CN116881967A - Privacy protection method, device and equipment - Google Patents
Privacy protection method, device and equipment Download PDFInfo
- Publication number
- CN116881967A CN116881967A CN202310897947.6A CN202310897947A CN116881967A CN 116881967 A CN116881967 A CN 116881967A CN 202310897947 A CN202310897947 A CN 202310897947A CN 116881967 A CN116881967 A CN 116881967A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- target area
- privacy
- original image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 61
- 238000000586 desensitisation Methods 0.000 claims abstract description 30
- 238000004891 communication Methods 0.000 claims description 20
- 230000007704 transition Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
- G06F21/6254—Protecting personal data, e.g. for financial or medical purposes by anonymising data, e.g. decorrelating personal data from the owner's identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
- G06T1/0028—Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Studio Devices (AREA)
Abstract
The application relates to a privacy protection method, device and equipment. The method comprises the following steps: acquiring an original image acquired by image acquisition equipment on a first target area; determining a privacy protection mode matched with any one of the image acquisition device and the first target area; processing the original image according to the privacy protection mode to obtain a desensitized image; the original image is deleted and the desensitized image is saved and output as the final image. According to the application, the original image acquired by the camera is processed, so that the personal privacy can be effectively protected. According to different privacy protection modes, target protection objects in the image can be identified, so that desensitization processing is performed in a targeted mode, the privacy protection effect is ensured, and the technical problem that privacy is revealed when electronic equipment is used in a public area is solved.
Description
Technical Field
The application relates to the technical field of public safety vision, in particular to a privacy protection method, device and equipment.
Background
A large number of cameras are installed in some public areas, such as coffee shops, restaurants and the like; particularly, a large number of cameras are also installed on the new energy vehicle, so that the new energy vehicle becomes mobile camera equipment. These devices effectively guarantee personnel and property safety, and at the same time, they capture a lot of private information, if some "careful people" get it, for example: some people can watch mobile phones and computers in places such as coffee shops, information displayed on the electronic equipment can be captured by the cameras, and the users are hidden and privately leaked.
In order to protect user privacy, the related art only considers the desensitization processing of information on the device being used by the user, for example, the user automatically blurs or cuts the content containing the user privacy in the image when releasing the image. However, there is no privacy protection method for limiting photographing in public areas, and users still face the risk of privacy disclosure when using electronic devices in public areas.
For the problem of privacy disclosure in using electronic devices in public areas, no effective solution has been proposed.
Disclosure of Invention
The application provides a privacy protection method, a privacy protection device and privacy protection equipment, which are used for solving the technical problem that privacy leakage exists when electronic equipment is used in a public area.
According to an aspect of an embodiment of the present application, there is provided a privacy protection method including:
acquiring an original image acquired by image acquisition equipment on a first target area;
determining a privacy protection mode matched with any one of the image acquisition device and the first target area;
processing the original image according to the privacy protection mode to obtain a desensitized image;
the original image is deleted and the desensitized image is saved and output as the final image.
Optionally, determining a privacy preserving pattern matching any of the image capturing device and the first target area comprises at least one of:
acquiring the equipment type of the image acquisition equipment, and determining a privacy protection mode corresponding to the equipment type;
acquiring the position information of a first target area, and determining a privacy protection mode corresponding to the position information;
receiving a privacy protection mode sent by a target server, wherein the target server is used for managing a target area;
the privacy protection mode comprises a portrait protection mode, a device protection mode, an intelligent protection mode and a complete protection mode.
Optionally, in the case of the privacy preserving mode and the portrait preserving mode, processing the original image according to the privacy preserving mode to obtain the desensitized image includes:
inputting the original image into a human image recognition model to recognize a target human image existing in the original image through the human image recognition model;
determining a target portrait as a target protection object, and determining a second target area where the target protection object is located in the original image;
and (3) desensitizing the second target area to obtain a desensitized image.
Optionally, in the case that the privacy preserving mode is the device preserving mode, processing the original image according to the privacy preserving mode to obtain the desensitized image includes:
Inputting the original image into an electronic equipment identification model to identify target electronic equipment existing in the original image through the electronic equipment identification model;
determining target electronic equipment as a target protection object, and determining a second target area where the target protection object is located in an original image;
and (3) desensitizing the second target area to obtain a desensitized image.
