of each displayed skeleton line segment in the verification source image is less than a preset value, it is determined that the preset condition is met.

[0016] In a possible design, in the verification source image, after replacing the skeleton lines corresponding to the partial skeleton image with corresponding skeleton line segments and displaying n skeleton line segments of the remaining skeleton line segments, the method further includes:

[0017] Highlighting the skeleton region to be replaced in the verification source image, and prompting the visitor to select a skeleton line segment corresponding to the skeleton region to be replaced from the remaining skeleton line segments;

[0018] receiving fourth operation information sent by the visitor, wherein the fourth operation information is used to determine a target skeleton line segment selected by the visitor;

[0019] If the target skeleton line segment is inconsistent with the skeleton line segment corresponding to the to-be-replaced skeleton region, it is determined that the preset condition is not satisfied.

[0020] In one possible design, obtaining the basic features of the human skeleton includes: inputting the verification source image into a preset bone recognition model, outputting a bone key point result map, and identifying N bone key point information and the connection information between each bone key point in the bone key point result map.

[0021] A second aspect of the present application provides a verification device, comprising:

[0022] An acquisition unit is used to acquire verification source information, wherein the verification source information is used to determine the correct human skeleton diagram and M interference skeleton diagrams, and randomly arrange and display them so that the visitor can perform verification;

[0023] a transceiver unit, configured to receive first operation information sent by the visitor, wherein the first operation information is used to select the skeleton diagram of the verification source image;

[0024] The determination unit is configured to determine that the visitor has legitimate access and allow the visitor to pass if a preset condition is met, wherein the preset condition includes that the skeleton diagram is consistent with the correct skeleton diagram.

[0025] A third aspect of the present application provides a computing device, characterized by comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0026] The memory is used to store at least one executable information, and the executable information enables the processor to execute the steps of the verification method based on human skeleton.

[0027] The fourth aspect of the present application provides a computer-readable storage medium, in which at least one executable information is stored. When the executable information is run on a computing device, the computing device executes the human skeleton-based verification method as described in the first aspect of the present application.

[0028] The fifth aspect of the present application discloses a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the human skeleton-based verification method described in the first aspect of the present application.

[0029] The sixth aspect of the present application discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes the human skeleton-based verification method described in the first aspect of the present application.

[0030] As can be seen from the above technical solution, the embodiment of the present application has the following advantages: obtaining verification source information and determining the correct skeleton diagram and the corresponding interference skeleton diagram based on the verification source information; receiving first operation information sent by the visitor through the client, the first operation information is used to determine the selected skeleton diagram selected by the visitor, and the selected skeleton diagram is included in the correct skeleton diagram and the corresponding interference skeleton diagram; verifying the visitor based on the selected skeleton diagram and the correct skeleton diagram. This can increase the difficulty coefficient of identifying cracking, thereby improving the security and accuracy of verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0032] Figure 1a A schematic diagram of an embodiment of a human skeleton-based verification method provided in an embodiment of the present application;

[0033] Figure 1b A possible verification source image provided in an embodiment of the present application;

[0034] Figure 1c A possible human body key bone point identification diagram provided in an embodiment of the present application;

[0035] Figure 1d Another possible verification source image provided in the embodiment of the present application;

[0036] Figure 1e An example diagram of a skeleton map and an interference skeleton map provided in an embodiment of the present application;

[0037] Figure 1f A possible schematic diagram of a graphic block skeleton line segment provided in an embodiment of the present application;

[0038] Figure 1g A schematic diagram of a correct selection and movement of a skeleton diagram provided in an embodiment of the present application;

[0039] Figure 1h A possible visitor verification skeleton segment schematic diagram provided in an embodiment of the present application;

[0040] Figure 1i A possible schematic diagram of correctly selecting and moving all skeletal line segments provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of the virtual structure of the verification device provided in an embodiment of the present application;

[0042] Figure 3 A schematic diagram of the hardware structure of a terminal device provided in an embodiment of the present application;

[0043] Figure 4 A schematic diagram of the hardware structure of another terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the present invention, the technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All embodiments in the present invention should fall within the scope of protection of the present invention.

