Image processing method, device and system

By screening and blurring the recognition results in image processing technology, the problem of facial information leakage is solved and effective protection of user privacy is achieved.

CN111967039BActive Publication Date: 2024-11-12ZHEJIANG DAHUA TECH CO LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202010636842.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-03
Publication Date
2024-11-12
Estimated Expiration
2040-07-03

AI Technical Summary

Technical Problem

When it is necessary to monitor a specific face, the prior art will be difficult to avoid the leakage of facial information from other users, resulting in the exposure of private information.

Method used

By identifying the acquired images to be processed, faces that meet preset conditions in the normal area are judged, and screening and blurring are performed based on pre-stored face information to ensure the privacy protection of specific faces.

Benefits of technology

It effectively avoids the leakage of facial information and protects user privacy, especially in areas with low face density, ensuring that the privacy of specific faces is not exposed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111967039B_ABST
    Figure CN111967039B_ABST
Patent Text Reader

Abstract

The present invention discloses an image processing method, device and system, which obtains a recognition result by recognizing an acquired image to be processed, and when it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition according to pre-stored face information, and a fuzzy processing is performed on the specific face, wherein the normal area is an area where the density of the recognized face is not greater than a first preset value. In this way, since the determined specific face is fuzzy, when the specific face is displayed, the specific face is blurred, which can avoid leakage of information of the specific face, thereby protecting the privacy of the user corresponding to the specific face.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an image processing method, device and system. Background Art

[0002] As users become increasingly aware of personal privacy protection, it becomes particularly important to protect user privacy.

[0003] When it is necessary to monitor the face corresponding to a target, the face corresponding to the target needs to be displayed for easy viewing. However, when collecting the face corresponding to the target, the faces of other users may also be collected. However, since the faces of other users do not need to be monitored, if the faces of other users are also displayed, the faces of other users will be exposed, thereby causing privacy information leakage for other users.

[0004] Based on this, how to avoid the leakage of user facial information and achieve protection of users is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] The embodiments of the present invention provide an image processing method, device and system to prevent the leakage of user's facial information and achieve protection for the user.

[0006] In a first aspect, an embodiment of the present invention provides an image processing method, including:

[0007] Recognize the acquired image to be processed to obtain a recognition result;

[0008] When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition according to pre-stored face information, and a fuzzy processing is performed on the specific face;

[0009] The normal area is an area where the density of recognized faces is not greater than a first preset value.

[0010] Optionally, in an embodiment of the present invention, the face that meets the preset condition is: the number of feature points of the recognized face is greater than a second preset value.

[0011] Optionally, in the embodiment of the present invention, selecting a specific face from faces that meet the preset conditions according to pre-stored face information includes:

[0012] The specific face is screened out from the faces meeting the preset conditions according to the similarity between the faces meeting the preset conditions and the pre-stored faces.

[0013] Optionally, in the embodiment of the present invention, selecting the specific face from the faces meeting the preset conditions according to the similarity between the faces meeting the preset conditions and the pre-stored faces includes:

[0014] Determining the similarity between the features of the human face that meet the preset conditions and the features of the pre-stored human face;

[0015] The human face that meets the preset condition and whose similarity is not greater than the third preset value is determined as the specific human face.

[0016] Optionally, in the embodiment of the present invention, the method further includes:

[0017] The specific face after the blurring process is displayed.

[0018] Optionally, in the embodiment of the present invention, the method further includes:

[0019] When there is a human face that does not meet the preset condition in the normal area, the human face that does not meet the preset condition is directly displayed.

[0020] Optionally, in the embodiment of the present invention, the method further includes:

[0021] When it is determined that the recognition result includes an abnormal area, directly displaying the abnormal area;

[0022] The abnormal area is an area where the density of recognized faces is greater than the first preset value.

[0023] In a second aspect, an embodiment of the present invention further provides an image processing device, including:

[0024] A memory for storing program instructions;

[0025] The processor is used to call the program instructions stored in the memory and execute according to the obtained program:

[0026] Recognize the acquired image to be processed to obtain a recognition result;

[0027] When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition according to pre-stored face information, and a fuzzy processing is performed on the specific face;

[0028] The normal area is an area where the density of recognized faces is not greater than a first preset value.