Optionally, in the case that the privacy protection mode is the intelligent protection mode, processing the original image according to the privacy protection mode to obtain the desensitized image includes:
inputting an original image into an intelligent recognition model to determine the confidence that each object in the original image belongs to a target protection object through the intelligent recognition model, wherein the intelligent recognition model is a neural network model obtained based on self-defined configuration training of the target protection object;
determining an object with the confidence reaching the target value as a target protection object, and determining a second target area where the target protection object is located in the original image;
and (3) desensitizing the second target area to obtain a desensitized image.
Optionally, determining the second target area where the target protection object is located in the original image includes:
Determining a local image which completely contains the target protection object in the original image;
performing Fourier transform on the local image to obtain a transformed image of the local image;
identifying and segmenting the outline of the target protection object in the transformed image;
determining a region surrounded by the outline of the target protection object as a second target region in the transformed image; or alternatively, the process may be performed,
the transformed image is subjected to inverse fourier transform to determine the contour of the target protection object in the original partial image, and a region surrounded by the contour of the target protection object in the partial image is determined as a second target region.
Optionally, desensitizing the second target area to obtain a desensitized image includes any of the following:
down-converting frequency data of a second target area in the converted image to soften the second target area; performing inverse Fourier transform to obtain a desensitized image;
determining a third target area and a fourth target area adjacent to the second target area in the partial image, wherein the third target area and the fourth target area are distributed on different sides of the second target area; determining a first image feature of a third target region and a second image feature of a fourth target region; generating a target transition image from the third target region to a fourth target region based on the first image feature and the second image feature; filling a second target area by using the target transition image to obtain a desensitized image;
Determining a fifth target region adjacent to the second target region and marked as background in the partial image; extracting any subarea in the fifth target area as a filling template; and filling the second target area by using a filling template to obtain a desensitized image.
Optionally, in the case that the privacy protection mode is the full protection mode, processing the original image according to the privacy protection mode further includes:
and deleting the original image, popping up a prompt popup window, and displaying prompt information for prohibiting shooting in the prompt popup window.
According to another aspect of an embodiment of the present application, there is provided a privacy protecting apparatus including:
the image acquisition module is used for acquiring an original image acquired by the image acquisition equipment on the first target area;
the mode selection module is used for determining a privacy protection mode matched with any one of the image acquisition equipment and the first target area;
the desensitization processing module is used for processing the original image according to the privacy protection mode to obtain a desensitized image;
and the storage output module is used for deleting the original image and storing and outputting the desensitized image as a final image.
According to another aspect of the embodiments of the present application, there is provided an electronic device including a memory, a processor, a communication interface, and a communication bus, where the memory stores a computer program executable on the processor, the memory, the processor, and the communication interface communicate through the communication bus, and the processor executes the steps of the method when the processor executes the computer program.
According to another aspect of embodiments of the present application, there is also provided a computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the above-described method.
Compared with the related art, the technical scheme provided by the embodiment of the application has the following advantages:
the application provides a privacy protection method, which comprises the following steps: acquiring an original image acquired by image acquisition equipment on a first target area; determining a privacy protection mode matched with any one of the image acquisition device and the first target area; processing the original image according to the privacy protection mode to obtain a desensitized image; the original image is deleted and the desensitized image is saved and output as the final image. According to the application, the original image acquired by the camera is processed, so that the personal privacy can be effectively protected. According to different privacy protection modes, target protection objects in the image can be identified, so that desensitization processing is performed in a targeted mode, the privacy protection effect is ensured, and the technical problem that privacy is revealed when electronic equipment is used in a public area is solved. Meanwhile, the application adopts the image processing technology, can more automatically carry out privacy protection, does not greatly influence the usability of the image, and has practicability and feasibility.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it will be apparent to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a schematic diagram of an alternative privacy preserving method hardware environment according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of an alternative privacy preserving method according to an embodiment of the present application;
FIG. 3 is a block diagram of an alternative privacy preserving apparatus provided in accordance with an embodiment of the present application;
fig. 4 is a schematic structural diagram of an alternative electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the following description, suffixes such as "module", "component", or "unit" for representing elements are used only for facilitating the description of the present application, and are not of specific significance per se. Thus, "module" and "component" may be used in combination.
In the related art, in order to protect the privacy of a user, only the desensitization processing of information on a device being used by the user is often considered, for example, the user automatically performs blurring or cropping processing on the content containing the privacy of the user in the image when the user issues the image. However, there is no privacy protection method for limiting photographing in public areas, and users still face the risk of privacy disclosure when using electronic devices in public areas.
In order to solve the problems mentioned in the background art, according to an aspect of the embodiments of the present application, an embodiment of a privacy protection method is provided.
