CN104966067A - Image processing method and system for protecting privacy - Google Patents
Image processing method and system for protecting privacy Download PDFInfo
- Publication number
- CN104966067A CN104966067A CN201510366888.5A CN201510366888A CN104966067A CN 104966067 A CN104966067 A CN 104966067A CN 201510366888 A CN201510366888 A CN 201510366888A CN 104966067 A CN104966067 A CN 104966067A
- Authority
- CN
- China
- Prior art keywords
- region
- privacy
- human face
- data frame
- image data
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Bioethics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses an image processing method and system for protecting the privacy. The method comprises: acquiring an image data frame by a camera; performing human face detection on the image data frame to obtain a human face region; and performing concealment processing on a region except the human face region. With the adoption of the manner, the privacy of a user except the human face region can be effectively protected.
Description
Technical field
The present invention relates to technical field of image processing, especially relate to a kind of image processing method and the system of protecting privacy.
Background technology
Current, camera head monitor is widely used in various occasion, but also Chang Yinwei privacy concern enjoys and denounces.Under some sight, need the compromise obtaining security and secret protection, such as, the lavatory of aide elderly service center, bathroom, household bedroom etc.
Along with the life idea of Smart Home is more and more universal, wired home security device also obtains the concern of more and more people, and more family selection has installed monitoring camera at home, and image is sent to the mobile phone of user by network.And when user is in time, also the moment monitors the every act and every move of user to camera, how to ensure the personal secrets of user, ensure that image information is not leaked on network, also become user to compare a problem of care.
Current family's monitoring camera technology relatively, as by after recognition of face, furthers camera lens, amplifies, only sees face position.Shortcoming is exactly, and in the time that the rear lens of recognition of face furthers, body part still can be uploaded up.Therefore, how camera can process the body part beyond face in real time and protect individual privacy to become one of important topic of indoor intelligent household camera in normal operating conditions.
Summary of the invention
Technical matters to be solved by this invention is: provide a kind of image processing method and the system of protecting privacy, realize user's face with the protection of exterior domain privacy.
In order to solve the problems of the technologies described above, the technical solution used in the present invention is: provide a kind of image processing method protecting privacy, comprising:
Camera obtains image data frame;
Face datection is carried out to described image data frame, obtains human face region;
Carry out hiding process to the region beyond human face region.
Wherein, carry out hiding the step processed to the region beyond human face region to be specially:
Obtain human face region center and area size;
With described regional center for benchmark, set the distance value relevant to described area size;
According to described distance value, the region controlled beyond to human face region carries out hiding process.
Wherein, with described regional center for benchmark, after setting the step of the distance value relevant to described area size, comprising:
According to described distance value, control human face region with the hiding process intensity of exterior domain.
Wherein, according to described distance value, control human face region and be specially with the step of the hiding process intensity of exterior domain:
Control human face region with the single intensity of the hiding process of exterior domain; Or
Control human face region with the mixing ratio intensity of the hiding process of exterior domain.
Wherein, carry out hiding being specially of process to the region beyond human face region:
Privacy places of human body detection is carried out to described image data frame, obtains privacy places region;
Described human face region is utilized to screen described privacy places region;
Carry out hiding process to described privacy places region.
Wherein, carry out privacy places of human body detection to described image data frame, the step obtaining privacy places region is specially:
Prepare privacy places picture training set in advance;
Described training set is utilized to obtain privacy places detecting device;
Utilize described detecting device scan image data frame, obtain privacy places region.
Wherein, utilize described detecting device scan image data frame, after obtaining the step in privacy places region, also comprise:
Retain the region overlapping with described privacy places region, delete the region beyond overlapping region; Or
Covert reason intensity is controlled in described privacy places region.
Wherein, camera also comprises after obtaining the step of image data frame:
Described image data frame is respectively divided into 3 regions by horizontal direction, vertical direction, extracts the pixel of 3% brightness before each region;
Calculate the brightness average of described pixel;
Judge whether described average is greater than 200;
If so, first set sorter is then used to carry out Face datection, the detection of head shoulder;
Otherwise, then the second cover sorter is used to carry out Face datection, the detection of head shoulder.
For solving the problem, the present invention also provides a kind of image processing system protecting privacy, comprising:
Camera, for obtaining image data frame;
Detection module, for carrying out Face datection to described image data frame, obtains human face region;
Processing module, hides process for carrying out the region beyond human face region.