[0045] See also Figure 1a , Figure 1a A schematic diagram of a human skeleton-based verification method provided in an embodiment of the present application:

[0046] 101. Obtain verification source information, and determine a correct skeleton graph and a corresponding interference skeleton graph based on the verification source information.

[0047] The verification source information is used to determine the correct human skeleton diagram and M interference skeleton diagrams, which are randomly arranged and displayed so that visitors can perform verification.

[0048] Specifically, the method includes the following steps:

[0049] 1011. Obtain verification source information, identify a human body in the verification source information, and obtain basic skeletal features of the human body;

[0050] In the embodiment of the present application, in order to facilitate a better understanding of the embodiment of the present application, the human body is used as an example for explanation. Specifically, the verification source information is obtained, wherein in the embodiment of the present application, the verification source information can be a verification source picture or other verification information. In the embodiment of the present application, the verification source information is taken as an example of a verification source picture, and the verification source picture can be randomly selected from a preset picture library, or combined according to a preset pattern to generate the verification source picture. After obtaining the verification source picture, the human body in the verification source picture is identified to obtain the basic skeletal features of the human body. The basic skeletal features include N skeletal key point information and the connection information between each skeletal key point. N is a preset integer. In actual applications, N can be set to 9, 14, 16, 18, etc., which can be determined according to actual needs. For example, please refer to Figure 1b As shown in FIG, a possible verification source image provided by an embodiment of the present application is identified by the verification source image to obtain a result image of the key points of the human skeleton, such as Figure 1c It can be seen that the recognition result includes 14 key points of the human skeleton and the connection lines and symmetric relationships of the corresponding key points of the skeleton. Among them, the 14 key points of the human skeleton are: point P1 (top of the head), 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), and point P14 (right ankle). The format is as follows: KeyPoint = {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]}, where p1 is the skeleton point identifier and [x1,y1] is the coordinate point.

[0051] The key points of the human skeleton are connected as follows: Line L1 (top of the head 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 P3-left elbow P4), Line L7 (left elbow P4-left wrist P5), Line L8 (right shoulder P6-right elbow P7), Line L9 (right elbow P7-right wrist P8), Line L10 (left hip P9-right hip P12), Line L11 (left hip P9-left knee P10), Line L12 (left knee P10-left ankle P11), Line L13 (right hip P12-right knee P13), Line L14 (right knee P13-right ankle P14). The format is as follows:

[0052] 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]},

[0053] Where L1 is the skeleton line identifier, len1 is the line length, and p1 and p2 are the skeleton point identifiers.

[0054] In addition, in an embodiment of the present application, obtaining the basic features of the human skeleton includes: inputting the verification source image into a preset bone recognition model, outputting a bone key point result graph, and identifying N bone key point information and the connection information between each bone key point in the bone key point result graph.

[0055] In addition, there may be one or more human bodies in the verification source image, and the postures of the human bodies may also be different, which is not specifically limited here.

[0056] 1012. Establish a correct skeleton map of the human body according to basic skeleton features of the human body, and determine M interfering skeleton maps corresponding to the correct skeleton map;

[0057] 1013. Randomly arrange and display the correct human skeleton diagram and the M interference skeleton diagrams, so that a visitor can perform verification according to the verification source image;

[0058] After obtaining the basic skeletal features of the human body, a correct skeletal map of the human body is established based on the basic skeletal features of the human body, and M interfering skeletal maps corresponding to the correct skeletal map are determined for verification by the visitor, where M is a positive integer. It should be noted that the correct skeletal map can be a complete skeletal map or a partial skeletal map.

[0059] For example, Figure 1d For example, another possible verification source image provided by the embodiment of the present application is: Figure 1d There are two human bodies in the image. To distinguish them, the left side is human body M1, and the right side is human body M2. Based on the basic skeletal features of M1, a complete skeletal map of 14 points is created. Based on the basic skeletal features of M2, a partial skeletal map of 5 points is created. Two corresponding interference skeletal maps are then generated for each. Specifically, the partial skeletal map of M2 with 5 points can be created by determining the number of key points to be displayed for M2 (num = random.randint(5,11), for example, 5 randomly selected key points. Then, a starting point (start = random.randint(1,15)) is randomly selected from the 14 key points, for example, P2. Then, based on the skeletal line SkeketonLine, the other four skeletal points connected to P2 (P2, P3, P4, P5, P6) are selected to create a partial skeletal map of the five skeletal points.