[0029] Optionally, in this embodiment of the present invention, the processor is further configured to:

[0030] When there is a human face that does not meet the preset condition in the normal area, the human face that does not meet the preset condition is directly displayed.

[0031] In a third aspect, an embodiment of the present invention provides an image processing system, comprising: an image acquisition device, and the above-mentioned image processing device;

[0032] Among them, the image acquisition device is used to acquire the image to be processed and transmit the image to be processed to the image processing device, so that the image processing device can determine the specific face from the image to be processed and then perform blurring processing on the specific face.

[0033] The beneficial effects of the present invention are as follows:

[0034] An image processing method and device provided by an embodiment of the present invention obtains a recognition result by recognizing an acquired image to be processed. When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition based on pre-stored face information, and a fuzzy processing is performed on the specific face, wherein the normal area is an area where the density of the recognized face is not greater than a first preset value. In this way, since the determined specific face is fuzzy, when the specific face is displayed, the specific face is blurred, which can avoid leakage of information of the specific face, thereby protecting the privacy of the user corresponding to the specific face. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of an image processing method provided in an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a process of an embodiment provided in an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the structure of an image processing device provided in an embodiment of the present invention;

[0038] Figure 4 A schematic diagram of the structure of another image processing device provided in an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of the structure of another image processing device provided in an embodiment of the present invention;

[0040] Figure 6 The figure is a schematic diagram of the structure of an image processing system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be described in detail with reference to the accompanying drawings to describe a specific implementation of an image processing method, device, and system provided by an embodiment of the present invention. It should be noted that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] An image processing method provided by an embodiment of the present invention is as follows: Figure 1 As shown, it may include:

[0043] S101, identifying the acquired image to be processed to obtain a recognition result;

[0044] The method for obtaining the image to be processed may be accomplished by using existing technologies and is not specifically limited here.

[0045] For example, the image to be processed may be acquired by a camera but is not limited to the above.

[0046] When identifying the image to be processed, the image to be processed may be identified by machine learning, but is not limited thereto. Any method known to those skilled in the art for identifying the image to be processed may also be used, which is not limited here.

[0047] S102. When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition based on pre-stored face information, and the specific face is blurred, wherein the normal area is an area where the density of the recognized faces is not greater than a first preset value.

[0048] Moreover, blurring a specific face can be understood as coding the specific face.

[0049] In this way, since the determined specific face is blurred, when the specific face is displayed, the specific face is blurred, which can avoid leakage of information of the specific face, thereby protecting the privacy of the user corresponding to the specific face.

[0050] It should be noted that the image acquisition device transmits the acquired image to be processed to the image processing device so that the image processing device executes the above-mentioned processes S101 and S102. In this way, the load of the image acquisition device can be reduced and the manufacturing cost of the image acquisition device can be reduced.

[0051] During specific implementation, in an embodiment of the present invention, the human face that meets the preset condition is: the number of feature points of the recognized human face is greater than a second preset value.

[0052] It should be noted that the second preset value can be set according to actual conditions and is not limited here, so as to meet the needs of different scenarios and improve the flexibility of design.

[0053] Among them, the feature points of the face can be understood as: points used to represent the corners of the mouth, nose, eyes and other parts of the face, and these feature points can be obtained through existing facial feature point recognition methods. For details, please refer to the existing technology and will not be described in detail here.

[0054] Furthermore, a face that meets preset conditions (temporarily referred to as a normal face) means that more feature points in the face can be identified, so that the identity of the user corresponding to the face can be determined through the feature points.

[0055] In a specific implementation, in an embodiment of the present invention, based on the pre-stored face information, a specific face is selected from faces that meet preset conditions, including:

[0056] According to the similarity between the human faces meeting the preset conditions and the pre-stored human faces, a specific human face is screened out from the human faces meeting the preset conditions.

[0057] The higher the similarity between a face that meets the preset conditions (which can be temporarily referred to as a normal face) and a pre-stored face, the more similar the normal face is to the pre-stored face, that is, the closer it is to the target;

[0058] Similarly, the lower the similarity between a normal face and a pre-stored face, the less the normal face resembles the pre-stored face, that is, the closer it is to the target.

[0059] In this way, according to the similarity between the human face meeting the preset conditions and the pre-stored human face, it is helpful to screen out a specific human face from the human faces meeting the preset conditions, so as to perform blurring processing on the specific human face later.

[0060] Specifically, in the embodiment of the present invention, based on the similarity between the face meeting the preset condition and the pre-stored face, selecting a specific face from the faces meeting the preset condition includes:

[0061] Determine the similarity between the features of the human face that meet the preset conditions and the features of the human face that are pre-stored;

[0062] A face that meets the preset conditions and has a similarity not greater than a third preset value is determined as a specific face.

[0063] Among them, the setting of the third preset value can be but not limited to 80% or 50%, etc., and can also be set according to actual conditions, which is not limited here, to meet the needs of different scenarios and improve the flexibility of design.

[0064] Furthermore, determining the similarity between the features of a human face that meets preset conditions (which may be but is not limited to the feature points mentioned above) and the features of a pre-stored human face may be accomplished using existing technologies, which are not limited here.

[0065] In this way, by determining the similarity between the features of the face that meets the preset conditions and the features of the pre-stored face, it is helpful to screen out a specific face from the faces that meet the preset conditions, so as to perform fuzzy processing on the specific face later.

[0066] In the specific implementation, in the embodiment of the present invention, it also includes:

[0067] Displays a specific face after blurring.

[0068] In this way, the specific face identified can be blurred and displayed through an image processing device. Since the specific face (i.e., unrelated person) is blurred, user privacy is protected and user concerns about privacy information leakage are resolved.

[0069] It should be noted that after determining a specific face, the image processing device can encapsulate the information of the specific face, and encapsulate it into the header data of the frame data of the image to be processed, and store it in the hard disk; when the image to be processed is played back, the image to be processed is first decapsulated, and then the specific face after blurring is displayed, thereby solving the problem of leaking user privacy.

[0070] In the specific implementation, in the embodiment of the present invention, it also includes:

[0071] When there is a face that does not meet the preset conditions in the normal area, the face that does not meet the preset conditions is directly displayed.

[0072] Furthermore, for a face that does not meet the preset conditions, it can be understood that: the user's face is at least partially blocked, resulting in fewer feature points of the recognized face. For example, the recognized face is wearing a mask, a mask, or at least a part of the face is blocked by other objects.

[0073] In this way, when the normal area includes a face that does not meet the preset conditions, the face that does not meet the preset conditions is not blurred, but is directly displayed. Therefore, for the above situation, sufficient clues can be obtained from the image in criminal cases or when necessary, that is, it is convenient to retrieve evidence later and is conducive to maintaining daily security management.

[0074] In the specific implementation, in the embodiment of the present invention, it also includes:

[0075] When it is determined that the recognition result includes an abnormal area, the abnormal area is directly displayed;

[0076] The abnormal area is an area where the density of recognized faces is greater than a first preset value.

[0077] It should be noted that the first preset value can be set according to actual conditions and is not limited here, so as to meet the needs of different scenarios and improve the flexibility of design.

[0078] Among them, the abnormal area can be understood as: an area with a dense population, for example, an area where a group of people fight or a large number of people gather, which makes the density of faces in these areas relatively high.

[0079] In this way, after the abnormal area is determined, blurring is not performed and the abnormal area is directly displayed, so that the face in the abnormal area can be clearly observed during subsequent viewing, which is convenient for later evidence collection.

[0080] The image processing method provided by the embodiment of the present invention is described below with reference to a specific embodiment.

[0081] Example: Figure 2 shown.

[0082] S201, identifying the acquired image to be processed to obtain a recognition result;

[0083] S202, determining whether the recognition result includes an abnormal area; if so, directly displaying the abnormal area; if not, it means that the recognition result includes a normal area, and executing step S203;

[0084] S203, after determining that the recognition result includes a normal area, determine whether the normal area includes a face that meets a preset condition; if so, execute step S204; if not, execute step S207;

[0085] S204, determining the similarity between the features of the human face that meet the preset conditions and the features of the human face that are pre-stored;

[0086] S205, determining a face that meets a preset condition and has a similarity not greater than a third preset value as a specific face;

[0087] S206, displaying the specific face after blurring;

[0088] S207: When it is determined that the normal area includes a face that does not meet the preset condition, directly display the face that does not meet the preset condition.

[0089] Based on the same inventive concept, an embodiment of the present invention provides an image processing device, the implementation principle of the device is similar to the implementation principle of the aforementioned image processing method. The specific implementation of the device can refer to the implementation of the aforementioned method, and the repeated parts will not be repeated.

[0090] Specifically, an embodiment of the present invention provides an image processing device, the structure of which is as follows: Figure 3 As shown, including:

[0091] Memory 301, used for storing program instructions;

[0092] The processor 302 is used to call the program instructions stored in the memory 301 and execute according to the obtained program:

[0093] Recognize the acquired image to be processed to obtain a recognition result;

[0094] When it is determined that the recognition result includes a normal area and a face that meets the preset conditions is determined from the normal area, a specific face is screened out from the faces that meet the preset conditions according to pre-stored face information, and a fuzzy processing is performed on the specific face;

[0095] The normal area is an area where the density of recognized faces is not greater than a first preset value.

[0096] Optionally, in the embodiment of the present invention, the human face that meets the preset condition is: the number of feature points of the recognized human face is greater than a second preset value.

[0097] Optionally, in this embodiment of the present invention, the processor 302 is specifically configured to:

[0098] According to the similarity between the human faces meeting the preset conditions and the pre-stored human faces, a specific human face is screened out from the human faces meeting the preset conditions.

[0099] Optionally, in this embodiment of the present invention, the processor 302 is specifically configured to:

[0100] Determine the similarity between the features of the human face that meet the preset conditions and the features of the human face that are pre-stored;

[0101] A face that meets the preset conditions and has a similarity not greater than a third preset value is determined as a specific face.

[0102] Optionally, in this embodiment of the present invention, the processor 302 is further configured to:

[0103] Displays a specific face after blurring.

[0104] Optionally, in this embodiment of the present invention, the processor 302 is further configured to:

[0105] When there is a face that does not meet the preset conditions in the normal area, the face that does not meet the preset conditions is directly displayed.

[0106] Optionally, in this embodiment of the present invention, the processor 302 is further configured to:

[0107] When it is determined that the recognition result includes an abnormal area, the abnormal area is directly displayed;

[0108] The abnormal area is an area where the density of recognized faces is greater than a first preset value.

[0109] Based on the same inventive concept, an embodiment of the present invention provides another image processing device, the implementation principle of the device is similar to the implementation principle of the aforementioned image processing method. The specific implementation of the device can refer to the implementation of the aforementioned method, and the repeated parts will not be repeated.

[0110] Specifically, the embodiment of the present invention provides another image processing device, the structure of which is as follows: Figure 4 As shown, including:

[0111] The recognition module 401 is used to recognize the acquired image to be processed and obtain a recognition result;

[0112] The processing module 402 is used to select a specific face from the faces that meet the preset conditions according to pre-stored face information, and perform fuzzy processing on the specific face when it is determined that the recognition result includes a normal area and a face that meets the preset conditions is determined from the normal area.

[0113] The normal area is an area where the density of recognized faces is not greater than a first preset value.

[0114] Optionally, in the embodiment of the present invention, the human face that meets the preset condition is: the number of feature points of the recognized human face is greater than a second preset value.

[0115] Optionally, in the embodiment of the present invention, the processing module 402 is specifically used for:

[0116] According to the similarity between the human faces meeting the preset conditions and the pre-stored human faces, a specific human face is screened out from the human faces meeting the preset conditions.

[0117] Optionally, in the embodiment of the present invention, the processing module 402 is specifically used for:

[0118] Determine the similarity between the features of the human face that meet the preset conditions and the features of the human face that are pre-stored;

[0119] A face that meets the preset conditions and has a similarity not greater than a third preset value is determined as a specific face.

[0120] Optionally, in this embodiment of the present invention, the processing module 402 is further configured to:

[0121] Displays a specific face after blurring.

[0122] Optionally, in this embodiment of the present invention, the processing module 402 is further configured to:

[0123] When there is a face that does not meet the preset conditions in the normal area, the face that does not meet the preset conditions is directly displayed.

[0124] Optionally, in this embodiment of the present invention, the processing module 402 is further configured to:

[0125] When it is determined that the recognition result includes an abnormal area, the abnormal area is directly displayed;

[0126] The abnormal area is an area where the density of recognized faces is greater than a first preset value.

[0127] Optionally, in an embodiment of the present invention, if Figure 5 As shown, it also includes: a storage module 403 and a playback module 404;

[0128] Storage module 403, used to store pre-stored face information and store specific face information;

[0129] The playback module 404 is used to playback the image to be processed after the blurring process.

[0130] Based on the same inventive concept, an embodiment of the present invention provides an image processing system, the structure of which is as follows: Figure 6 As shown, it includes: an image acquisition device 601, and an image processing device 602;

[0131] Among them, the image acquisition device 601 is used to acquire the image to be processed and transmit the image to be processed to the image processing device 602, so that the image processing device 602 determines the specific face from the image to be processed and then performs blurring processing on the specific face.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device, so that the instructions executed by the processor of the computer or other programmable data processing device can implement one or more processes and / or blocks in the flowchart. Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0135] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An image processing method, characterized in that: include: Recognize the acquired image to be processed to obtain a recognition result; When it is determined that the recognition result includes an abnormal area, directly displaying the abnormal area; When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition according to pre-stored face information, and a fuzzy processing is performed on the specific face; The abnormal area is an area where the density of recognized faces is greater than a first preset value; the normal area is an area where the density of recognized faces is not greater than the first preset value; The step of selecting a specific face from faces that meet the preset conditions based on the pre-stored face information includes: Filtering the specific face from the faces that meet the preset conditions according to the similarity between the faces that meet the preset conditions and the pre-stored faces; The step of selecting the specific face from the faces that meet the preset condition based on the similarity between the face that meets the preset condition and the pre-stored face includes: Determining the similarity between the features of the human face that meet the preset conditions and the features of the pre-stored human face; Determine the face that meets the preset condition and whose similarity is not greater than a third preset value as the specific face; The method further comprises: When there is a human face that does not meet the preset condition in the normal area, the human face that does not meet the preset condition is directly displayed.

2. The method according to claim 1, characterized in that The human face that meets the preset condition is: the number of feature points of the recognized human face is greater than a second preset value.

3. The method according to claim 1, characterized in that Also includes: The specific face after the blurring process is displayed.

4. An image processing device, characterized in that: include: A memory for storing program instructions; The processor is used to call the program instructions stored in the memory and execute according to the obtained program: Recognize the acquired image to be processed to obtain a recognition result; When it is determined that the recognition result includes an abnormal area, directly displaying the abnormal area; When it is determined that the recognition result includes a normal area and a face that meets a preset condition is determined from the normal area, a specific face is screened out from the faces that meet the preset condition according to pre-stored face information, and a fuzzy processing is performed on the specific face; The abnormal area is an area where the density of recognized faces is greater than a first preset value; the normal area is an area where the density of recognized faces is not greater than the first preset value; The step of selecting a specific face from faces that meet the preset conditions based on the pre-stored face information includes: Filtering the specific face from the faces that meet the preset conditions according to the similarity between the faces that meet the preset conditions and the pre-stored faces; The step of selecting the specific face from the faces that meet the preset condition based on the similarity between the face that meets the preset condition and the pre-stored face includes: Determining the similarity between the features of the human face that meet the preset conditions and the features of the pre-stored human face; Determine the face that meets the preset condition and whose similarity is not greater than a third preset value as the specific face; The processor is further configured to: When there is a human face that does not meet the preset condition in the normal area, the human face that does not meet the preset condition is directly displayed.

5. An image processing system, characterized in that: include: An image acquisition device, and an image processing device as claimed in claim 4; Among them, the image acquisition device is used to acquire the image to be processed and transmit the image to be processed to the image processing device, so that the image processing device can determine the specific face from the image to be processed and then perform blurring processing on the specific face.

Citation Information

Patent Citations

  • Face recognition method, device and mobile terminal capable of recognizing face

    CN102542299A

  • Human face detection method and human face detection equipment

    CN103049733A

  • Human face identification method, terminal and computer readable storage medium

    CN107609508A

  • Image privacy protection method and system

    CN108197453A

  • Layout control method and apparatus, electronic device and computer storage medium

    CN108229323A