Wherein, also comprise sorter, for carrying out Face datection, head shoulder detects.
Beneficial effect of the present invention is: the present invention obtains image data frame by camera; And carry out Face datection, obtain human face region; Carry out hiding process to the region beyond human face region.User can be effectively protected to remove face with the secret protection of exterior domain.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the inventive method embodiment one;
Fig. 2 is the schematic flow sheet of the inventive method embodiment two;
Fig. 3 is the schematic flow sheet of the inventive method embodiment three;
Fig. 4 is the schematic flow sheet of the inventive method embodiment four;
Fig. 5 is the structured flowchart of present system embodiment five;
Fig. 6 is the structured flowchart of present system embodiment six;
Fig. 7 is that the specific embodiment of the invention calculates schematic diagram one;
Fig. 8 is that the specific embodiment of the invention calculates schematic diagram two.
Embodiment
By describing technology contents of the present invention in detail, realized object and effect, accompanying drawing is coordinated to be explained below in conjunction with embodiment.
Please refer to Fig. 1, the inventive method embodiment one provides a kind of image processing method protecting privacy, comprises the steps:
S1: camera obtains image data frame;
S2: carry out Face datection to described image data frame, obtains human face region;
S3: carry out hiding process to the region beyond human face region.
Be different from prior art, the present invention obtains image data frame by camera; And carry out Face datection, obtain human face region; Carry out hiding process to the region beyond human face region.User can be effectively protected to remove face with the secret protection of exterior domain.
Wherein, as shown in Figure 2, on the basis of embodiment one, the embodiment of the present invention two, when performing step S3, is specially:
S31: obtain human face region center and area size;
S32: with described regional center for benchmark, sets the distance value relevant to described area size;
S33: according to described distance value, the region controlled beyond to human face region carries out hiding process.
Particularly, as shown in Figure 7, in acquisition human face region after image, carry out human face characteristic point demarcation, obtain eyes position and nose position.
Utilize eyes position and nose position to calculate, method is: connect eyes position and obtain line segment AB, make AB vertical line with nose and obtain line segment CD, C is intersection point.Detect AC, CB length, if these two length differences are apart within 10%, then establish the length * 2 of W=AB, otherwise, the length * 3 of W=CD is set.Should be understood that, those skilled in the art also can at face up and down, choose a most stable reference length W, i.e. human face region wide senior middle school smaller value W when tilting.
With human face region center for benchmark, point each in image is operated: if with distance between reference in 1.0*W to 2.5*W scope (or in 1.0*W to 3.5*W scope), then carry out hiding process to this pixel;
So just nature divides the region that may occur to conceal thorax abdomen, in like manner also can select with distance between reference in 2.7*W to 4*W scope (or in 3.7*W to 6*W scope), for hiding possible waist hip portion.
Said method can hide possible privacy area quickly and easily, reduces the loss of monitoring image information simultaneously.
As shown in Figure 8, as a preferred embodiment, when selecting the ratio of hidden area, also obtain by following manner:
After acquisition human face region, head shoulder is carried out to image data frame and detects, obtain and take on region to the end.
Wherein W1 is calculated to human face region, the calculating of method senior middle school as wide in above-mentioned human face region smaller value W;
Correct shoulder region calculates W2, and method is: straight-line detection is carried out in correct shoulder region, obtains nose section AB, W2=AB length/2; Merge W1, W2, method is: the mid point takeing on region common factor part with human face region and head makes vertical line CD to AB, and C is intersection point, detects AC, CB length, if hybrid parameter M=|AC-CB|/AB; W=M*W1+ (1-M) * W2 is set.
Recycling W is by the hidden area of method estimation above.
Shoulder length information adaptively according to the rotational case in head shoulder region, can join in reference length calculating, increases the reliability of reference length by the preferred embodiments of the present invention.The detection of head shoulder refers to head and the whole region of shoulder and provides rectangle frame.
Wherein in one embodiment, step S34 also can be used to replace step S33, that is:
S34: according to described distance value, controls human face region with the hiding process intensity of exterior domain.
Wherein, step S34 is specially:
S341: control human face region with the single intensity of the hiding process of exterior domain; Or
S342: control human face region with the mixing ratio intensity of the hiding process of exterior domain.