Alternatively, in the embodiment of the present application, the above privacy protection method may be applied to a hardware environment constituted by the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, the server 103 is connected to the terminal 101 through a network, which may be used to provide services (such as image processing services, privacy preserving services, etc.) to the terminal or clients installed on the terminal, and a database 105 may be provided on the server or independent of the server, for providing data storage services to the server 103, where the network includes, but is not limited to: a wide area network, metropolitan area network, or local area network, the terminal 101 includes, but is not limited to, devices having image acquisition capabilities, such as cell phones, tablet computers, video cameras, camera-equipped travel tools, and the like.
A privacy preserving method in the embodiment of the present application may be performed by the server 103, or may be performed by the server 103 and the terminal 101 together, as shown in fig. 2, and the method may include the following steps:
step S202, acquiring an original image acquired by image acquisition equipment for a first target area;
step S204, determining a privacy protection mode matched with any one of the image acquisition device and the first target area;
step S206, processing the original image according to the privacy protection mode to obtain a desensitized image;
step S208, the original image is deleted, and the desensitized image is saved and output as a final image.
Through steps S202 to S208, the method and the device can effectively protect personal privacy by processing the original image acquired by the camera. According to different privacy protection modes, target protection objects in the image can be identified, so that desensitization processing is performed in a targeted mode, the privacy protection effect is ensured, and the technical problem that privacy is revealed when electronic equipment is used in a public area is solved. Meanwhile, the application adopts the image processing technology, can more automatically carry out privacy protection, does not greatly influence the usability of the image, and has practicability and feasibility.
In public areas such as coffee shops, waiting rooms, parks, streets and the like, a large number of cameras are installed, and particularly, a large number of cameras are installed on new energy vehicles, so that the mobile camera equipment is formed. When the cameras shoot images of public areas, the cameras inevitably acquire figures and electronic products being used, and if the display screen of the electronic products contains private contents of users, the private contents of the users are possibly revealed. Therefore, the application aims at privacy protection of the image shot in the public area, and the desensitization processing is directly carried out in the shooting stage of the image according to the corresponding privacy protection mode, and the shot image is the image subjected to the desensitization processing.
In the embodiment of the application, the privacy protection function can be preset before the image acquisition equipment leaves the factory, or the privacy protection function can be obtained through updating, so that the image acquisition equipment can select a proper privacy protection mode to desensitize the original image when the image acquisition equipment acquires the image. The mode is suitable for intelligent electronic equipment with photographing functions such as mobile phones, tablet computers, intelligent cameras and video cameras.
In the embodiment of the application, the image acquisition equipment can be associated with the external control unit, when the image acquisition equipment acquires the image, the control unit selects a proper privacy protection mode, so that the original image acquired by the image acquisition equipment is subjected to desensitization, and finally the image subjected to the desensitization is stored. The method is suitable for intelligent equipment taking photos as auxiliary functions, such as a car machine system, a car body camera controlled by the car machine system and the like.
In step S202, the first target area may be any area that needs privacy protection, such as a public area, a private area, and a regulated area.
In step S204, determining a privacy preserving mode matching any of the image capturing device and the first target area includes at least one of:
acquiring the equipment type of the image acquisition equipment, and determining a privacy protection mode corresponding to the equipment type;
acquiring the position information of a first target area, and determining a privacy protection mode corresponding to the position information;
receiving a privacy protection mode sent by a target server, wherein the target server is used for managing a target area;
the privacy protection mode comprises a portrait protection mode, a device protection mode, an intelligent protection mode and a complete protection mode.
In the embodiment of the application, the privacy protection mode can comprise, but is not limited to, a portrait protection mode, a device protection mode, an intelligent protection mode, a complete protection mode and the like.
In the embodiment of the application, the corresponding privacy protection mode can be determined according to the equipment type of the image acquisition equipment, the equipment type can comprise a security camera, a private camera and the like, and for the security camera, as basic traceability requirements (such as searching for an accident liability person and the like through monitoring exist, the equipment can be set into the equipment protection mode, namely only equipment content used by shooting personnel is forbidden, and the fuzzy processing is carried out on the display screen of the electronic product appearing in the original image without processing the portrait. For the private camera, a portrait protection mode, a device protection mode or a combination of the portrait protection mode and the device protection mode can be set for the private camera according to actual requirements, and the private camera can be selected according to actual conditions.
In the embodiment of the application, the privacy protection mode can be determined according to the position of the original image, namely the position of the first target area, for example, the privacy protection mode can be set for public areas so as to meet basic traceability requirements, the full protection mode can be set for special areas such as a secret area and a control area, equipment entering the area is forbidden to acquire images, and if a vehicle runs to a military control area, the vehicle camera is forbidden to shoot the images of the area according to the constraint of the full protection mode.