[0060] Among them, there are several ways to establish an interference skeleton map: 1. Randomly select N points from the skeleton key point set KeyPoint1 in M1, and offset the coordinates of the N points respectively. For example, the coordinates of point P1 are [x1, y1], then the coordinates after offset conversion are: [x1-Δx1, y1-Δy1], where Δx1, Δy1 are coordinate offset values. Based on the coordinates of the N points after conversion, the skeleton point connection lines and the complete skeleton map are regenerated, which is the interference skeleton map of M1. 2. Select several skeleton maps of different human bodies from the skeleton feature database as interference skeleton maps. The skeleton feature database is established by saving a large number of human body pictures and obtaining human skeleton features through deep learning model recognition. Therefore, there are many ways to generate interference maps, which are not limited here.

[0061] See also Figure 1e , which is an example diagram of a skeleton map and an interference skeleton map provided in an embodiment of the present application, including a complete skeleton map and 2 interference skeleton maps of M1, and a partial skeleton map and 2 interference skeleton maps of M2. The above-mentioned complete skeleton map and 2 interference skeleton maps of M1 are randomly arranged, and the partial skeleton map and 2 interference skeleton maps of M2 are randomly arranged and then displayed to the visitor so that the visitor can verify it.

[0062] 102. Receive first operation information sent by the visitor through the client, where the first operation information is used to determine the selected skeletal diagram selected by the visitor.

[0063] 103. Verify the visitor based on the selected skeleton diagram and the correct skeleton diagram.

[0064] After presenting the image to the visitor, first operation information sent by the visitor is received, wherein the first operation information is used to select the skeleton diagram of the verification source image; if a preset condition is met, including that the skeleton diagram is consistent with the correct skeleton diagram, the visitor is determined to have legitimate access and is allowed to access. If the preset condition is not met, the visitor is determined to have illegal access and is denied access.

[0065] Optionally, in order to increase the difficulty and accuracy of the verification, after receiving the first operation information sent by the visitor and before determining that the visitor's access is legal and allowing the visitor to pass, the following steps may also be performed:

[0066] If the selected skeleton diagram is consistent with the correct skeleton diagram, the visitor's second operation information is received, and the second operation information is used to move the skeleton diagram to a first target position in the verification source image; if the first position deviation between the first target position and the corresponding position of the correct skeleton diagram in the verification source image is less than a preset value, it is determined that the preset condition is met.

[0067] Alternatively, T skeleton line segment graphs can be generated based on the line information between the skeleton key points, and the endpoints of the T skeleton line segments are different, and the shapes of the endpoints of the skeleton line segment graphs are different. For example, 14 skeleton line segments D1 to D14 are regenerated based on M2, and the generation method is as follows: First, graphic blocks are assigned to the 14 key points, and the graphic blocks can be selected in various ways. For example, you can choose from the following forms, which are not limited here: triangle, square, rectangle, trapezoid, rhombus, pentagon, hexagon, etc. Secondly, based on the skeleton connection method SkeketonLine in M2, connect the lines according to the graphic blocks corresponding to the key points. Among the 14 generated skeleton lines, the posture and length of each skeleton line remain unchanged, and its two endpoints are the graphic blocks corresponding to the key points. The 14 regenerated skeleton line segments D, such as Figure 1f , which is a possible schematic diagram of a graphic block skeleton line segment provided in an embodiment of the present application.

[0068] Further, the color of skeleton line segment D can be changed by selection. Wherein the color selection mode can be selected according to the color mixer. Also can be selected according to the following method: for example, a color slider is arranged on the skeleton line segment, and when the slider is moved, the skeleton line segment shows a variety of color areas. When the slider moves to a certain color area, the color of the skeleton line segment becomes this color. In another embodiment, the conversion of color can be completed by pressing the different strengths of the screen. Finally, the complete skeleton diagram of M1 and its interference skeleton diagram are randomly arranged and displayed below the client picture. Equally, the skeleton diagram of M2 and its interference skeleton diagram are randomly arranged and displayed below the client picture, wait for the user to verify.

[0069] Optionally, if the correct skeleton diagram is a partial skeleton diagram, the skeleton line corresponding to the partial skeleton diagram is replaced with the corresponding skeleton line segment in the verification source image, and the remaining skeleton line segments are displayed to prompt the visitor to move the n skeleton line segments to the corresponding positions in the verification source image; receive the third operation information sent by the visitor, and the third operation information is used to move each displayed skeleton line segment to each second target position in the verification source image; if the second target position and the second position deviation of the corresponding position of each displayed skeleton line segment in the verification source image is less than a preset value, it is determined that the preset condition is met.

[0070] In the verification source image, after the skeleton lines corresponding to the partial skeleton diagram are replaced with corresponding skeleton line segments, and n skeleton line segments of the remaining skeleton line segments are displayed, the method further includes: highlighting the skeleton area to be replaced in the verification source image, and prompting the visitor to select the skeleton line segment corresponding to the skeleton area to be replaced from the remaining skeleton line segments; receiving the fourth operation information sent by the visitor, and the fourth operation information is used to determine the target skeleton line segment selected by the visitor; if the target skeleton line segment is inconsistent with the skeleton line segment corresponding to the skeleton area to be replaced, it is determined that the preset condition is not met. It should be noted that there are many ways to highlight the skeleton area to be replaced, including increasing the brightness of the skeleton area to be replaced or marking the skeleton area to be replaced, which is not limited here.

[0071] In order to better understand this program, Figure 1d As a calibration source image, a display calibration is performed on the visitor. The specific process includes the following steps:

[0072] like Figure 1f As shown, there are two people in the image. Below the image are shown a complete skeleton diagram of 14 key points of the left person and its two interference items, as well as a partial skeleton diagram of 5 key points of the right person and its two interference items.

[0073] Step 1: Visitors need to select the correct skeleton diagram for each character and move the skeleton diagram to the appropriate position in the image, so that the moved skeleton diagram corresponds to the skeleton point of the character in the image or the position deviation is within a certain threshold range. If the wrong skeleton diagram is selected, that is, the selected skeleton is an interference item, or the position deviation of the moved skeleton diagram is large, the user will be prompted to fail. If the selected skeleton diagram is correct and the moved position is correct, such as Figure 1g As shown, this is a schematic diagram of correctly selecting and moving the skeleton diagram provided in an embodiment of the present application, and then proceed to the next step.

[0074] Step 2: If Figure 1h As shown, the 4 skeleton lines in the partial skeleton diagram of the 5 key points are automatically replaced with the corresponding skeleton line segments D generated by the server, and the remaining 10 skeleton line segments are displayed below. Figure 1h The complete skeleton diagram on the left has been successfully verified. Then the posture, length and endpoint of the skeleton segment are judged, and the correct skeleton segment D is selected and moved to the appropriate position in the image so that the two endpoints of the moved skeleton segment are connected to the corresponding skeleton points of the character in the image. Figure 1h Verify the skeleton segment diagram for visitors.

[0075] If the selected skeleton line is inconsistent with the actual skeleton line D, including the following scenarios: the selected skeleton line segment length is inconsistent with the actual one, or the selected skeleton line segment endpoint graphic block is inconsistent with the actual one, then the prompt "fail" will be displayed;

[0076] If the moved position is incorrect, including the following scenarios: the two endpoints of the bone segment are not connected to the corresponding bone points, the prompt "fail" will appear;

[0077] If the skeleton line is selected correctly and the moving position is correct, then continue to select the next one from the remaining color-changing skeleton segments and move it to the correct position until all the skeleton segments pass, and the verification is passed. Figure 1i If shown, proceed to the next step.

[0078] In the fourth step, N (N < 14) of the 14 skeleton segments are randomly selected as color-changing skeleton segments, while the remaining 14-N skeleton segments remain the same color. The visitor needs to adjust the color of each color-changing skeleton segment D individually, so that all 14 skeleton segments have the same color. If the verification succeeds, the visit is deemed legitimate and is allowed to proceed. Otherwise, the verification fails and the visit is denied.

[0079] Furthermore, the difficulty of the verification code can be adjusted according to the number of characters in the image, the number of character skeleton points and skeleton lines, the number of color-changing skeleton line segments, etc., which are not specifically limited here.

[0080] In the embodiments of this application, the difficulty of cracking the verification code is increased by marking the key points of the human skeleton and connecting them. Based on deep learning image recognition technology, the verification code is automatically verified. At the same time, the key points of the human skeleton are used as the verification code, which innovatively improves the display and style of the existing verification code, effectively solving the problem of updating the current verification code. By interacting with the visitor multiple times, the cost and time of machine cracking are improved, achieving a good anti-scam purpose while adding a certain degree of fun. It can be used in many scenarios such as user login and payment.

[0081] The above describes the present application from the perspective of a verification method based on human skeleton, and the following describes the present application from the perspective of a verification device.

[0082] See also Figure 2 , Figure 2 This is a schematic diagram of a virtual structure of a verification device provided in an embodiment of the present application. The verification device 200 includes:

[0083] An acquisition unit 201 is configured to acquire verification source information and determine a correct skeleton graph and a corresponding interference skeleton graph based on the verification source information;

[0084] The transceiver unit 202 is configured to receive first operation information sent by the visitor via the client, wherein the first operation information is used to determine a selected skeleton diagram selected by the visitor, wherein the selected skeleton diagram is included in the correct skeleton diagram and the corresponding interference skeleton diagram;

[0085] The verification unit 203 is used to verify the visitor based on the selected skeleton diagram and the correct skeleton diagram.

[0086] The specific working process of the verification device in the embodiment of the present invention is generally consistent with the above method embodiment and will not be repeated here.

[0087] In the embodiment of the present application, by increasing the number of visitor operations, the difficulty coefficient of cracking and identification is enhanced, which leads to an increase in machine processing costs; 2. The human skeleton recognition method is adopted to obtain the bone point features according to the deep learning algorithm. The user manually selects the specific bone point, completes the rule verification, and then unlocks the verification code, which makes the brute force hard solution of the machine algorithm invalid and increases its security; 3. Rich pictures will produce a variety of verification codes, solving the problem of recognition by machine learning algorithms.

[0088] See also Figure 3 , Figure 3 The hardware structure diagram of a computing device 300 provided in an embodiment of the present application is as follows. The computing device 300 can execute the above-mentioned verification method based on human skeleton and can be applied in Figure 1a-Figure 1i In the application scenario shown, and corresponding Figure 1a-Figure 1iThe computing device 300 may be a smart phone, a personal computer, a tablet computer (Tablet Personal Computer, Tablet PC), a PAD, etc.

[0089] Specifically, such as Figure 4 As shown, 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 connect and communicate with these components. The terminal device 400 optionally includes a visitor interface 403, including a display (e.g., a touch screen, LCD, CTR, holographic imaging, or projector), a keyboard, or a pointing device (e.g., a mouse, trackball, touchpad, or touch screen).

[0090] The memory 405 may include a read-only memory and a random access memory and provide information and data to the processor. A portion of the memory 405 may also include a non-volatile random access memory (NVRAM).

[0091] In some embodiments, the memory 405 stores the following elements, executable modules or data structures, or a subset or extended set thereof:

[0092] Operating system 4051, including various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic services and process hardware-based tasks;

[0093] The application module 4052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0094] In the embodiment of the present application, all the operations performed by the verification device are implemented by calling the program or information stored in the memory 405.

[0095] The present application also provides a computer-readable storage medium, in which at least one executable instruction is stored. When the executable instruction is executed on a computing device, the computing device executes the verification method described in any of the above embodiments.

[0096] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0097] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a server, or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0098] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0101] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0103] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A verification method based on human skeleton, characterized in that: include: Verification source information is obtained, and a correct skeletal diagram and a corresponding interference skeletal diagram are determined based on the verification source information; wherein, when the verification source information is a verification source picture, a human body in the verification source picture is identified, and basic skeletal features of the human body are obtained, wherein the basic skeletal features include information of N skeletal key points and information of lines between the skeletal key points, where N is a preset integer; a correct skeletal diagram of the human body is established based on the basic skeletal features of the human body, and M interference skeletal diagrams corresponding to the correct skeletal diagram are determined, where M is a positive integer; the correct skeletal diagram of the human body and the M interference skeletal diagrams are randomly arranged and displayed, so that a visitor can perform verification based on the verification source picture; receiving first operation information sent by the visitor through a client, wherein the first operation information is used to determine a selected skeleton diagram selected by the visitor, wherein the selected skeleton diagram is included in the correct skeleton diagram and the corresponding interference skeleton diagram; The visitor is verified based on the selected skeleton diagram and the correct skeleton diagram.

2. The method according to claim 1, characterized in that After receiving the first operation information sent by the visitor through the client, the method further includes: If the selected skeleton diagram is consistent with the correct skeleton diagram, receiving second operation information from the visitor, wherein the second operation information is used to move the skeleton diagram to a first target position in the verification source image; If a first position deviation between the first target position and a corresponding position of the correct skeleton image in the verification source image is less than a preset value, it is determined that the preset condition is met.

3. The method according to claim 1, characterized in that The determining of M interfering skeleton graphs corresponding to the correct skeleton graph comprises: Randomly selecting n skeleton key points from the N skeleton key points, and performing offset transformation on the coordinates of the n skeleton key points to obtain n transformed coordinates; generating the interference skeleton map according to the n transformed coordinates; or, The M bone graphs are selected from a preset bone feature database as the interference bone graphs.

4. The method according to claim 3, characterized in that After obtaining the basic skeletal features of the human body, the method further includes: Based on the line information between the skeleton key points, T skeleton line segment graphs are generated, the endpoints of the T skeleton line segments are different, and the shapes of the endpoints of the skeleton line segment graphs are different.

5. The method according to claim 4, characterized in that The method further comprises: If the correct skeleton diagram is a partial skeleton diagram, then in the verification source image, the skeleton line corresponding to the partial skeleton diagram is replaced with the corresponding skeleton line segment, and the remaining skeleton line segments are displayed to prompt the visitor to move the n skeleton line segments to the corresponding positions in the verification source image; receiving third operation information sent by the visitor, wherein the third operation information is used to move each displayed skeleton line segment to each second target position in the verification source image; If a second position deviation between the second target position and the corresponding position of each displayed skeleton line segment in the verification source image is less than a preset value, it is determined that the preset condition is met.

6. The method according to claim 5, characterized in that In the verification source image, after replacing the skeleton lines corresponding to the partial skeleton diagram with corresponding skeleton line segments and displaying n skeleton line segments of the remaining skeleton line segments, the method further includes: Highlighting the skeleton region to be replaced in the verification source image, and prompting the visitor to select a skeleton line segment corresponding to the skeleton region to be replaced from the remaining skeleton line segments; receiving fourth operation information sent by the visitor, wherein the fourth operation information is used to determine a target skeleton line segment selected by the visitor; If the target skeleton line segment is inconsistent with the skeleton line segment corresponding to the to-be-replaced skeleton region, it is determined that the preset condition is not satisfied.

7. A calibration device, characterized in that: include: An acquisition unit is configured to acquire verification source information and determine a correct skeletal diagram and a corresponding interference skeletal diagram based on the verification source information; wherein, when the verification source information is a verification source image, the unit identifies a human body in the verification source image and acquires basic skeletal features of the human body, wherein the basic skeletal features include information of N skeletal key points and information of lines between the skeletal key points, where N is a preset integer; establish a correct skeletal diagram of the human body based on the basic skeletal features of the human body, and determine M interference skeletal diagrams corresponding to the correct skeletal diagram, where M is a positive integer; and randomly arrange and display the correct skeletal diagram of the human body and the M interference skeletal diagrams, so that a visitor can perform verification based on the verification source image; a transceiver unit, configured to receive first operation information sent by the visitor via a client, wherein the first operation information is used to determine a selected skeletal graph selected by the visitor, wherein the selected skeletal graph is included in the correct skeletal graph and the corresponding interference skeletal graph; A verification unit is used to verify the visitor based on the selected skeleton diagram and the correct skeleton diagram.

8. A computing device, characterized in that include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the steps of the human skeleton-based verification method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one executable instruction. When the executable instruction is executed on a computing device, the computing device executes the human skeleton-based verification method according to any one of claims 1 to 6.

Images