Particularly, if with distance between reference in 1.0*W to 2.5*W scope, be 100% intensity with distance 1.75*W, 1.0*W and 2.5*W place is 0%, and centre seamlessly transits.
Therefore can select single intensity, or the image after mosaic processing, with the mixing ratio of original image, such as, 100% intensity is the figure of complete mosaic processing, then 50% intensity is the image after the mosaic processing of 50%, with 50% original image and.Select mixing ratio intensity to be conducive to monitoring image and seem smoother attractive in appearance.
Wherein, as shown in Figure 3, on the basis of embodiment one, the embodiment of the present invention three, when performing step S3, is specially:
S35: carry out privacy places of human body detection to described image data frame, obtains privacy places region;
S36: utilize described human face region to screen described privacy places region;
S37: carry out hiding process to described privacy places region.
Wherein, step S35 is specially:
S351: prepare privacy places picture training set in advance;
S352: utilize described training set to obtain privacy places detecting device;
S353: utilize described detecting device scan image data frame, obtains privacy places region.
Wherein, after step S353, also comprise:
S354: retain the region overlapping with described privacy places region, deletes the region beyond overlapping region; Or
S355: control covert reason intensity in described privacy places region.
The embodiment of the present invention three kinds is very high to privacy places testing result false detection rate, can obtain the surveyed area of a lot of mistake, screen, can remove error result by the human face region testing result comparatively determined.
Wherein human-face detector in the similar prior art of privacy places detecting device, human face region is utilized to be similar with the hiding scheme processed in embodiment two to the concrete grammar that the result that privacy places of human body detects is screened, first possible privacy area is obtained, utilize this area information to adjust the result of privacy places detector acquisition, can step S354 be performed.
Or, also can be similar to the method controlling the intensity hiding process in embodiment two, higher-strength process be given to the results area falling into possibility privacy area, namely performs step S355.
Wherein, as shown in Figure 4, on the basis of embodiment one, the embodiment of the present invention four, after execution step S1, also comprises:
S11: described image data frame is respectively divided into 3 regions by horizontal direction, vertical direction, extracts the pixel of 3% brightness before each region;
S12: the brightness average calculating described pixel;
S13: judge whether described average is greater than 200;
If so, then step S14 is performed: use first set sorter to carry out Face datection, head shoulder detects;
Otherwise, then step S15 is performed: use the second cover sorter to carry out Face datection, the detection of head shoulder.
The computing method of use sorter are: carry out moving window process to image, use classifier calculated score, select wherein score the maximum to each window.First set sorter in the embodiment of the present invention can be cascade cascade classifier, and the second cover sorter can be svm Support Vector Machine sorter.
The embodiment of the present invention four is applicable to dim environment, particularly,
Training multiple Face datection, head to take on and detect sorter, for adapting to different illumination conditions, is that sorter is overlapped in training two in embodiments of the present invention;
Obtain after image data frame, image is divided into 3 regions by horizontal direction, extract the pixel of 3% brightness before each region; Again image is divided into 3 regions by vertical direction, extracts the pixel of 3% brightness before each region; Brightness average is asked by cumulative for these pixels.If this average >200, preferably 230, then select first set sorter, otherwise select the second cover sorter.
Wherein, by choosing front 3 ~ 5% pixels, get average brightness to carry out light-metering, but may in the nearer environment of adularescent ceramic tile, light source in toilet etc., this obtaining value method can cause concentrating and is taken at certain region, and cannot reflect global illumination situation.Therefore be divided into some regions, each region is got front 3% pixel and just can be scatter, and realizes the rationality of sample value, thus overcomes the problems referred to above.Subregion samples, when other concrete conditions, and the desirable pixel of front 5%.
As more in considered toilet white background, getting 200 is proper reference values, preferably 230, and good to the differentiation performance of illumination quality.Therefore the embodiment of the present invention four is by judging whether brightness average is greater than 200, carries out selecting two cover sorters; And carry out the subsequent operation such as Face datection, the detection of head shoulder with the sorter selected.
The method of selection sort device is, to overlap sorter compared with the image under dark situation and the training of image data set under normal circumstances two, when average is greater than threshold value (200 ~ 230), uses the sorter of training under normal circumstances, otherwise then select the sorter in darker situation.
The method of selection sort device can also be, image is divided into 3 regions by horizontal direction, and before extracting each region, the pixel of 3% brightness obtains average A1 ~ A3; Again image is divided into 3 regions by vertical direction, before extracting each region, the pixel of 3% brightness obtains average B1 ~ B3; Obtain 3*3=9 region so altogether, each region comprises Xa, Xb two averages.Carry out moving window on this basis, suppose that moving window major part is in region M, if Xa, Xb are all greater than 200, this window area is used to the sorter of training under normal circumstances, otherwise the sorter of training under selecting low-light conditions.
Wherein, the embodiment of the present invention five correspondence also provides a kind of image processing system 100 protecting privacy, comprising:
Camera 110, for obtaining image data frame;
Detection module 120, for carrying out Face datection to described image data frame, obtains human face region;
Processing module 130, hides process for carrying out the region beyond human face region.
Wherein, as shown in Figure 6, described in the embodiment of the present invention six, system 100 also comprises sorter 140, and for carrying out Face datection, head shoulder detects.
The foregoing is only embodiments of the invention; not thereby the scope of the claims of the present invention is limited; every equivalents utilizing instructions of the present invention and accompanying drawing content to do, or be directly or indirectly used in relevant technical field, be all in like manner included in scope of patent protection of the present invention.
Claims (10)
1. protect an image processing method for privacy, it is characterized in that, comprising:
Camera obtains image data frame;
Face datection is carried out to described image data frame, obtains human face region;
Carry out hiding process to the region beyond human face region.
2. protect the image processing method of privacy according to claim 1, it is characterized in that, the step region beyond human face region being carried out hiding to process is specially:
Obtain human face region center and area size;
With described regional center for benchmark, set the distance value relevant to described area size;
According to described distance value, the region controlled beyond to human face region carries out hiding process.
3. protect the image processing method of privacy according to claim 2, it is characterized in that, with described regional center for benchmark, after setting the step of the distance value relevant to described area size, comprising:
According to described distance value, control human face region with the hiding process intensity of exterior domain.
4. protect the image processing method of privacy according to claim 3, it is characterized in that, according to described distance value, control human face region and be specially with the step of the hiding process intensity of exterior domain:
Control human face region with the single intensity of the hiding process of exterior domain; Or
Control human face region with the mixing ratio intensity of the hiding process of exterior domain.
5. protect the image processing method of privacy according to claim 1, it is characterized in that, carry out hiding being specially of process to the region beyond human face region:
Privacy places of human body detection is carried out to described image data frame, obtains privacy places region;
Described human face region is utilized to screen described privacy places region;
Carry out hiding process to described privacy places region.
6. protect the image processing method of privacy according to claim 5, it is characterized in that, carry out privacy places of human body detection to described image data frame, the step obtaining privacy places region is specially:
Prepare privacy places picture training set in advance;
Described training set is utilized to obtain privacy places detecting device;
Utilize described detecting device scan image data frame, obtain privacy places region.
7. protect the image processing method of privacy according to claim 6, it is characterized in that, utilize described detecting device scan image data frame, after obtaining the step in privacy places region, also comprise:
Retain the region overlapping with described privacy places region, delete the region beyond overlapping region; Or
Covert reason intensity is controlled in described privacy places region.
8. protect the image processing method of privacy according to claim 1, it is characterized in that, camera also comprises after obtaining the step of image data frame:
Described image data frame is respectively divided into 3 regions by horizontal direction, vertical direction, extracts the pixel of 3% brightness before each region;
Calculate the brightness average of described pixel;
Judge whether described average is greater than 200;
If so, first set sorter is then used to carry out Face datection, the detection of head shoulder;
Otherwise, then the second cover sorter is used to carry out Face datection, the detection of head shoulder.
9. protect an image processing system for privacy, it is characterized in that, comprising:
Camera, for obtaining image data frame;
Detection module, for carrying out Face datection to described image data frame, obtains human face region;
Processing module, hides process for carrying out the region beyond human face region.
10. protect the image processing system of privacy according to claim 9, it is characterized in that, also comprise sorter, for carrying out Face datection, head shoulder detects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510366888.5A CN104966067B (en) | 2015-06-29 | 2015-06-29 | Protect the image processing method and system of privacy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510366888.5A CN104966067B (en) | 2015-06-29 | 2015-06-29 | Protect the image processing method and system of privacy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104966067A true CN104966067A (en) | 2015-10-07 |
| CN104966067B CN104966067B (en) | 2018-05-18 |
Family
ID=54220103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510366888.5A Active CN104966067B (en) | 2015-06-29 | 2015-06-29 | Protect the image processing method and system of privacy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104966067B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550592A (en) * | 2015-12-09 | 2016-05-04 | 上海斐讯数据通信技术有限公司 | Face image protection method and system and mobile terminal |
| CN107333055A (en) * | 2017-06-12 | 2017-11-07 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN107770443A (en) * | 2017-10-26 | 2018-03-06 | 努比亚技术有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| CN109035167A (en) * | 2018-07-17 | 2018-12-18 | 北京新唐思创教育科技有限公司 | Method, apparatus, equipment and the medium that multiple faces in image are handled |
| CN109145528A (en) * | 2018-08-01 | 2019-01-04 | 上海碳蓝网络科技有限公司 | A kind of calling hold-up interception method of mobile terminal and photographic device |
| WO2019109722A1 (en) * | 2017-12-06 | 2019-06-13 | 杭州海康威视数字技术股份有限公司 | Privacy shielding processing method, device, electronic apparatus, and storage medium |
| CN110084147A (en) * | 2019-04-04 | 2019-08-02 | 广州大学 | A kind of gender method for secret protection and system for recognition of face |
| CN110084143A (en) * | 2019-04-04 | 2019-08-02 | 广州大学 | A kind of emotional information guard method and system for recognition of face |
| CN110096955A (en) * | 2019-03-21 | 2019-08-06 | 北京迈格威科技有限公司 | Monitoring method, device, system and storage medium |
| CN110929287A (en) * | 2019-11-21 | 2020-03-27 | 深圳传音控股股份有限公司 | Picture processing method and device |
| CN111031348A (en) * | 2019-12-11 | 2020-04-17 | 浙江宇视科技有限公司 | Video scrambling method, device, server and storage medium |
| CN114048489A (en) * | 2021-09-01 | 2022-02-15 | 广东智媒云图科技股份有限公司 | Human body attribute data processing method and device based on privacy protection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767638A (en) * | 2005-11-30 | 2006-05-03 | 北京中星微电子有限公司 | Visible image monitoring method for protecting privacy right and its system |
| CN101510957A (en) * | 2008-02-15 | 2009-08-19 | 索尼株式会社 | Image processing device, camera device, communication system, image processing method, and program |
| CN102067175A (en) * | 2008-03-31 | 2011-05-18 | 谷歌公司 | Automatic face detection and identity masking in images, and applications thereof |
| US20110123076A1 (en) * | 2009-11-23 | 2011-05-26 | Electronics And Telecommunications Research Institute | Method and apparatus for detecting specific human body parts in image |
| CN104378542A (en) * | 2013-08-14 | 2015-02-25 | 腾讯科技（深圳）有限公司 | Media content processing method and device and terminal device |
-
2015
- 2015-06-29 CN CN201510366888.5A patent/CN104966067B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1767638A (en) * | 2005-11-30 | 2006-05-03 | 北京中星微电子有限公司 | Visible image monitoring method for protecting privacy right and its system |
| CN101510957A (en) * | 2008-02-15 | 2009-08-19 | 索尼株式会社 | Image processing device, camera device, communication system, image processing method, and program |
| CN102067175A (en) * | 2008-03-31 | 2011-05-18 | 谷歌公司 | Automatic face detection and identity masking in images, and applications thereof |
| US20110123076A1 (en) * | 2009-11-23 | 2011-05-26 | Electronics And Telecommunications Research Institute | Method and apparatus for detecting specific human body parts in image |
| CN104378542A (en) * | 2013-08-14 | 2015-02-25 | 腾讯科技（深圳）有限公司 | Media content processing method and device and terminal device |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550592B (en) * | 2015-12-09 | 2018-06-29 | 上海斐讯数据通信技术有限公司 | A kind of guard method of face picture, system and mobile terminal |
| CN105550592A (en) * | 2015-12-09 | 2016-05-04 | 上海斐讯数据通信技术有限公司 | Face image protection method and system and mobile terminal |