In the embodiment of the application, the privacy protection mode can be selected by the image acquisition equipment or a control unit associated with the image acquisition equipment, and can also be selected by a server. The server monitors the equipment entering the first target area in real time, and sends a corresponding privacy protection mode to the equipment from the moment when the equipment enters the first target area so as to restrict the shooting behavior of the equipment in the first target area.
In the embodiment of the application, only shooting of the human images is forbidden in the human image protection mode, so that desensitization processing such as blurring, replacement and the like is required to be carried out on the human images existing in the original images. In the equipment protection mode, only equipment contents used by shooting personnel, such as notebook computers used by people sitting in a coffee shop, are forbidden, so that electronic products in original images need to be identified first, and then the electronic products or display screens of the electronic products are subjected to fuzzy desensitization processing. In the intelligent protection mode, a user can customize the privacy content to be protected, and further train the neural network model based on the custom configuration, so that the neural network model can automatically perform desensitization processing when the privacy content to be protected is identified. In the full protection mode, shooting of an image is prohibited. These several privacy preserving modes are described further below, respectively.
In step S206, in the case of the privacy preserving mode being the portrait preserving mode, processing the original image according to the privacy preserving mode to obtain the desensitized image includes:
step 1, inputting an original image into a human image recognition model to recognize a target human image existing in the original image through the human image recognition model;
step 2, determining a target portrait as a target protection object, and determining a second target area where the target protection object is located in the original image;
and step 3, desensitizing the second target area to obtain a desensitized image.
In the embodiment of the application, if the portrait protection mode is selected, the portrait existing in the original image can be identified through the portrait identification model, the position of the portrait is further determined in the original image, and finally the desensitization treatment is carried out on the image content at the position.
In step S206, when the privacy preserving mode is the device preserving mode, processing the original image according to the privacy preserving mode to obtain the desensitized image includes:
step 1, inputting an original image into an electronic equipment identification model to identify target electronic equipment existing in the original image through the electronic equipment identification model;
Step 2, determining the target electronic equipment as a target protection object, and determining a second target area where the target protection object is located in the original image;
and step 3, desensitizing the second target area to obtain a desensitized image.
In the embodiment of the application, if the equipment protection mode is selected, the electronic equipment existing in the original image can be identified through the electronic equipment identification model, the position of the electronic equipment is further determined in the original image, and finally the desensitization treatment is carried out on the image content at the position.
In step S206, when the privacy protection mode is the intelligent protection mode, processing the original image according to the privacy protection mode to obtain the desensitized image includes:
step 1, inputting an original image into an intelligent recognition model to determine the confidence that each object in the original image belongs to a target protection object through the intelligent recognition model, wherein the intelligent recognition model is a neural network model obtained based on custom configuration training of the target protection object;
step 2, determining an object with the confidence reaching the target value as a target protection object, and determining a second target area where the target protection object is located in the original image;
And step 3, desensitizing the second target area to obtain a desensitized image.
In the embodiment of the application, if the intelligent protection mode is selected, each object existing in the original image can be identified through the intelligent identification model obtained by training based on the user-defined configuration in advance, and each object is scored, wherein the scoring value is the probability that the object belongs to the privacy content to be protected, namely the confidence level. And determining the object with the confidence reaching the target value as a target protection object, determining the position of the target protection object in the original image, and performing desensitization treatment on the image content at the position.
In the embodiment of the application, the model can be obtained based on yolo model training, and can also be used for object recognition by adopting other target recognition algorithms.
Because the security camera has basic traceability requirements, the photographed image needs to protect privacy and safety on the basis of meeting basic traceability conditions, and the area of the content needing privacy protection needs to be identified more accurately, so that modification to other content is reduced. Taking the equipment protection mode as an example, the display screen of the electronic product is ideally accurately identified, and only the area of the display screen is subjected to desensitization treatment. Based on this, the application proposes a method for accurately identifying the outline of the target protection object, specifically, determining the second target area where the target protection object is located in the original image includes:
Step 1, determining a local image which completely contains a target protection object in an original image;
step 2, carrying out Fourier transform on the local image to obtain a transformed image of the local image;
step 3, recognizing and dividing the outline of the target protection object in the transformed image;
step 4, determining a region surrounded by the outline of the target protection object as a second target region in the transformed image; alternatively, the transformed image is subjected to inverse fourier transform to determine the contour of the target protection object in the original partial image, and the region surrounded by the contour of the target protection object in the partial image is determined as the second target region.
In the embodiment of the application, the outline of the target protection object can be more accurately identified by carrying out Fourier transform on the local image of the original image. After the contour of the target protection object is identified, the contour can be marked on the transformed image to directly carry out the next processing, or the transformed image can be subjected to inverse Fourier transform to determine the contour of the target protection object in the original partial image, and then the contour is marked on the original image to enter the next processing.
In an alternative embodiment, desensitizing the second target area to obtain a desensitized image includes any of:
Firstly, frequency data of a second target area in the transformed image is subjected to frequency reduction so as to soften the second target area; and performing inverse Fourier transform to obtain a desensitized image.
In the embodiment of the application, the frequency domain of Fourier transformation can be processed, and the frequency data of 'outline' is subjected to frequency reduction, so that blurring and softening are performed, details are blurred, meanwhile, abrupt is reduced, and then the normal image data is recovered through Fourier transformation, so as to obtain a desensitized image.
Secondly, determining a third target area and a fourth target area adjacent to the second target area in the partial image, wherein the third target area and the fourth target area are distributed on different sides of the second target area; determining a first image feature of a third target region and a second image feature of a fourth target region; generating a target transition image from the third target region to a fourth target region based on the first image feature and the second image feature; and filling the second target area by using the target transition image to obtain a desensitized image.
In the embodiment of the present application, the third target area and the fourth target area may be front and rear areas, left and right areas, and the like, where the second target area is adjacent. And taking the third target area and the fourth target area as a starting image and an ending image, generating a series of transition images from the starting image to the ending image through an image processing algorithm, and further filling the second target area into the transition images so as to delete the target protection object on the image, and simultaneously enabling the desensitization image to be more natural.
Third, determining a fifth target area adjacent to the second target area and marked as a background in the partial image; extracting any subarea in the fifth target area as a filling template; and filling the second target area by using a filling template to obtain a desensitized image.
In the embodiment of the application, the background where the target protection object is located can be found out, and the target protection object is directly covered by using a background covering mode to obtain the desensitized image.
In step S206, when the privacy protection mode is the full protection mode, the processing of the original image according to the privacy protection mode further includes:
and deleting the original image, popping up a prompt popup window, and displaying prompt information for prohibiting shooting in the prompt popup window.
In the embodiment of the application, for the full protection mode of completely prohibiting shooting, the system needs to delete the original image and give prompt information of prohibiting shooting through a popup window.
In step S208, the finally output image is a desensitized image, and the original image is not saved and is not post-processed, so that the user privacy is protected from the source.
According to the application, the original image acquired by the camera is processed, so that the personal privacy can be effectively protected. According to different privacy protection modes, target protection objects in the image can be identified, so that desensitization processing is performed in a targeted manner, and the privacy protection effect is ensured. Meanwhile, the application adopts the image processing technology, can more automatically carry out privacy protection, does not greatly influence the usability of the image, and has practicability and feasibility.
The privacy protection method of the application can be applied to equipment such as public places, new energy vehicles and the like, and can also be applied to other places and equipment needing to protect personal privacy, such as markets, banks, hospitals and the like. In addition, the privacy protection method can be applied to a monitoring system to protect the privacy of the monitored image, so that the privacy of the monitored object is protected. Meanwhile, the privacy protection method can be applied to processing and analyzing the image data, and personal privacy in the image is protected, so that the safety and the privacy of the data are guaranteed.
The application can also be combined with artificial intelligence technology, and the accuracy and efficiency of privacy protection are improved through automatic learning and optimization of privacy protection modes. Meanwhile, the privacy protection method can be applied to the virtual reality technology to protect personal privacy in the virtual scene, so that the availability and safety of the virtual reality technology are improved.
The method and the device can also be applied to the online communication fields such as video conferences and the like, protect the privacy of the users and improve the safety of online communication. In addition, the method and the device can be applied to the fields of urban monitoring, traffic supervision and the like, personal privacy in the monitored image is protected, and safety and fairness of a monitoring system are improved.
The privacy protection method can also be applied to the fields of intelligent home furnishing and the like, the privacy of residents is protected, and the usability and safety of the intelligent home furnishing are improved. In addition, the application can be applied to the technologies such as face recognition and the like to protect personal privacy and improve the usability and safety of the face recognition technology.
The privacy preserving method of the present application may also be applied to the medical field. In the medical industry, doctors and nurses need to diagnose and treat patients by taking photographs or videos of the patients, but these photographs or videos may contain personal privacy information of the patients, such as facial features, body parts, etc. The privacy protection method provided by the application can protect personal privacy information in the photos or videos and ensure the privacy rights of patients.
The privacy protection method can also be applied to the field of security protection. The monitoring camera used in the security system may capture a picture containing personal privacy information, such as an identification card number, a bank card number, etc. The privacy protection method provided by the application can protect the personal privacy information in the pictures and ensure the privacy rights of citizens.
The privacy protection method of the application can also be applied to the field of electronic commerce. In electronic commerce, users need to input personal information and payment information to make purchases and payments, which may be obtained and illegally used by malicious third parties. The privacy protection method provided by the application can protect the personal information and payment information input by the user, and ensure the privacy and fund security of the user.
The privacy protection method can also be applied to the fields of intelligent equipment such as social media and toys. In social media, users upload their own personal photos and videos, which may be illegally acquired and used by others. In intelligent devices such as toys, information such as voice and video of a user may be illegally acquired and used. The privacy protection method provided by the application can protect the information and ensure the privacy and the safety of the user.
In a word, the privacy protection method provided by the application has wide application fields and prospects, can improve the value and the utilization efficiency of data while guaranteeing personal privacy in various fields, and creates a safer and more credible digital world.
According to still another aspect of an embodiment of the present application, as shown in fig. 3, there is provided a privacy protecting apparatus, including:
an image acquisition module 301, configured to acquire an original image acquired by an image acquisition device for a first target area;
a mode selection module 303, configured to determine a privacy protection mode that matches either the image capturing device or the first target area;
the desensitization processing module 305 is configured to process the original image according to the privacy protection mode to obtain a desensitized image;
a save output module 307 for deleting the original image and saving and outputting the desensitized image as a final image.
It should be noted that, the image acquiring module 301 in this embodiment may be used to perform step S202 in the embodiment of the present application, the mode selecting module 303 in this embodiment may be used to perform step S204 in the embodiment of the present application, the desensitizing processing module 305 in this embodiment may be used to perform step S206 in the embodiment of the present application, and the save output module 307 in this embodiment may be used to perform step S208 in the embodiment of the present application.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or hardware as a part of the apparatus in the hardware environment shown in fig. 1.
Optionally, the mode selection module is specifically configured to:
acquiring the equipment type of the image acquisition equipment, and determining a privacy protection mode corresponding to the equipment type;
acquiring the position information of a first target area, and determining a privacy protection mode corresponding to the position information;
receiving a privacy protection mode sent by a target server, wherein the target server is used for managing a target area;
the privacy protection mode comprises a portrait protection mode, a device protection mode, an intelligent protection mode and a complete protection mode.
Optionally, the desensitization processing module is specifically configured to:
inputting the original image into a human image recognition model to recognize a target human image existing in the original image through the human image recognition model;
determining a target portrait as a target protection object, and determining a second target area where the target protection object is located in the original image;
and (3) desensitizing the second target area to obtain a desensitized image.
Optionally, the desensitization processing module is specifically configured to:
inputting the original image into an electronic equipment identification model to identify target electronic equipment existing in the original image through the electronic equipment identification model;
determining target electronic equipment as a target protection object, and determining a second target area where the target protection object is located in an original image;
And (3) desensitizing the second target area to obtain a desensitized image.
Optionally, the desensitization processing module is specifically configured to:
inputting an original image into an intelligent recognition model to determine the confidence that each object in the original image belongs to a target protection object through the intelligent recognition model, wherein the intelligent recognition model is a neural network model obtained based on self-defined configuration training of the target protection object;
determining an object with the confidence reaching the target value as a target protection object, and determining a second target area where the target protection object is located in the original image;
and (3) desensitizing the second target area to obtain a desensitized image.
Optionally, the desensitization processing module further comprises a contour recognition unit, specifically configured to:
determining a local image which completely contains the target protection object in the original image;
performing Fourier transform on the local image to obtain a transformed image of the local image;
identifying and segmenting the outline of the target protection object in the transformed image;
determining a region surrounded by the outline of the target protection object as a second target region in the transformed image; or alternatively, the process may be performed,
the transformed image is subjected to inverse fourier transform to determine the contour of the target protection object in the original partial image, and a region surrounded by the contour of the target protection object in the partial image is determined as a second target region.
Optionally, the desensitization processing module further comprises a desensitization processing unit, specifically configured to:
down-converting frequency data of a second target area in the converted image to soften the second target area; performing inverse Fourier transform to obtain a desensitized image;
determining a third target area and a fourth target area adjacent to the second target area in the partial image, wherein the third target area and the fourth target area are distributed on different sides of the second target area; determining a first image feature of a third target region and a second image feature of a fourth target region; generating a target transition image from the third target region to a fourth target region based on the first image feature and the second image feature; filling a second target area by using the target transition image to obtain a desensitized image;
determining a fifth target region adjacent to the second target region and marked as background in the partial image; extracting any subarea in the fifth target area as a filling template; and filling the second target area by using a filling template to obtain a desensitized image.
Optionally, the desensitizing processing module is further configured to:
and deleting the original image, popping up a prompt popup window, and displaying prompt information for prohibiting shooting in the prompt popup window.
According to another aspect of the embodiments of the present application, as shown in fig. 4, the present application provides an electronic device, including a memory 401, a processor 403, a communication interface 405 and a communication bus 407, where the memory 401 stores a computer program that can be executed on the processor 403, and the memory 401 and the processor 403 communicate with each other through the communication interface 405 and the communication bus 407, and the processor 403 executes the steps of the method.
The memory and the processor in the electronic device communicate with the communication interface through a communication bus. The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The communication bus may be classified as an address bus, a data bus, a control bus, or the like.
The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
There is also provided, in accordance with yet another aspect of embodiments of the present application, a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of any of the embodiments described above.
Optionally, in an embodiment of the present application, the computer readable medium is arranged to store program code for the processor to:
acquiring an original image acquired by image acquisition equipment on a first target area;
determining a privacy protection mode matched with any one of the image acquisition device and the first target area;
processing the original image according to the privacy protection mode to obtain a desensitized image;
the original image is deleted and the desensitized image is saved and output as the final image.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
When the embodiment of the application is specifically implemented, the above embodiments can be referred to, and the application has corresponding technical effects.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (DSP devices, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc. It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a specific embodiment of the application to enable those skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A privacy preserving method, comprising:
acquiring an original image acquired by image acquisition equipment on a first target area;
determining a privacy protection mode matched with any one of the image acquisition device and the first target area;
processing the original image according to the privacy protection mode to obtain a desensitized image;
deleting the original image, and storing and outputting the desensitized image as a final image.
2. The method of claim 1, wherein the determining a privacy preserving pattern matching any of the image capturing device and the first target area comprises at least one of:
Acquiring the equipment type of the image acquisition equipment, and determining the privacy protection mode corresponding to the equipment type;
acquiring the position information of the first target area, and determining the privacy protection mode corresponding to the position information;
receiving the privacy protection mode sent by a target server, wherein the target server is used for managing the target area;
the privacy protection mode comprises a portrait protection mode, a device protection mode, an intelligent protection mode and a complete protection mode.
3. The method according to claim 2, wherein, in the case that the privacy preserving mode is the portrait preserving mode, the processing the original image according to the privacy preserving mode to obtain a desensitized image includes:
inputting the original image into a portrait identification model to identify a target portrait existing in the original image through the portrait identification model;
determining the target portrait as a target protection object, and determining a second target area where the target protection object is located in the original image;
and carrying out desensitization treatment on the second target area to obtain the desensitized image.
4. The method of claim 2, wherein, in the case where the privacy preserving mode is the device preserving mode, the processing the original image in the privacy preserving mode to obtain the desensitized image includes:
inputting the original image into an electronic equipment identification model to identify target electronic equipment existing in the original image through the electronic equipment identification model;
determining the target electronic equipment as a target protection object, and determining a second target area where the target protection object is located in the original image;
and carrying out desensitization treatment on the second target area to obtain the desensitized image.
5. The method according to claim 2, wherein, in the case that the privacy preserving mode is the intelligent preserving mode, the processing the original image according to the privacy preserving mode to obtain the desensitized image includes:
inputting the original image into an intelligent recognition model to determine the confidence that each object in the original image belongs to a target protection object through the intelligent recognition model, wherein the intelligent recognition model is a neural network model obtained based on custom configuration training of the target protection object;
Determining the object with the confidence reaching the target value as the target protection object, and determining a second target area where the target protection object is located in the original image;
and carrying out desensitization treatment on the second target area to obtain the desensitized image.
6. The method according to any one of claims 3 to 5, wherein determining a second target area in the original image where the target protection object is located includes:
determining a partial image completely containing the target protection object in the original image;
performing Fourier transform on the local image to obtain a transformed image of the local image;
identifying and segmenting the outline of the target protection object in the transformed image;
determining a region surrounded by the outline of the target protection object as the second target region in the transformation image; or alternatively, the process may be performed,
performing inverse fourier transform on the transformed image to determine a contour of the target protection object in the original partial image, and determining a region surrounded by the contour of the target protection object in the partial image as the second target region.
7. The method of claim 6, wherein desensitizing the second target area to obtain the desensitized image comprises any of:
Down-converting the frequency data of the second target area in the converted image to soften the second target area; performing inverse Fourier transform to obtain the desensitized image;
determining a third target area and a fourth target area adjacent to the second target area in the partial image, wherein the third target area and the fourth target area are distributed on different sides of the second target area; determining a first image feature of the third target region and a second image feature of the fourth target region; generating a target transition image from the third target region to the fourth target region based on the first image feature and the second image feature; filling the second target area by using the target transition image to obtain the desensitized image;
determining a fifth target region in the partial image adjacent to the second target region and marked as background; extracting any subarea in the fifth target area as a filling template; and filling the second target area by using the filling template to obtain the desensitized image.
8. The method according to claim 2, wherein, in the case where the privacy preserving mode is the full preserving mode, the processing the original image in the privacy preserving mode further includes:
And deleting the original image, popping up a prompt popup window, and displaying prompt information for prohibiting shooting in the prompt popup window.
9. A privacy preserving apparatus, comprising:
the image acquisition module is used for acquiring an original image acquired by the image acquisition equipment on the first target area;
a mode selection module, configured to determine a privacy protection mode that matches any of the image capturing device and the first target area;
the desensitization processing module is used for processing the original image according to the privacy protection mode to obtain a desensitized image;
and the storage output module is used for deleting the original image and storing and outputting the desensitized image as a final image.
10. An electronic device comprising a memory, a processor, a communication interface and a communication bus, said memory storing a computer program executable on said processor, said memory, said processor communicating with said communication interface via said communication bus, characterized in that said processor, when executing said computer program, implements the steps of the method of any of the preceding claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897947.6A CN116881967A (en) | 2023-07-20 | 2023-07-20 | Privacy protection method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897947.6A CN116881967A (en) | 2023-07-20 | 2023-07-20 | Privacy protection method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116881967A true CN116881967A (en) | 2023-10-13 |
Family
ID=88271184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310897947.6A Pending CN116881967A (en) | 2023-07-20 | 2023-07-20 | Privacy protection method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116881967A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455751A (en) * | 2023-12-22 | 2024-01-26 | 新华三网络信息安全软件有限公司 | Road section image processing system and method |
-
2023
- 2023-07-20 CN CN202310897947.6A patent/CN116881967A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455751A (en) * | 2023-12-22 | 2024-01-26 | 新华三网络信息安全软件有限公司 | Road section image processing system and method |
| CN117455751B (en) * | 2023-12-22 | 2024-03-26 | 新华三网络信息安全软件有限公司 | Road section image processing system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10936760B1 (en) | System and method for concealing sensitive data on a computing device | |
| CN107169458B (en) | Data processing method, device and storage medium | |
| US8761446B1 (en) | Object detection with false positive filtering | |
| Pang et al. | Classifying discriminative features for blur detection | |
| US9412017B1 (en) | Methods systems and computer program products for motion initiated document capture | |
| CN109815843B (en) | Image processing method and related product | |
| JP2020532802A (en) | Face unlocking method, information registration method and devices, devices and media | |
| JP7419080B2 (en) | computer systems and programs | |
| WO2018225775A1 (en) | Image masking device and image masking method | |
| CN116881967A (en) | Privacy protection method, device and equipment | |
| Li et al. | An accurate and efficient user authentication mechanism on smart glasses based on iris recognition | |
| CN112101200A (en) | Human face anti-recognition method, system, computer equipment and readable storage medium | |
| CN108776800B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN113177480A (en) | Financial business processing method, device, equipment and medium based on face recognition | |
| Dick | How to address privacy questions raised by the expansion of augmented reality in public spaces | |
| CN114861241A (en) | Anti-peeping screen method based on intelligent detection and related equipment thereof | |
| CN111666976A (en) | Feature fusion method and device based on attribute information and storage medium | |
| CN113642639B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| CN115147705B (en) | Face copying detection method and device, electronic equipment and storage medium | |
| CN113033243A (en) | Face recognition method, device and equipment | |
| CN108270973B (en) | Photographing processing method, mobile terminal and computer readable storage medium | |
| CN108875472B (en) | Image acquisition device and face identity verification method based on image acquisition device | |
| CN115222621A (en) | Image correction method, electronic device, storage medium, and computer program product | |
| CN111985305A (en) | Screen peeping prevention method and device and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |