CN111476273A - Image processing method and device - Google Patents

Abstract

The present disclosure provides an image processing method and apparatus, relating to the technical field of computer images, wherein the method comprises: acquiring a rendering instruction, wherein the rendering instruction is generated according to an operation message of terminal equipment; rendering according to the rendering instruction to generate an image frame to be processed; identifying the type of the image frame to be processed, wherein the type of the image frame to be processed comprises a variable image frame and a constant image frame; filtering the image frame to be processed based on the type of the image frame to be processed to obtain a target image frame; and sending the target image frame to the terminal equipment. The method and the device can realize that the user cannot watch the sensitive words or the sensitive images on the terminal equipment.

Description

Image processing method and device

technical field

The present disclosure relates to the field of computer image technology, and in particular, to an image processing method and apparatus.

Background technique

With the rapid development of cloud virtualization technology, enterprises have further increased demand for virtual desktop cloud systems. The virtual desktop cloud system includes a cloud server and multiple user terminals (R terminals), and pictures are transmitted between the cloud server and the R terminal. Install systems and applications on the cloud server, and the cloud server completes almost all processing tasks, while the R terminal is a display with coding function. The cloud server generates multiple virtual machines (Virtual machines, VMs), one VM corresponds to one R terminal, and the user operates the VM through the R terminal. Because the user terminal in the virtual desktop cloud system does not obtain the data information itself, such as the original code, and does not have the storage function, therefore, even if the user terminal is attacked or stolen, important data will not be lost, and the security is high.

In the scenario where the virtual desktop cloud system is applied to corporate office, how to manage and restrict employees' office behavior is a problem to be solved.

SUMMARY OF THE INVENTION

Embodiments of the present disclosure provide an image processing method and apparatus, and the present disclosure can realize that a user cannot view sensitive words or sensitive images on a terminal device. The technical solution is as follows:

According to a first aspect of the embodiments of the present disclosure, there is provided an image processing method, which is applied to an image processing apparatus, and the method includes:

Obtaining a rendering instruction, the rendering instruction is generated according to the operation message of the terminal device;

Rendering according to the rendering instruction to generate a to-be-processed image frame;

Perform filtering processing on the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame;

Send the target image frame to the terminal device.

In one embodiment, filtering the to-be-processed image frame based on the type of the to-be-processed image frame to obtain the target image frame includes:

Identifying the type of the image frame to be processed, the type of the image frame to be processed includes a changing image frame and an invariant image frame;

If it is a changing image frame, the changing image frame is used as a sample image frame, and whether the sample image frame is a sensitive image is judged according to a preset image recognition algorithm;

If it is a sensitive image frame, replace the changed image frame with a preset image frame.

In one embodiment, the method further includes:

If it is a constant image frame, record the constant image frame, and determine the type of the next image frame, until a changed image frame is detected;

In every M frames of invariant image frames, select a sample image frame, and determine whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

If it is a sensitive image, replace the M frames of invariant image frames with preset image frames.

In one embodiment, the image frame to be processed includes at least one macroblock, and identifying the type of the image frame to be processed includes:

Judging whether the macroblock in the to-be-processed image frame is exactly the same as the pixel point of the macroblock at the corresponding position in the previous image frame;

If they are identical, then identify the to-be-processed image frame as a constant macroblock, if not, identify the to-be-processed image frame as a changed macroblock;

Count the number of unchanged macroblocks, and if the number of unchanged macroblocks is not greater than a preset threshold, then determine that the image frame to be processed is an unchanged image frame; if the number of unchanged macroblocks is less than the predetermined threshold If the threshold is set, it is determined that the image frame to be processed is a changed image frame.

In one embodiment, before identifying the type of the image frame to be processed, the method further includes:

It is determined that the to-be-processed image frame contains video macroblocks.

In one embodiment, judging whether the image frame to be processed is a sensitive image according to a preset image recognition algorithm includes:

Extracting keywords/feature values in the sample image frame, and comparing the extracted keywords/feature values with preset sensitive keywords/sensitive feature values;

If the keyword/feature value of the sample image frame contains a preset sensitive keyword/sensitive feature value, the sample image frame is determined to be a sensitive image.

In one embodiment, the rendering instruction is that the server receives at least one operation message sent by a terminal device, allocates a virtual machine corresponding to the terminal device according to the account information, and sequentially parses the at least one operation message through the virtual machine, Generated according to the parsing result, the at least one operation message includes account information.

In one embodiment, the method further includes:

According to the account information, the sensitive images corresponding to each account information are counted.

According to a second aspect of the embodiments of the present disclosure, there is provided an image processing apparatus, the apparatus comprising:

an acquisition module, used for acquiring rendering instructions, the rendering instructions are generated according to the operation message of the terminal device;

a rendering module, configured to perform rendering according to the rendering instruction, and generate a to-be-processed image frame;

an identification module for identifying the type of the image frame to be processed, and the type of the image frame to be processed includes a changing image frame and an invariant image frame;

a processing module, configured to filter the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame;

A sending module, configured to send the target image frame to the terminal device.

In one embodiment, the processing module includes:

a judging sub-module, configured to use the changed image frame as a sample image frame if it is a changing image frame, and judge whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

The first replacement submodule is configured to replace the changed image frame with a preset image frame.

In one embodiment, the processing module includes:

a recording submodule, for recording the invariant image frame if it is an invariant image frame, and determining the type of the next image frame, until the changed image frame is detected;

A selection sub-module for selecting sample image frames in every M frames of invariant image frames, and judging whether the sample image frames are sensitive images according to a preset image recognition algorithm;

The second replacement sub-module is configured to replace the M frames of unchanged image frames with preset image frames if it is a sensitive image.

In one embodiment, the image frame to be processed includes macroblocks, and the identification module includes:

Judging submodule, for judging whether the macroblock in the image frame to be processed is exactly the same as the pixel point of the macroblock at the corresponding position in the previous image frame;

an identification submodule, used for identifying the to-be-processed image frame as an invariant macroblock if it is identical, and identifying the to-be-processed image frame as a changing macroblock if not identical;

Statistics sub-module, used to count the number of unchanged macroblocks, if the number of unchanged macroblocks is not greater than a preset threshold, then determine that the image frame to be processed is an unchanged image frame; If the number of macroblocks is less than the preset threshold, it is determined that the to-be-processed image frame is a changed image frame.

In one embodiment, the apparatus further includes:

The determining module is configured to determine that the to-be-processed image frame contains video macroblocks before identifying the type of the to-be-processed image frame.

In one embodiment, the judging submodule includes:

an extraction subunit, used for extracting keywords/feature values in the sample image frame, and comparing the extracted keywords/feature values with preset sensitive keywords/sensitive feature values;

A determination subunit, configured to determine that the sample image frame is a sensitive image if the keyword/feature value of the sample image frame contains a preset sensitive keyword/sensitive feature value.

In one embodiment, the rendering instruction is that the server receives at least one operation message sent by a terminal device, allocates a virtual machine corresponding to the terminal device according to the account information, and sequentially parses the at least one operation message through the virtual machine, Generated according to the parsing result, the at least one operation message includes account information.

In one embodiment, the apparatus further includes:

The statistics module is configured to count the sensitive images corresponding to each account information according to the account information.

In the present disclosure, the rendered image frames can be identified and classified, and the sensitive images that do not meet the requirements of the enterprise can be replaced, and then the replaced image frames can be sent to the terminal device, so that the employees cannot view it on the terminal device. Sensitive images can ensure a good atmosphere in the office and improve the work efficiency of employees.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure;

FIG. 2 is a flowchart of filtering processing of a changed image frame provided by an embodiment of the present disclosure;

3 is a flowchart of an invariant image frame filtering process provided by an embodiment of the present disclosure;

FIG. 4 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure;

5 is a structural diagram of a processing module of an image processing apparatus provided by an embodiment of the present disclosure;

6 is a structural diagram of a processing module of an image processing apparatus provided by an embodiment of the present disclosure;

7 is a structural diagram of an image processing device identification module provided by an embodiment of the present disclosure;

8 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure;

9 is a structural diagram of a judgment sub-module of an image processing apparatus provided by an embodiment of the present disclosure;

10 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure;

11 is an application structure diagram of an image processing system provided by an embodiment of the present disclosure;

FIG. 12 is a flowchart of an image processing method based on the system of FIG. 11 provided by an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.

Portions of the following description relate explicitly or implicitly to algorithms and functional or symbolic representations of operations on data within a computer memory. The descriptions and functional or symbolic representations of these algorithms are the means used by those skilled in the image processing arts to more effectively convey the substance of their work to others skilled in the art. Algorithms are often conceived here as a series of organized steps leading to a desired result. These steps are those requiring physical manipulations of physical quantities such as electrical, magnetic, or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated.

Unless otherwise stated, it should be understood that discussions of terms such as "selecting," "rendering," "displaying," "sending," "acquiring," "generating," etc. used throughout this specification are understood to refer to computer The actions and processing of systems or similar electronic devices that manipulate and convert data represented as physical quantities within a computer system into other data also represented as physical quantities within a computer system or other information storage, transmission, or display device.

The specification also discloses apparatus for performing the operations of the method. Such apparatus is specially constructed for the required purposes, or it may comprise a general purpose computer or other apparatus selectively activated or reconfigured by a computer program stored in the computer. The algorithms and displays described herein are not inherently related to any particular computer or other device. Various general-purpose machines can be used with the programs taught herein. Alternatively, more specific apparatus configurations for performing the required method steps may be applicable. The structure of a conventional general-purpose computer will be described in the following description.

Furthermore, this specification also implicitly discloses computer programs, since it will be apparent to those skilled in the art that the steps of the methods described herein can be implemented by computer code. The computer program is not intended to be limited to any particular programming language and its implementation. It should be understood that a variety of programming languages and codes thereof may be used to implement the teachings of the disclosure contained herein. Furthermore, the computer program is not intended to be limited to any particular flow of control. There are many other kinds of computer programs that can use different control flows without departing from the spirit or scope of the present disclosure.

Furthermore, one or more steps of a computer program may be executed in parallel rather than sequentially. Such a computer program can be stored on any computer-readable medium. The computer-readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with a general purpose computer, and the like. Computer-readable media may also include hard-wired media, such as in Internet systems, or wireless media. When loaded and executed on such a general purpose computer, the computer program effectively produces an apparatus for carrying out the steps of the preferred method.

The present disclosure may also be implemented as hardware modules. More specifically, in the hardware sense, a module is a functional hardware unit designed for use with other components or modules. For example, a module may be implemented using discrete electronic components, or it may form part of an overall electronic circuit such as an application specific integrated circuit (ASIC). Many other possibilities exist. Those skilled in the art will understand that the system can also be implemented as a combination of hardware and software modules.

FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present disclosure, which is applied to an image processing apparatus. The image processing method shown in FIG. 1 includes the following steps:

Step 101, obtaining a rendering instruction, the rendering instruction is generated according to the operation message of the terminal device;

Step 102, performing rendering according to the rendering instruction to generate a to-be-processed image frame;

Step 103, identifying the type of the image frame to be processed, the type of the image frame to be processed includes a changing image frame and an invariant image frame;

Specifically, the image frame to be processed includes at least one macroblock. For example, the image frame to be processed is divided into multiple macroblocks, and each macroblock includes M*N pixels. Identifying the type of the image frame to be processed includes:

Judging whether the macroblock in the to-be-processed image frame is exactly the same as the pixel point of the macroblock at the corresponding position in the previous image frame;

If they are identical, then identify the to-be-processed image frame as a constant macroblock, if not, identify the to-be-processed image frame as a changed macroblock;

Exemplarily, it is determined whether each pixel of the macroblock X in the image frame to be processed is exactly the same as that of the macroblock Y in the previous image frame, that is, it is necessary to compare the macroblock X and each pixel in the macroblock Y. The three values of YUV of the point, and all three values of YUV are equal, the two pixels are considered to be identical), wherein the position of the macroblock Y in the previous image frame is the same as the position of the macroblock X in the image frame to be processed ; If the pixel point in the macroblock X in the image frame to be processed is exactly the same as the pixel point in the macroblock Y in the previous image frame, then it can be determined that the macroblock X is a constant unchange macroblock; If the macroblock in the image frame to be processed is identical The pixels in X are not exactly the same as the pixels in the macroblock Y in the previous image frame, so it can be determined that the macroblock X is an unchanged macroblock.

Count the number of unchanged macroblocks, and if the number of unchanged macroblocks is not greater than a preset threshold, then determine that the image frame to be processed is an unchanged image frame; if the number of unchanged macroblocks is less than the predetermined threshold If the threshold is set, it is determined that the image frame to be processed is a changed image frame.

Specifically, count the number of unchange macroblocks in the image frame to be processed. If the number of unchange macroblocks exceeds the threshold, it means that the difference between the current image frame and the previous image frame is small, and it can be considered that the current image frame is in the previous image frame. The change on the basis of the frame is small; if the number of unchange macroblocks does not exceed the threshold, it can be considered that the change of the image frame to be processed on the basis of the previous image frame is large, and the identifier X can be used to mark the current image frame.

Wherein, if the total number of macroblocks of the image frame to be processed is 100 blocks, the threshold value may be 80 blocks. The threshold value may also be the number of unchange macroblocks in the current image frame, which accounts for the proportion of the total number of macroblocks in the current image frame, for example, 80%.

Step 104, filtering the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame;

If the image frame to be processed is a changing image frame, as shown in Figure 2, the changing image frame is used as a sample image frame, and the following steps are performed:

Step 1041: Determine whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

Step 1042: If the sample logical image frame is a sensitive image, replace the changed image frame with a preset image frame.

If the image frame to be processed is an invariant image frame, as shown in Figure 3, perform the following steps:

Step 104a, record the invariable image frame, and determine the type of the next image frame, until the changed image frame is detected;

Step 104b, in every M frames of invariant image frames, select a sample image frame, and judge whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

M is a positive integer, and a sample image frame is selected, for example, any one frame among 30 frames is selected as the sample image frame.

Step 104c: Whether the sample image frame is a sensitive image, replace the M frames of invariant image frames with preset image frames.

Replace the image frames belonging to the sensitive image, and mark the replaced image frame with the identifier Z; specifically, it can be replaced with a solid color picture, or with a picture with the word "unable to display".

Step 105: Send the target image frame to the terminal device.

In one embodiment, before identifying the type of the image frame to be processed, the method further includes:

It is determined that the to-be-processed image frame contains video macroblocks.

Specifically, it is determined whether the macroblock of the image frame to be processed includes a video macroblock, and if so, it is determined that the image frame to be processed is a video image frame, and the identifier Y can be used to mark the current image frame.

This step enables the embodiments of the present disclosure to improve processing efficiency when processing video images.

In the above-described embodiment, whether the sample image frame is judged to be a sensitive image according to a preset image recognition algorithm includes:

Extracting keywords/feature values in the to-be-processed image frame, and comparing the extracted keywords/feature values with preset sensitive keywords/sensitive feature values;

If the keyword/feature value of the image frame to be processed includes a preset sensitive keyword/sensitive feature value, the image frame to be processed is determined to be a sensitive image.

In addition, some mature intelligent algorithms, such as neural networks, can be used to automatically identify whether image frames include sensitive images.

It should be noted that the sensitive feature value can be the feature value of the sensitive marker map in the sensitive image, and the sensitive marker can be sensitive text (such as books, articles, slogans, etc.), sensitive scenes (buildings), sensitive person images. Wait. When using an intelligent algorithm, when training a neural network, it is necessary to use images containing sensitive markers for training, so that the neural network can identify sensitive images.

Of course, the sensitive marker can also be a display screen of other content that does not meet the company's requirements or is not related to the company's work. For example, for national defense and military units, sensitive markers may include reactionary articles, reactionary pictures, and images of reactionary leaders. For educational institutions, sensitive markers may be violent pornographic images and videos.

In one embodiment, the rendering instruction is that the server receives an operation message sent by a terminal device, allocates a virtual machine VM corresponding to the terminal device according to the account information, parses the operation message sequentially through the virtual machine, and parses the operation message according to the parsing result. generated, the operation message includes account information.

For example, the terminal device packages and compresses the operation information and sends it to the VM through the network. The VM parses the received operation information one by one according to the injection sequence, and obtains multiple operation instructions; the VM executes multiple operation instructions, such as opening a word document, Edit, save, play video and other operations; generate rendering instructions according to the execution results. The rendering instructions are used to generate the screen displayed after executing the operation instructions corresponding to the operation information. For example, the operation instruction is to open a document, then the rendering instruction is to use Generates the page displayed after the document is opened.

In one embodiment, the method further includes:

According to the account information, the sensitive images corresponding to each account information are counted.

FIG. 4 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure. The image processing apparatus 40 shown in FIG.

an obtaining module 401, configured to obtain a rendering instruction, the rendering instruction is generated according to an operation message of the terminal device;

A rendering module 402, configured to perform rendering according to the rendering instruction, and generate an image frame to be processed;

The identification module 403 is used to identify the type of the image frame to be processed, and the type of the image frame to be processed includes a changing image frame and an invariant image frame;

A processing module 404, configured to perform filtering processing on the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame;

The sending module 405 is configured to send the target image frame to the terminal device.

FIG. 5 is a structural diagram of a processing module of an image processing apparatus provided by an embodiment of the present disclosure. The processing module 404 shown in FIG. 5 includes:

Judging sub-module 4041, for if it is a changing image frame, then taking the changing image frame as a sample image frame, and judging whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

The first replacement sub-module 4042 is configured to replace the changed image frame with a preset image frame.

FIG. 6 is a structural diagram of a processing module of an image processing apparatus provided by an embodiment of the present disclosure. The processing module 404 shown in FIG. 6 includes:

The recording submodule 4043 is used to record the unchanged image frame if it is an unchanged image frame, and determine the type of the next image frame until the changed image frame is detected;

The selection submodule 4044 is used to select a sample image frame in every M frames of invariant image frames, and judge whether the sample image frame is a sensitive image according to a preset image recognition algorithm;

The second replacement sub-module 4045 is configured to replace the M frames of unchanged image frames with preset image frames if it is a sensitive image.

FIG. 7 is a structural diagram of a recognition module of an image processing apparatus provided by an embodiment of the present disclosure. The recognition module 403 shown in FIG. 7 includes:

Judging submodule 4031, for judging whether the macroblock in the image frame to be processed is exactly the same as the pixel point of the macroblock at the corresponding position in the previous image frame;

The identification submodule 4032 is used to identify the to-be-processed image frame as an invariant macroblock if it is identical, and to identify the to-be-processed image frame as a changed macroblock if it is not identical;

The statistics sub-module 4033 is used to count the number of the unchanged macroblocks, and if the number of the unchanged macroblocks is not greater than a preset threshold, determine that the image frame to be processed is an unchanged image frame; If the number of variable macroblocks is less than the preset threshold, the image frame to be processed is determined to be a changed image frame.

FIG. 8 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure. The image processing apparatus 40 shown in FIG. 8 further includes:

The determining module 406 is configured to determine that the to-be-processed image frame contains video macroblocks before identifying the type of the to-be-processed image frame.

FIG. 9 is a structural diagram of a judgment sub-module of an image processing apparatus provided by an embodiment of the present disclosure. The judgment sub-module 4031 shown in FIG. 9 includes:

The extraction subunit 11 is used to extract keywords/feature values in the sample image frame, and compare the extracted keywords/feature values with preset sensitive keywords/sensitive feature values;

The determination subunit 12 is configured to determine that the sample image frame is a sensitive image if the keyword/feature value of the sample image frame contains a preset sensitive keyword/sensitive feature value.

In the above-mentioned embodiment, the rendering instruction is that the server receives an operation message sent by a terminal device, allocates a virtual machine corresponding to the terminal device according to the account information, parses the operation message sequentially through the virtual machine, and generates an operation message according to the parsing result. Yes, the operation message includes account information.

FIG. 10 is a structural diagram of an image processing apparatus provided by an embodiment of the present disclosure. The image processing apparatus 40 shown in FIG. 10 includes an acquisition module 401, a rendering module 402, an identification module 403, a processing module 404, a transmission module 405, and a statistics module 407,

The statistics module 407 is configured to count the sensitive images corresponding to each account information according to the account information.

FIG. 11 is an application structure diagram of an image processing system provided by an embodiment of the present disclosure. The server is a cloud server, including multiple virtual machine VM modules, and each VM module corresponds to an account; the image processing apparatus may include a GPU POOL module (equivalent to a GPU POOL module). The acquisition module and the rendering module in the above-mentioned embodiment), the management S2 module (equivalent to the identification module and the sending module in the above-mentioned embodiment) and the monitoring module (equivalent to the processing module in the above-mentioned embodiment), the monitoring module can also exist independently , the terminal device is an R terminal. The specific execution process is shown in Figure 12:

Step 601 , the user performs an operation on the R terminal, and the R terminal uploads the operation information to the corresponding VM on the cloud server.

The operation information includes key events of the keyboard, movement and click events of the mouse or the touchpad, and the like.

Step 602: The VM parses the operation information, and generates a rendering instruction according to the parsing result.

Step 603, the VM sends the rendering instruction to the GPU POOL module in the GPU POOL system, and the rendering instruction is rendered by the GPU POOL module to obtain an image frame;

The GPU POOL module sends the image frames to the S2 module.

In step 604, the S2 module classifies each image frame in units of macroblocks.

In this step, the S2 module divides the rendered image frame into a plurality of macroblocks, and determines the type of each macroblock. The macroblock types include unchange macroblocks and change macroblocks.

The specific judging process is the same as that in the above-mentioned embodiment, and will not be repeated here.

Step 605, S2 sends all the image frames to the monitoring module, and the monitoring module performs filtering processing on the image frames according to the classification.

The image frames here include identified image frames and unidentified image frames.

In addition, it is also necessary to record the frame number and time of the image frames intercepted by each account according to the VM account, so as to facilitate statistical analysis of the network management, so that the network management can quickly find out the video or image viewed by the employee with a large number of sensitive images. .

Step 606, the S2 module encodes the processed image frame, and sends the encoded data to the R terminal.

Specifically, since the sensitive images in the image frames received by S2 have been replaced, and the replaced images are marked as Z, the S module can re-define the image frames marked as Z into macroblocks, and The macroblock type of the newly divided macroblock is determined, and the image frame of the newly determined macroblock type is replaced with the original image frame.

The S2 module encodes the image frame according to the macroblock type of each macroblock, and sends the encoded encoded data to the R terminal.

Step 607: The R terminal decodes and displays the received encoded data.

In the present disclosure, the rendered image frames can be identified and classified, and the sensitive images that do not meet the requirements of the enterprise can be replaced, and then the replaced image frames can be sent to the terminal device, so that the employees cannot view it on the terminal device. Sensitive images can ensure a good atmosphere in the office and improve the work efficiency of employees.

Based on the image processing method described in the above-mentioned embodiment corresponding to FIG. 1 , an embodiment of the present disclosure further provides a computer-readable storage medium. For example, the non-transitory computer-readable storage medium may be a read-only memory (English: ReadOnly Memory). , ROM), random access memory (English: Random Access Memory, RAM), CD-ROM, magnetic tape, floppy disk and optical data storage devices, etc. The storage medium stores computer instructions for executing the image processing method described in the embodiment corresponding to FIG. 1 , which will not be repeated here.

Other embodiments of the present disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or techniques in the technical field not disclosed by the present disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

Claims (10)

1. An image processing method, applied to an image processing device, wherein the method comprises: Obtaining a rendering instruction, the rendering instruction is generated according to the operation message of the terminal device; Rendering according to the rendering instruction to generate a to-be-processed image frame; Identifying the type of the image frame to be processed, the type of the image frame to be processed includes a changing image frame and an invariant image frame; Perform filtering processing on the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame; Send the target image frame to the terminal device. 2. The method according to claim 1, wherein filtering the to-be-processed image frame based on the type of the to-be-processed image frame to obtain the target image frame comprises: If it is a changing image frame, the changing image frame is used as a sample image frame, and whether the sample image frame is a sensitive image is judged according to a preset image recognition algorithm; If it is a sensitive image frame, replace the changed image frame with a preset image frame. 3. The method according to claim 1, wherein filtering the to-be-processed image frame based on the type of the to-be-processed image frame to obtain the target image frame comprises: If it is a constant image frame, record the constant image frame, and determine the type of the next image frame, until a changed image frame is detected; In every M frames of invariant image frames, select a sample image frame, and determine whether the sample image frame is a sensitive image according to a preset image recognition algorithm; If it is a sensitive image, replace the M frames of invariant image frames with preset image frames. 4. The method according to claim 2 or 3, wherein the image frame to be processed comprises at least one macroblock, and identifying the type of the image frame to be processed comprises: Judging whether the macroblock in the to-be-processed image frame is exactly the same as the pixel point of the macroblock at the corresponding position in the previous image frame; If they are identical, then identify the to-be-processed image frame as a constant macroblock, if not, identify the to-be-processed image frame as a changed macroblock; Count the number of unchanged macroblocks, and if the number of unchanged macroblocks is not greater than a preset threshold, then determine that the image frame to be processed is an unchanged image frame; if the number of unchanged macroblocks is less than the predetermined threshold If the threshold is set, it is determined that the image frame to be processed is a changed image frame. 5. The method according to claim 4, wherein before identifying the type of the image frame to be processed, the method further comprises: It is determined that the to-be-processed image frame contains video macroblocks. 6. method according to claim 5, is characterized in that, according to preset image recognition algorithm, judge whether described sample image frame is sensitive class image comprises: Extracting keywords/feature values in the sample image frame, and comparing the extracted keywords/feature values with preset sensitive keywords/sensitive feature values; If the keyword/feature value of the sample image frame contains a preset sensitive keyword/sensitive feature value, the sample image frame is determined to be a sensitive image. 7. The method according to claim 6, wherein the rendering instruction is that a server receives at least one operation message sent by a terminal device, allocates a virtual machine corresponding to the terminal device according to the account information, and uses the The virtual machine sequentially parses the at least one operation message, and is generated according to the parsing result, and the at least one operation message includes account information. 8. The method according to claim 7, wherein the method further comprises: According to the account information, the sensitive images corresponding to each account information are counted. 9. An image processing device, wherein the device comprises: an acquisition module, used for acquiring rendering instructions, the rendering instructions are generated according to the operation message of the terminal device; a rendering module, configured to perform rendering according to the rendering instruction, and generate a to-be-processed image frame; a processing module, configured to filter the to-be-processed image frame based on the type of the to-be-processed image frame to obtain a target image frame; A sending module, configured to send the target image frame to the terminal device. 10. The apparatus according to claim 9, wherein the processing module comprises: an identification sub-module for identifying the type of the image frame to be processed, the type of the image frame to be processed includes a changing image frame and an invariant image frame; a judging sub-module, configured to use the changed image frame as a sample image frame if it is a changing image frame, and judge whether the sample image frame is a sensitive image according to a preset image recognition algorithm; The first replacement submodule is configured to replace the changed image frame with a preset image frame.

Images