| CN107333055A (en) * | 2017-06-12 | 2017-11-07 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
| CN107770443A (en) * | 2017-10-26 | 2018-03-06 | 努比亚技术有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| WO2019109722A1 (en) * | 2017-12-06 | 2019-06-13 | 杭州海康威视数字技术股份有限公司 | Privacy shielding processing method, device, electronic apparatus, and storage medium |
| CN109035167B (en) * | 2018-07-17 | 2021-05-18 | 北京新唐思创教育科技有限公司 | Method, device, equipment and medium for processing multiple faces in image |
| CN109035167A (en) * | 2018-07-17 | 2018-12-18 | 北京新唐思创教育科技有限公司 | Method, apparatus, equipment and the medium that multiple faces in image are handled |
| CN109145528A (en) * | 2018-08-01 | 2019-01-04 | 上海碳蓝网络科技有限公司 | A kind of calling hold-up interception method of mobile terminal and photographic device |
| CN110096955A (en) * | 2019-03-21 | 2019-08-06 | 北京迈格威科技有限公司 | Monitoring method, device, system and storage medium |
| CN110084147A (en) * | 2019-04-04 | 2019-08-02 | 广州大学 | A kind of gender method for secret protection and system for recognition of face |
| CN110084143A (en) * | 2019-04-04 | 2019-08-02 | 广州大学 | A kind of emotional information guard method and system for recognition of face |
| CN110084143B (en) * | 2019-04-04 | 2021-09-28 | 广州大学 | Emotion information protection method and system for face recognition |
| CN110084147B (en) * | 2019-04-04 | 2021-09-28 | 广州大学 | Gender privacy protection method and system for face recognition |
| CN110929287A (en) * | 2019-11-21 | 2020-03-27 | 深圳传音控股股份有限公司 | Picture processing method and device |
| CN110929287B (en) * | 2019-11-21 | 2023-01-10 | 深圳传音控股股份有限公司 | Picture processing method and device |
| CN111031348A (en) * | 2019-12-11 | 2020-04-17 | 浙江宇视科技有限公司 | Video scrambling method, device, server and storage medium |
| CN111031348B (en) * | 2019-12-11 | 2022-03-15 | 浙江宇视科技有限公司 | Video scrambling method, device, server and storage medium |
| CN114048489A (en) * | 2021-09-01 | 2022-02-15 | 广东智媒云图科技股份有限公司 | Human body attribute data processing method and device based on privacy protection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104966067B (en) | 2018-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104966067A (en) | Image processing method and system for protecting privacy | |
| CN104834446B (en) | A kind of display screen multi-screen control method and system based on eyeball tracking technology | |
| WO2022052475A1 (en) | Image capture processing method, apparatus and device, storage medium, and program product | |
| KR100954835B1 (en) | System for extracting the face change of same person, and intelligent system using it | |
| CN104834901A (en) | Binocular stereo vision-based human face detection method, device and system | |
| CN111242025B (en) | Real-time action monitoring method based on YOLO | |
| CN103236249B (en) | The method and apparatus that display device regulates automatically | |
| CN103927520A (en) | Method for detecting human face under backlighting environment | |
| CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
| CN106941588B (en) | Data processing method and electronic equipment | |
| CN107547852A (en) | A kind of big data storage system | |
| CN107330370A (en) | A kind of brow furrows motion detection method and device and vivo identification method and system | |
| Husein et al. | Motion detect application with frame difference method on a surveillance camera | |
| CN109996379B (en) | Light control method and device | |
| CN110472574A (en) | A kind of nonstandard method, apparatus of detection dressing and system | |
| CN102737463A (en) | Monitoring and alarming system for indoor personnel intrusion based on intelligent video | |
| CN103049748A (en) | Behavior-monitoring method and behavior-monitoring system | |
| JPH1115979A (en) | Face detection and method and device for tracing face | |
| CN105549927B (en) | A kind of display methods and terminal | |
| CN102063753A (en) | Method for identification and statistic of visitors based on Internet of things | |
| CN106022283A (en) | Biometric identification method, biometric identification device and identification equipment | |
| CN107944424A (en) | Front end human image collecting and Multi-angle human are distributed as comparison method | |
| JP2001094968A (en) | Video processor | |
| CN106411670A (en) | Smart home system | |
| CN102567951A (en) | Binary image display technology for protecting user privacy in video monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |