Image tracing method, device, equipment and storage medium

By embedding the steganographic information of the ring graphic component in the image traceability method and enhancing the processing, extracting corner point contour information, and combining the traceability mapping relationship, the problem of poor recognition effect of low-frequency ring contour in the existing technology is solved, and screenshots are realized Accurate traceability of images and precise positioning of leaked sources.

CN114359007BActive Publication Date: 2024-11-19SHANJIE INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111589759.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-23
Publication Date
2024-11-19
Estimated Expiration
2041-12-23

AI Technical Summary

Technical Problem

The existing image traceability method has poor recognition of low-frequency or image enhanced elliptical contours, which cannot effectively solve the traceability problem of sensitive files being screenshot and leaked when displayed at the terminal.

Method used

By embedding the steganographic information assembled by the ring graphic component in the image to be traced, preprocessing and image enhancement processing are performed, corner point contour information is extracted, ring contour information is filtered, and traceability information is determined in combination with the steganographic traceability mapping relationship. Achieve accurate positioning and traceability of the source of leakage.

Benefits of technology

It realizes accurate traceability, precise positioning and traceability of steganographic information of pre-embedded low-frequency ring contour features in screenshot images, and has anti-film, compression, and stretching capabilities. It is suitable for different scenarios such as office, web page, video images, etc. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114359007B_ABST
    Figure CN114359007B_ABST
Patent Text Reader

Abstract

The present application provides an image tracing method, device, equipment and storage medium, which relates to the field of information security technology. The method includes: obtaining an image to be traced; preprocessing the image to be traced to obtain a set of preprocessed intermediate images; performing image enhancement processing on each image in the intermediate image set to obtain an enhanced image set; extracting corner point contour information in each enhanced image in the enhanced image set to obtain a corner point image set containing corner point contour information; performing annular contour screening on each corner point image in the corner point image set to obtain an annular contour image set; obtaining a steganographic information set of the image to be traced based on the annular contour image set and the enhanced image set; determining the tracing information of the image to be traced based on the steganographic information set and the pre-established steganographic tracing mapping relationship. This scheme can realize the accurate tracing of the steganographic information of the low-frequency annular contour feature in the image to be traced, and thus realize the tracing of the source of the leak.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to an image tracing method, device, equipment and storage medium. Background Art

[0002] With the rapid development of Internet information technology, information security issues have become a social hotspot. For some sensitive files, various encryption modes are usually used to protect them. However, if sensitive files are leaked by screenshots when used on a terminal, it will be difficult to trace and locate the leaker, which will bring great security risks.

[0003] At present, most of the existing image tracing methods extract image contour features from the image to be traced, and obtain tracing information based on the image contour features, thereby tracing and locating the image leaker.

[0004] However, this tracing method based on ellipse feature detection has a good extraction effect on visually obvious ellipse contours, but has a poor recognition effect on low-frequency or image-enhanced ellipse contours. Therefore, it cannot effectively solve the tracing problem of sensitive files being leaked by screenshots when displayed on the terminal. Summary of the invention

[0005] The purpose of the present invention is to provide an image tracing method, device, equipment and storage medium to address the deficiencies in the above-mentioned prior art, so as to accurately trace the steganographic information of the low-frequency annular contour features pre-embedded in the image to be traced, and then accurately locate and trace the source of the leak based on the tracing information of the image to be traced.

[0006] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0007] In a first aspect, an embodiment of the present application provides an image tracing method, which is applied to a tracing server in a steganalysis tracing system, wherein the steganalysis tracing system includes a plurality of terminals and the tracing server, and each of the terminals is in communication connection with the tracing server;

[0008] The method comprises:

[0009] Acquire an image to be traced; wherein the image to be traced refers to an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in an original frame image displayed on the terminal;

[0010] Preprocessing the image to be traced to obtain a set of preprocessed intermediate images, wherein the set of intermediate images includes multiple images in multiple dimensions corresponding to the image to be traced;

[0011] Performing image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, wherein the enhanced image set includes a plurality of enhanced images;

[0012] Extracting corner point contour information from each enhanced image in the enhanced image set to obtain a corner point image set containing corner point contour information;

[0013] Performing annular contour screening on each corner point image in the corner point image set to obtain an annular contour image set;

[0014] Obtaining a steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set;

[0015] Based on the stego information set and a pre-established stego-tracing mapping relationship, the tracing information of the image to be traced is determined, wherein the stego-tracing mapping relationship includes: a corresponding relationship between each stego information and the tracing information, and the tracing information is used to indicate the identification information of the terminal that generated the image to be traced.

[0016] Optionally, performing annular contour screening on each corner point image in the corner point image set to obtain the annular contour image set includes:

[0017] Traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image;

[0018] Performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result;

[0019] According to the clustering result, a set of annular contours of the image to be traced is calculated; wherein the set of annular contour images includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between the annular contours.

[0020] Optionally, performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result includes:

[0021] Calculate the center point and the number of rows and columns of each circular contour in the target circular contour set;

[0022] The central coordinate point of each of the annular contours is used as a cluster center point, and each of the annular contours is clustered onto a two-dimensional plane grid lattice cluster center according to the number of contour rows and columns to obtain a clustering result.

[0023] Optionally, obtaining the steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set includes:

[0024] Determine the boundaries of each atomic layer in the image to be traced according to the positioning corner points of each atomic layer pre-embedded in the image to be traced, the preset arrangement rules of each atomic layer, and the annular contour image set;

[0025] Binarization is performed on each enhanced image in the enhanced image set to obtain a histogram pixel value distribution diagram of the image to be traced;

[0026] Determine each of the atomic layers and the steganographic information of each of the atomic layers in the image to be traced according to the histogram pixel value distribution diagram of the image to be traced and the boundaries of each of the atomic layers;

[0027] Based on the stego information of each of the atomic layers, a stego information set of the image to be traced is determined.

[0028] Optionally, the determining the tracing information of the image to be traced based on the stego information set and a pre-established stego tracing mapping relationship includes:

[0029] Each stego information in the stego information set is matched with the stego tracing mapping relationship, and if the match is successful, the tracing information of the image to be traced is obtained.

[0030] Optionally, preprocessing the to-be-traced images to obtain a set of preprocessed intermediate images includes:

[0031] Resizing the image to be traced to obtain an image of a target size after adjustment;

[0032] According to at least one preset brightness level, performing image brightness contrast processing on the target size image to obtain a processed brightness contrast image set;

[0033] Performing edge-preserving filtering on each image in the brightness contrast image set to obtain a filtered image set;

[0034] Performing channel difference processing on the target size image, the brightness contrast image set, and the filter image set respectively to obtain a sub-channel image set;

[0035] The target size image, the brightness contrast image set, the filtered image set, and the sub-channel image set are used as the intermediate image set.

[0036] Optionally, before performing annular contour screening on each corner point image in the corner point image set to obtain the annular contour image set, the method further comprises:

[0037] An image closing operation is performed on each image in the enhanced image set to obtain a processed closed image set.

[0038] In a second aspect, an embodiment of the present application further provides an image tracing device, which is applied to a tracing server in a steganalysis tracing system, wherein the steganalysis tracing system includes a plurality of terminals and the tracing server, and each of the terminals is in communication connection with the tracing server;

[0039] The device comprises:

[0040] An acquisition module, used for acquiring an image to be traced; wherein the image to be traced refers to an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in an original frame image displayed on the terminal;

[0041] a processing module, configured to preprocess the image to be traced to obtain a preprocessed intermediate image set, wherein the intermediate image set includes multiple images in multiple dimensions corresponding to the image to be traced; and perform image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, wherein the enhanced image set includes multiple enhanced images;

[0042] An extraction module, used for extracting corner point contour information from each enhanced image in the enhanced image set, to obtain a corner point image set containing corner point contour information;

[0043] A screening module, used for performing annular contour screening on each corner point image in the corner point image set to obtain annular contour image set;

[0044] The processing module is further used to obtain a steganographic information set of the image to be traced based on the annular contour image set and the enhanced image set;

[0045] A determination module is used to determine the traceability information of the image to be traced based on the stego information set and a pre-established stego-tracing mapping relationship, wherein the stego-tracing mapping relationship includes: a correspondence between each stego information and the traceability information, and the traceability information is used to indicate the identification information of the terminal that generated the image to be traced.

[0046] Optionally, the screening module is further used to:

[0047] Traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image;

[0048] Performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result;

[0049] According to the clustering result, a set of annular contours of the image to be traced is calculated; wherein the set of annular contour images includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between the annular contours.

[0050] Optionally, the screening module is further used to:

[0051] Calculate the center point and the number of rows and columns of each circular contour in the target circular contour set;

[0052] The central coordinate point of each of the annular contours is used as a cluster center point, and each of the annular contours is clustered onto a two-dimensional plane grid lattice cluster center according to the number of contour rows and columns to obtain a clustering result.

[0053] Optionally, the processing module is further used to:

[0054] Determine the boundaries of each atomic layer in the image to be traced according to the positioning corner points of each atomic layer pre-embedded in the image to be traced, the preset arrangement rules of each atomic layer, and the annular contour image set;

[0055] Binarization is performed on each enhanced image in the enhanced image set to obtain a histogram pixel value distribution diagram of the image to be traced;

[0056] Determine each of the atomic layers and the steganographic information of each of the atomic layers in the image to be traced according to the histogram pixel value distribution diagram of the image to be traced and the boundaries of each of the atomic layers;

[0057] Based on the stego information of each of the atomic layers, a stego information set of the image to be traced is determined.

[0058] Optionally, the determining module is further used to:

[0059] Each stego information in the stego information set is matched with the stego tracing mapping relationship, and if the match is successful, the tracing information of the image to be traced is obtained.

[0060] Optionally, the processing module is further used to:

[0061] Resizing the image to be traced to obtain an image of a target size after adjustment;

[0062] According to at least one preset brightness level, performing image brightness contrast processing on the target size image to obtain a processed brightness contrast image set;

[0063] Performing edge-preserving filtering on each image in the brightness contrast image set to obtain a filtered image set;

[0064] Performing channel difference processing on the target size image, the brightness contrast image set, and the filter image set respectively to obtain a sub-channel image set;

[0065] The target size image, the brightness contrast image set, the filtered image set, and the sub-channel image set are used as the intermediate image set.

[0066] Optionally, the processing module is further used to:

[0067] An image closing operation is performed on each image in the enhanced image set to obtain a processed closed image set.

[0068] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the image tracing method provided in the first aspect above are performed.

[0069] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the image tracing method provided in the first aspect above are executed.

[0070] The beneficial effects of this application are:

[0071] The embodiment of the present application provides an image tracing method, device, equipment and storage medium, the method comprising: obtaining an image to be traced; wherein the image to be traced refers to: an image obtained by embedding an atomic layer composed of annular graphic components and containing steganographic information in an original frame image displayed on a terminal; preprocessing the image to be traced to obtain a preprocessed intermediate image set, the intermediate image set including multiple images in multiple dimensions corresponding to the image to be traced; performing image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, the enhanced image set including multiple enhanced images; extracting Enhance the corner point contour information in each enhanced image in the image set to obtain a corner point image set containing the corner point contour information; perform ring contour screening on each corner point image in the corner point image set to obtain a ring contour image set; obtain a stego information set of the image to be traced based on the ring contour image set and the enhanced image set; determine the traceability information of the image to be traced based on the stego information set and a pre-established stego-tracing mapping relationship, wherein the stego-tracing mapping relationship includes: a correspondence between each stego information and the traceability information, and the traceability information is used to indicate the identification information of the terminal that generates the image to be traced. In this scheme, the image to be traced is first preprocessed to obtain a set of preprocessed intermediate images, and then each image in the intermediate image set is enhanced to reduce the interference of the text content in the image to be traced on the extraction of stego information; then, the corner contour information is extracted from the enhanced image obtained after enhancement, and the corner image set containing the corner contour information is subjected to circular contour screening to obtain a circular contour image set; and based on the circular contour image set and the enhanced image set, the stego information set of the screenshot image to be traced is obtained to achieve accurate tracing of the stego information of the low-frequency circular contour feature pre-embedded in the screenshot image; finally, each stego information in the stego information set is matched with the pre-established stego tracing mapping relationship to obtain the tracing information of the image to be traced, and then the source of the leak can be accurately located and traced according to the tracing information of the image to be traced. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0073] Figure 1 A schematic diagram of the architecture of a steganalysis tracing system provided in an embodiment of the present application;

[0074] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0075] Figure 3 A schematic diagram of a flow chart of an image tracing method provided in an embodiment of the present application;

[0076] Figure 4 A schematic diagram of a flow chart of another image tracing method provided in an embodiment of the present application;

[0077] Figure 5 A flowchart of another image tracing method provided in an embodiment of the present application;

[0078] Figure 6 A schematic diagram of a flow chart of another image tracing method provided in an embodiment of the present application;

[0079] Figure 7 A flowchart of another image tracing method provided in an embodiment of the present application;

[0080] Figure 8 A schematic diagram of the structure of an image tracing device provided in an embodiment of the present application.

[0081] Icon: 100-steganographic tracing system; 101-tracing server; 102-terminal. DETAILED DESCRIPTION

[0082] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0083] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0084] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0085] In order to enable those skilled in the art to use the contents of this application, the following implementation methods are provided in combination with specific application scenarios to trace the steganographic information in screenshot images. For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0086] The following methods, devices, electronic devices or computer-readable storage media of the embodiments of the present application can be applied to any scenario where it is necessary to trace the hidden information in the screenshot image. The embodiments of the present application are not limited to specific application scenarios. Any solution using an image tracing method, device, electronic device and readable storage medium provided by the embodiments of the present application is within the protection scope of the present application.

[0087] First of all, before explaining the technical solution provided by the present application in detail, a brief explanation of the relevant background involved in the present application is given.

[0088] With the rapid development of Internet information technology, information security issues have become a social hotspot. For some sensitive files, various encryption modes are usually used to protect them. However, if sensitive files are leaked by screenshots when used on a terminal, it will be difficult to trace and locate the leaker, which will bring great security risks.

[0089] Currently, the problem of tracing the origin of an atomic layer containing steganographic information pre-embedded in the image to be traced, which is assembled from ring-shaped graphic components, is mostly solved by extracting image contour features in the image to be traced, and obtaining tracing information based on the image contour features, thereby tracing and locating the image leaker.

[0090] However, this tracing method based on ellipse feature detection has a good extraction effect on visually obvious ellipse contours, but has a poor recognition effect on low-frequency or image-enhanced ellipse contours. Therefore, it cannot effectively solve the tracing problem of sensitive files being leaked by screenshots when displayed on the terminal.

[0091] In order to solve the technical problems existing in the above-mentioned prior art, the present application proposes an image tracing method, which is mainly for tracing the source of images of the type "taking advantage of the phenomenon that human eyes are insensitive to low-frequency signals, and integrating a steganographic layer composed of low-frequency ring graphic components into the original frame images displayed by each terminal. These images contain hidden sensitive information. When a user takes a screenshot of the original frame image displayed on the terminal he uses, a screenshot image is obtained." At this time, the image tracing method provided by the present application can be used to enhance the screenshot image to be traced, and extract corner contour information from the enhanced image obtained after the enhancement, and perform ring contour screening on the corner image set containing corner contour information to obtain a ring contour image set; then, based on the ring contour image set and the enhanced image set, a steganographic information set of the screenshot image to be traced is obtained; finally, each steganographic information in the steganographic information set is matched with a pre-established steganographic tracing mapping relationship to obtain the tracing information of the screenshot image to be traced, so as to achieve accurate tracing of the steganographic information of the low-frequency ring contour feature pre-embedded in the screenshot image, and then, based on the tracing information of the screenshot image, the source of the leak can be accurately located and traced.

[0092] It should be understood that the image tracing method provided in the present application also supports taking screenshots of part of the original frame image displayed on the terminal to obtain screenshot images for tracing, and this method has certain advantages such as anti-fouling, compression, stretching capabilities, and high robustness; this method is also suitable for general imaging devices on the market, and can effectively trace imaging screenshots of different office scenes such as office, web pages, video images, etc., and has a wide range of application scenarios.

[0093] The following is a brief description of the architecture of the steganographic tracing system provided by this application.

[0094] Reference Figure 1 As shown, the image tracing method provided by this application is applied to Figure 1 The tracing server 101 in the steganalysis tracing system 100 is shown.

[0095] It should be noted that the steganalysis tracing system 100 can be deployed as a separate system or integrated into a third-party data monitoring system.

[0096] The steganographic tracing system 100 includes one or more of a plurality of terminals 102, a tracing server 101, and a network 103, and each terminal 102 is connected to the tracing server 101 through the network 103. Figure 1 As shown, the tracing server 101 and the terminal 102 are independently deployed and run in different electronic devices. For example, each terminal 102 can be a computer, a mobile Internet device, a tablet, a mobile phone terminal, and other devices with operation and display functions. The tracing server 101 is a processing device deployed in the server and has a data processing function.

[0097] When a leak occurs (a screenshot image is maliciously spread), the screenshot image can be traced online or offline. Specifically, the tracing server 101 obtains the image to be traced, and executes the image tracing method to obtain the traceability information of the image to be traced, and determines the identity information of the leaker based on the traceability information of the image to be traced, thereby achieving accurate positioning and tracing of the source of the leak.

[0098] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application; the electronic device may be the above Figure 1 The processing devices such as the tracing server 101 in the embodiment are used to implement the image tracing method provided by the present application. Figure 2 As shown, the electronic device includes: a processor 201 and a memory 202 .

[0099] The processor 201 and the memory 202 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, the electrical connection can be achieved through one or more communication buses or signal lines.

[0100] The processor 201 may be an integrated circuit chip having the ability to process signals. The processor 201 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. The methods, steps, and logic diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor.

[0101] The memory 202 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0102] Understandably, Figure 2 The structure described is for illustration only. The electronic device may also include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations are shown. Figure 2Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0103] The memory 202 is used to store programs, and the processor 201 calls the programs stored in the memory 202 to execute the image tracing method provided in the following embodiment.

[0104] The image tracing method provided by the present application and the corresponding beneficial effects will be described below through multiple embodiments.

[0105] Figure 3 The flowchart of an image tracing method provided in the embodiment of the present application is shown in FIG. 1 . Optionally, the execution subject of the method can be a server, computer or other electronic device with data processing function. It should be understood that in other embodiments, the order of some steps in the image tracing method can be interchanged according to actual needs, or some steps can be omitted or deleted. Figure 2 As shown, the method includes:

[0106] S301, obtaining the image to be traced.

[0107] Among them, the image to be traced refers to: an image obtained by embedding an atomic layer containing stego information assembled by a ring graphic component in the original frame image displayed on the terminal. Exemplarily, a client of a stego tracing system is pre-installed on terminal A. The stego tracing system generates the stego information of terminal A according to the identification information of terminal A and the pre-established stego tracing mapping relationship, and encodes the stego information to obtain a coding string; then, the atomic layer is assembled according to the coding string, and multiple atomic layers are spliced ​​into a stego layer; finally, the spliced ​​stego layer is superimposed on the original frame image displayed on terminal A. When the user takes a screenshot of the original frame image displayed on terminal A, the screenshot image contains the pre-embedded atomic layer containing stego information assembled by a ring graphic component.

[0108] It should be understood that the image tracing method provided by the present application is mainly aimed at tracing the source of images of the type "taking advantage of the phenomenon that the human eye is insensitive to low-frequency signals, and integrating the steganographic layer composed of low-frequency ring graphic components into the original frame images displayed by each terminal. These images contain hidden sensitive information. When a user takes a screenshot of the original frame image displayed on the terminal he uses, a screenshot image is obtained."

[0109] The following will describe how to perform encrypted information steganography on the original frame image displayed on each terminal according to the identification information of each terminal to obtain the steganographic image to be traced.

[0110] The first step is that the steganographic tracing system issues a steganographic mark.

[0111] For example, the identification information of each terminal includes a physical address (Media Access Control Address, MAC for short), an Internet Protocol version 4 (IPV4 for short), a user name, and the like.

[0112] For example, the identification information of terminal A is: "MAC: 00-C1-40-82-0A-3A; IPV4: 168.18.10.200; USER: Wang", and the identification information string is mapped into a unique hexadecimal string in the database, such as "1F2F3". Then, the string "1F2F3" is used as the steganographic mark of terminal A.

[0113] The second step is to perform CRC and BCH encoding on the steganographic mark to obtain the encoded string.

[0114] Specifically, the steganographic mark of terminal A is converted into a binary bit string, and the binary bit string is sequentially subjected to CRC checksum coding and BCH error correction coding to improve the accuracy of subsequent image tracing.

[0115] Step 3: Assemble the atomic layer according to the coding string.

[0116] In this embodiment, a ring graphic component is mainly used to represent binary 0 or 1. The ring graphic component utilizes the phenomenon that human eyes are insensitive to differences in adjacent gray values, and is formed by merging four groups of ellipses with the same center position, different sizes, and different gray values.

[0117] According to the encoded binary bit string, 64 groups of ring graphic components are used to assemble an atomic layer containing complete steganographic information. The lower left corner and upper right corner of the atomic layer are positioning feature points, which are used to locate the boundaries of each atomic layer in the image to be traced.

[0118] Step 4: Combine multiple atomic layers into a steganographic layer.

[0119] Specifically, for example, a multi-copy mechanism is used to splice six atomic layers into one imaged steganographic layer.

[0120] Step 5: Overlay the spliced ​​steganographic layer onto the original frame image displayed by each terminal.

[0121] Specifically, the steganographic layer is fused to the original frame image displayed by each terminal, and imaging is performed on the display screen of each terminal.

[0122] Since the steganographic layer is a low-frequency signal, it has little interference with the original imaging content and provides a good user visual experience.

[0123] S302 , preprocessing the image to be traced to obtain a set of preprocessed intermediate images, where the set of intermediate images includes multiple images in multiple dimensions corresponding to the image to be traced.

[0124] In the present application, the preprocessing of the image to be traced may include at least one of the following: image size adjustment, image brightness contrast adjustment, image binarization, image edge-preserving filtering, or image channel difference, image channel difference, etc., to obtain multiple images in multiple dimensions corresponding to the image to be traced.

[0125] S303: Perform image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, where the enhanced image set includes multiple enhanced images.

[0126] In this embodiment, in order to amplify and enhance the low-frequency ring component signals in multiple images in multiple dimensions corresponding to the image to be traced, a local contrast enhancement algorithm can be used to perform image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, and the enhanced image set after enhancement is recorded as {enhance_img}.

[0127] S304: extracting corner point contour information from each enhanced image in the enhanced image set, and obtaining a corner point image set containing corner point contour information.

[0128] The corner point image set includes at least one corner point image, and each corner point image includes a plurality of corner point contour information extracted from the enhanced image.

[0129] In this example, corner contour detection technology can be used. For example, the Canny operator can be used to perform corner contour detection on each enhanced image {enhance_img} in the enhanced image set to obtain multiple corner images containing corner contour information, and based on the multiple corner images containing corner contour information, a corner image set is obtained, and the corner image set is recorded as {corner_img}.

[0130] S305 , performing annular contour screening on each corner point image in the corner point image set to obtain an annular contour image set.

[0131] In order to ensure the accuracy of the steganographic information set of the image to be traced, the present application proposes that it is also necessary to perform ring contour screening on each corner point image in the corner point image set {corner_img}, retain all corner point contour set information in the corner point image set {corner_img} that meet the screening conditions, and the ring contour image set obtained after screening is recorded as {ring_corner_img}, and filter out invalid ring contour data in the corner point image set {corner_img}.

[0132] S306 , obtaining a steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set.

[0133] In this embodiment, the "image histogram pixel value distribution" of the image to be traced can be obtained according to each enhanced image in the enhanced image set {enhance_img}; then, the boundaries of each atomic layer in the image to be traced can be determined according to the ring contour image set {ring_corner_img}; finally, the atomic layers of the image to be traced are determined by combining the "image histogram pixel value distribution" and the "boundaries of each atomic layer in the image to be traced", and layer processing is performed for each atomic layer to obtain the steganographic information corresponding to each atomic layer. That is, the steganographic information set of the image to be traced is obtained, and the steganographic information set is recorded as {decode_bin_id}.

[0134] S307: Determine the tracing information of the image to be traced based on the stego information set and the pre-established stego tracing mapping relationship.

[0135] The steganalysis traceability mapping relationship includes: the correspondence between each steganalysis information and the traceability information, and the traceability information is used to indicate the identification information of the terminal that generates the image to be traced.

[0136] Specifically, the "hidden information set {decode_bin_id}" of the image to be traced is matched with the steganographic tracing mapping relationship pre-established in the database to obtain the tracing information of the image to be traced, so as to accurately trace the steganographic information of the low-frequency ring contour feature pre-embedded in the screenshot image, and then the source of the leak can be accurately located and traced based on the tracing information of the screenshot image.

[0137] In summary, an embodiment of the present application provides an image tracing method, the method comprising: obtaining an image to be traced; wherein the image to be traced refers to: an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in an original frame image displayed on a terminal; preprocessing the image to be traced to obtain a preprocessed intermediate image set, the intermediate image set including multiple images in multiple dimensions corresponding to the image to be traced; performing image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, the enhanced image set including multiple enhanced images; extracting the enhanced image corner point contour information in each enhanced image in the image set is obtained to obtain a corner point image set containing the corner point contour information; a ring contour screening is performed on each corner point image in the corner point image set to obtain a ring contour image set; a stego information set of the image to be traced is obtained according to the ring contour image set and the enhanced image set; based on the stego information set and a pre-established stego tracing mapping relationship, the tracing information of the image to be traced is determined, wherein the stego tracing mapping relationship includes: a corresponding relationship between each stego information and the tracing information, and the tracing information is used to indicate the identification information of the terminal that generates the image to be traced. In this scheme, the image to be traced is first preprocessed to obtain a set of preprocessed intermediate images, and then each image in the intermediate image set is enhanced to reduce the interference of the text content in the image to be traced on the extraction of stego information; then, the corner contour information is extracted from the enhanced image obtained after enhancement, and the corner image set containing the corner contour information is subjected to circular contour screening to obtain a circular contour image set; and based on the circular contour image set and the enhanced image set, the stego information set of the screenshot image to be traced is obtained to achieve accurate tracing of the stego information of the low-frequency circular contour feature pre-embedded in the screenshot image; finally, each stego information in the stego information set is matched with the pre-established stego tracing mapping relationship to obtain the tracing information of the image to be traced, and then the source of the leak can be accurately located and traced according to the tracing information of the image to be traced.

[0138] The following embodiment will explain in detail how to perform annular contour screening on each corner point image in a corner point image set to obtain annular contour image set.

[0139] Optionally, refer to Figure 4 As shown, the above step S305: performing annular contour screening on each corner point image in the corner point image set to obtain annular contour image set includes:

[0140] S401 , traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image.

[0141] In this embodiment, all detected corner point contour information {i_corner_img} in each corner point image is traversed, the convex hull corner point contour in the corner point contour information {i_corner_img} is retained, and the corner point contours of small areas are filtered to obtain a target ring contour set of each corner point image after filtering. The target ring contour set is recorded as {i_ring_corner}.

[0142] S402 , performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result.

[0143] The following embodiment will explain how to perform image contour clustering on each annular contour in the target annular contour set, and this process will be specifically introduced.

[0144] Optionally, refer to Figure 5 As shown, the above S402: performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result includes:

[0145] S501, calculating the center coordinate point and the number of rows and columns of each circular contour in the target circular contour set.

[0146] S502 , taking the central coordinate point of each annular contour as a cluster center point, clustering each annular contour onto a two-dimensional plane grid point array cluster center according to the number of contour rows and columns, and obtaining a clustering result.

[0147] In this example, the center point of each ring contour in the target ring contour set {i_ring_corner} is calculated, and the number of contour rows and columns of each corner point image is counted; then, the contour center point is used as the cluster center point, and all ring contours are clustered to the cluster center of the two-dimensional plane grid lattice. The clustering result is recorded as {i_ring_corner_w_h}.

[0148] S403: Calculate and obtain a set of annular contours of the image to be traced based on the clustering result.

[0149] The annular contour image set includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between the annular contours.

[0150] Based on the above example, according to the clustering result {i_ring_corner_w_h}, the ring contour clustering information of all corner point images is counted, and invalid ring contours are eliminated. Finally, the position of each ring contour in the image to be traced and the minimum horizontal and vertical distances between each ring contour are calculated, and the image set where each ring contour is located is recorded as {ring_corner_img}.

[0151] The following embodiments will explain in detail how to obtain the steganographic information set of the image to be traced based on the annular contour image set and the enhanced image set.

[0152] Optionally, refer to Figure 6 As shown, the above step S306: obtaining the steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set, includes:

[0153] S601, determining the boundaries of each atomic layer in the image to be traced according to the positioning corner points of each atomic layer pre-embedded in the image to be traced, the preset arrangement rules of each atomic layer, and the annular contour image set.

[0154] Exemplarily, for example, the lower left corner and the upper right corner of each atomic layer can be used as positioning feature points, so that the boundaries of each atomic layer in the image to be traced can be located according to the positioning corner points of each atomic layer.

[0155] The preset arrangement rules of each atomic layer are used to represent the arrangement method according to which the atomic layers are spliced ​​to form a steganographic layer.

[0156] In this embodiment, based on the positioning corner points of each atomic layer pre-embedded in the image to be traced, and the preset arrangement rules of each atomic layer, and using a boundary positioning algorithm, the boundaries of each atomic layer in the tracing screenshot are calculated according to the ring contour data in the ring contour image set {ring_corner_img}.

[0157] S602: Binarize each enhanced image in the enhanced image set to obtain a histogram pixel value distribution diagram of the image to be traced.

[0158] In this embodiment, each enhanced image in the enhanced image set {enhance_img} is adaptively binarized to obtain a processed binary image, and the number of each pixel value in the binary image is counted. According to the number of each pixel value in the binary image, a histogram pixel value distribution diagram of the image to be traced is drawn.

[0159] S603, determining each atomic layer and the steganographic information of each atomic layer in the image to be traced according to the histogram pixel value distribution diagram of the image to be traced and the boundaries of each atomic layer.

[0160] In this embodiment, each atomic layer in the image to be traced is determined based on the histogram pixel value distribution diagram of the image to be traced and the boundaries of each atomic layer; then, the steganographic information in each atomic layer is traced from each atomic layer using the BCH error correction and CRC check algorithm.

[0161] S604: Based on the stego information of each atomic layer, determine the stego information set of the image to be traced.

[0162] On the basis of the above embodiment, the stego information of each atomic layer is used as the stego information set of the image to be traced, and the stego information set is recorded as {decode_bin_id}.

[0163] The following embodiments will explain in detail how to determine the traceability information of the image to be traced based on the stego information set and the pre-established stego traceability mapping relationship.

[0164] Optionally, the above step S307: determining the traceability information of the image to be traced based on the stego information set and the pre-established stego traceability mapping relationship includes:

[0165] Each stego information in the stego information set is matched with the stego tracing mapping relationship. If the match is successful, the tracing information of the image to be traced is obtained.

[0166] Exemplarily, for example, if each steganographic information in the steganographic information set {decode_bin_id} is converted into a hexadecimal steganographic information string of "1ABF7", the steganographic information string "1ABF7" is matched with the steganalysis traceability mapping relationship. If the match is successful, the traceability information obtained is "MAC: 00-C1-40-82-0A-1A; IPV4: 168.10.10.155; USER: Tong".

[0167] For another example, if each steganographic information in the steganographic information set {decode_bin_id} is converted into a hexadecimal steganographic information string of "1F2F3", the steganographic information string "1F2F3" is matched with the steganalysis traceability mapping relationship. If the match is successful, the traceability information obtained is "MAC: 00-C1-40-82-0A-3A; IPV4: 168.18.10.200; USER: Wang".

[0168] Therefore, the source of the leak can be accurately located and traced based on the traceability information corresponding to each stego information in the stego information set.

[0169] In another achievable manner, if the matching fails, then the tracing of the image to be traced fails, or there is no steganographic information in the image to be traced.

[0170] The following embodiments will explain in detail how to preprocess the traceable images to obtain a set of preprocessed intermediate images.

[0171] Optionally, refer to Figure 7As shown, in the above step S303, the image to be traced is preprocessed to obtain a set of preprocessed intermediate images, including:

[0172] S701 , resizing the image to be traced to obtain an image of a target size after resizing.

[0173] In this embodiment, considering that the image to be traced is obtained by taking a screenshot of a part of the original frame image displayed on the terminal, the present application proposes that the width and height of the "image to be traced" can be rounded up to integer multiples of 2 to adjust the image size, and obtain an adjusted target size image, which is recorded as resize_img.

[0174] S702: Perform brightness contrast processing on the target size image according to at least one preset brightness level to obtain a processed brightness contrast image set.

[0175] In this embodiment, considering the differences in different office scenes, the present application proposes to adjust the image brightness contrast of the target size image resize_img to three levels of bright, dark, and moderate, so as to enhance the background difference of the "image to be traced", and the adjusted brightness contrast image set is recorded as {brightness_contrast_img}.

[0176] S703 , performing edge-preserving filtering on each image in the brightness contrast image set to obtain a filtered image set.

[0177] In this embodiment, a side window filter (Side Window Filtering, SWF for short) may be used to perform edge-preserving filtering on each image in the brightness contrast image set {brightness_contrast_img}, and the obtained filtered image set is recorded as {filter_img}.

[0178] It should be understood that the side window filter has a strong edge preservation capability and can suppress image noise while preserving image edge contour features.

[0179] S704 , performing channel difference processing on the target size image, the brightness contrast image set, and the filter image set respectively to obtain a sub-channel image set.

[0180] In this embodiment, considering that the image to be traced is a RGB three-channel image, it is proposed that the target size image resize_img, the brightness contrast image set {brightness_contrast_img}, and the filter image set {filter_img} can be respectively subjected to channel difference processing to reduce the interference of the main text content in the image to be traced on the extraction of "low-frequency stego information". The obtained sub-channel image set is recorded as {channel_sub_img}.

[0181] S705 , taking the target size image, the brightness contrast image set, the filter image set, and the sub-channel image set as an intermediate image set.

[0182] Based on the above embodiment, the target size image resize_img, the brightness contrast image set {brightness_contrast_img}, the filter image set {filter_img}, and the sub-channel image set {channel_sub_img} can be used as the intermediate image set.

[0183] Optionally, before the above step S305: performing annular contour screening on each corner point image in the corner point image set to obtain the annular contour image set, the method further includes:

[0184] An image closing operation is performed on each image in the enhanced image set to obtain a processed closed image set.

[0185] In this embodiment, since the text content in the image to be traced is also enhanced while the image enhancement processing is performed on each image in the intermediate image set, it is necessary to reduce the interference of the text content in the image to be traced on the extraction of stego information. Therefore, this application proposes that an image closing operation is also required for each enhanced image in the enhanced image set {enhance_img}, and the processed closed image set is recorded as {close_img}.

[0186] Based on the same inventive concept, an image tracing device corresponding to the image tracing method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned image tracing method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0187] Alternatively, if Figure 8 As shown, the embodiment of the present application also provides an image tracing device, which is applied to a tracing server in a steganographic tracing system. The steganographic tracing system includes multiple terminals and a tracing server, and each terminal is connected to the tracing server in communication; the device includes:

[0188] The acquisition module 801 is used to acquire the image to be traced; wherein the image to be traced refers to: an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in the original frame image displayed on the terminal;

[0189] The processing module 802 is used to preprocess the image to be traced to obtain a preprocessed intermediate image set, wherein the intermediate image set includes multiple images in multiple dimensions corresponding to the image to be traced; perform image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, wherein the enhanced image set includes multiple enhanced images;

[0190] An extraction module 803 is used to extract the corner point contour information in each enhanced image in the enhanced image set to obtain a corner point image set containing the corner point contour information;

[0191] A screening module 804 is used to perform annular contour screening on each corner point image in the corner point image set to obtain annular contour image set;

[0192] The processing module 802 is further used to obtain a steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set;

[0193] The determination module 805 is used to determine the traceability information of the image to be traced based on the stego information set and the pre-established stego traceability mapping relationship, wherein the stego traceability mapping relationship includes: the correspondence between each stego information and the traceability information, and the traceability information is used to indicate the identification information of the terminal that generates the image to be traced.

[0194] Optionally, the screening module 804 is further configured to:

[0195] Traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image;

[0196] Perform image contour clustering on each circular contour in the target circular contour set to obtain a clustering result;

[0197] According to the clustering results, a set of annular contours of the image to be traced is calculated; wherein the set of annular contour images includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between each annular contour.

[0198] Optionally, the screening module 804 is further configured to:

[0199] Calculate the center point and the number of rows and columns of each circular contour in the target circular contour set;

[0200] The central coordinate point of each circular contour is used as the cluster center point, and each circular contour is clustered to the cluster center of the two-dimensional plane grid lattice according to the number of contour rows and columns to obtain the clustering result.

[0201] Optionally, the processing module 802 is further configured to:

[0202] According to the positioning corner points of each atomic layer pre-embedded in the image to be traced, the preset arrangement rules of each atomic layer, and the annular contour image set, the boundaries of each atomic layer in the image to be traced are determined;

[0203] Binarization is performed on each enhanced image in the enhanced image set to obtain a histogram pixel value distribution diagram of the image to be traced;

[0204] Determine each atomic layer and the steganographic information of each atomic layer in the image to be traced according to the histogram pixel value distribution diagram of the image to be traced and the boundaries of each atomic layer;

[0205] Based on the steganalysis information of each atomic layer, the steganalysis information set of the image to be traced is determined.

[0206] Optionally, the determination module 805 is further configured to:

[0207] Each stego information in the stego information set is matched with the stego tracing mapping relationship. If the match is successful, the tracing information of the image to be traced is obtained.

[0208] Optionally, the processing module 802 is further configured to:

[0209] Adjust the image size of the image to be traced to obtain an image of the adjusted target size;

[0210] According to at least one preset brightness level, performing image brightness contrast processing on the target size image to obtain a processed brightness contrast image set;

[0211] Performing edge-preserving filtering on each image in the brightness contrast image set to obtain a filtered image set;

[0212] Perform channel difference processing on the target size image, the brightness contrast image set, and the filter image set respectively to obtain a sub-channel image set;

[0213] The target size image, the brightness contrast image set, the filtered image set, and the sub-channel image set are taken as the intermediate image set.

[0214] Optionally, the processing module 802 is further configured to:

[0215] An image closing operation is performed on each image in the enhanced image set to obtain a processed closed image set.

[0216] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0217] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0218] Optionally, the present invention also provides a program product, such as a computer-readable storage medium, comprising a program, which is used to execute the above method embodiment when executed by a processor.

[0219] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0220] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0221] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0222] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: Processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

Claims

1. An image tracing method, characterized in that: A tracing server used in a steganalysis tracing system, wherein the steganalysis tracing system comprises a plurality of terminals and the tracing server, and each of the terminals is in communication connection with the tracing server; The method comprises: Acquire an image to be traced; wherein the image to be traced refers to an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in an original frame image displayed on the terminal; Preprocessing the image to be traced to obtain a set of preprocessed intermediate images, wherein the set of intermediate images includes multiple images in multiple dimensions corresponding to the image to be traced; Performing image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, wherein the enhanced image set includes a plurality of enhanced images; Extracting corner point contour information from each enhanced image in the enhanced image set to obtain a corner point image set containing corner point contour information; Performing annular contour screening on each corner point image in the corner point image set to obtain an annular contour image set; Obtaining a steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set; Based on the stego information set and the pre-established stego-tracing mapping relationship, the tracing information of the image to be traced is determined, wherein the stego-tracing mapping relationship includes: a correspondence between each stego information and the tracing information, and the tracing information is used to indicate the identification information of the terminal that generates the image to be traced; The step of performing annular contour screening on each corner point image in the corner point image set to obtain annular contour image set includes: Traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image; Performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result; According to the clustering result, a set of annular contours of the image to be traced is calculated; wherein the set of annular contour images includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between the annular contours.

2. The method according to claim 1, characterized in that The performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result includes: Calculate the center point and the number of rows and columns of each circular contour in the target circular contour set; The central coordinate point of each of the annular contours is used as a cluster center point, and each of the annular contours is clustered onto a two-dimensional plane grid lattice cluster center according to the number of contour rows and columns to obtain a clustering result.

3. The method according to claim 1, characterized in that The step of obtaining the steganographic information set of the image to be traced according to the annular contour image set and the enhanced image set includes: Determine the boundaries of each atomic layer in the image to be traced according to the positioning corner points of each atomic layer pre-embedded in the image to be traced, the preset arrangement rules of each atomic layer, and the annular contour image set; Binarization is performed on each enhanced image in the enhanced image set to obtain a histogram pixel value distribution diagram of the image to be traced; Determine each of the atomic layers and the steganographic information of each of the atomic layers in the image to be traced according to the histogram pixel value distribution diagram of the image to be traced and the boundaries of each of the atomic layers; Based on the stego information of each of the atomic layers, a stego information set of the image to be traced is determined.

4. The method according to claim 1, characterized in that: The determining the traceability information of the image to be traced based on the stego information set and the pre-established stego traceability mapping relationship includes: Each stego information in the stego information set is matched with the stego tracing mapping relationship, and if the match is successful, the tracing information of the image to be traced is obtained.

5. The method according to any one of claims 1 to 4, characterized in that: The preprocessing of the to-be-traced image to obtain a set of preprocessed intermediate images includes: Resizing the image to be traced to obtain an image of a target size after adjustment; According to at least one preset brightness level, performing image brightness contrast processing on the target size image to obtain a processed brightness contrast image set; Performing edge-preserving filtering on each image in the brightness contrast image set to obtain a filtered image set; Performing channel difference processing on the target size image, the brightness contrast image set, and the filter image set respectively to obtain a sub-channel image set; The target size image, the brightness contrast image set, the filtered image set, and the sub-channel image set are used as the intermediate image set.

6. The method according to claim 5, characterized in that Before performing annular contour screening on each corner point image in the corner point image set to obtain the annular contour image set, the method further comprises: An image closing operation is performed on each image in the enhanced image set to obtain a processed closed image set.

7. An image tracing device, characterized in that: A tracing server used in a steganalysis tracing system, wherein the steganalysis tracing system comprises a plurality of terminals and the tracing server, and each of the terminals is in communication connection with the tracing server; The device comprises: An acquisition module, used for acquiring an image to be traced; wherein the image to be traced refers to an image obtained by embedding an atomic layer containing steganographic information assembled by annular graphic components in an original frame image displayed on the terminal; a processing module, configured to preprocess the image to be traced to obtain a preprocessed intermediate image set, wherein the intermediate image set includes multiple images in multiple dimensions corresponding to the image to be traced; and perform image enhancement processing on each image in the intermediate image set to obtain an enhanced image set, wherein the enhanced image set includes multiple enhanced images; An extraction module, used for extracting corner point contour information from each enhanced image in the enhanced image set, to obtain a corner point image set containing corner point contour information; A screening module, used for performing annular contour screening on each corner point image in the corner point image set to obtain annular contour image set; The processing module is further used to obtain a steganographic information set of the image to be traced based on the annular contour image set and the enhanced image set; A determination module, configured to determine the traceability information of the image to be traced based on the stego information set and a pre-established stego-tracing mapping relationship, wherein the stego-tracing mapping relationship includes: a correspondence between each stego information and the traceability information, and the traceability information is used to indicate identification information of a terminal that generates the image to be traced; The screening module is specifically used for: Traversing the corner point contours of each corner point image in the corner point image set, removing the interfering corner point contours in each corner point image, and obtaining a target annular contour set of each corner point image; Performing image contour clustering on each annular contour in the target annular contour set to obtain a clustering result; According to the clustering result, a set of annular contours of the image to be traced is calculated; wherein the set of annular contour images includes information of at least one annular contour image, and the information of each annular contour image includes: the position of the annular contour, and the horizontal and vertical distances between the annular contours.

8. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of any method as claimed in claims 1-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.