CN105389801B - Character contour setting method, character image weakening method, system and camera terminal - Google Patents
Character contour setting method, character image weakening method, system and camera terminal Download PDFInfo
- Publication number
- CN105389801B CN105389801B CN201510682643.3A CN201510682643A CN105389801B CN 105389801 B CN105389801 B CN 105389801B CN 201510682643 A CN201510682643 A CN 201510682643A CN 105389801 B CN105389801 B CN 105389801B
- Authority
- CN
- China
- Prior art keywords
- region
- contour
- character
- character contour
- head
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of character contour setting methods, character image weakening method, system and camera terminal, it to pending image by carrying out Face datection, obtain human face region, and contouring head region is calculated according to the human face region, combine the intrinsic ratio and slope on body and head that body contour region is calculated in the contouring head region, whole character contour region is finally obtained according to the contouring head region and the body contour region, to realize intelligent recognition character contour, further to carry out virtualization processing to the background area other than the character contour region, without manually smearing and selection region, user experience is more preferable.
Description
Technical field
The present invention relates to technical field of image processing, especially a kind of character contour setting method, character image virtualization side
The system of method and its application this method, camera terminal.
Background technology
In the prior art, we often blur background to protrude personage, still when handling character image
The prior art is all the region for needing user smear or specify manually virtualization, or the fixed character contour of setting
Character contour information in image is compared template with the character contour template of setting, to obtain non-personage profile region
Domain, then virtualization processing is carried out to non-personage's contour area.The method for specifying virtualization region manually for user, not only effect is not
It is good, and the time for spending user more is needed, user experience is bad;For using character contour template, need by outside
Reference, operation is more cumbersome, and needs to provide enough character contour templates and carry out selecting suitable template for user, still
Needing user to participate in selection can realize, not enough automation and intelligence, user experience is bad.Therefore, how intelligently to set
Setting character contour then becomes the key blurred in treatment technology.
Invention content
The present invention is to solve the above problems, provide a kind of character contour setting method, character image weakening method, system
And camera terminal, the method based on Face datection, using obtained human face region calculate corresponding contouring head region and
Body contour region is smeared to obtain whole character contour region without auxiliary manually, realizes intelligent recognition personage wheel
Exterior feature, user experience are more preferable.
To achieve the above object, the technical solution adopted by the present invention is:
First, the present invention provides a kind of character contour setting method comprising following steps:
10. a pair pending image carries out Face datection, human face region is obtained;
20. calculating contouring head region according to the human face region;
30. the contouring head region to be combined to the intrinsic ratio and slope of body and head, body wheel is calculated
Wide region;
40. according to the contouring head region and the body contour region, whole character contour region is obtained.
Preferably, contouring head region is calculated according to the human face region in the step 20, further comprised:
21. calculating facial contour region according to the human face region;
It is calculated 22. the facial contour region described in pair carries out outside extension, obtains contouring head region.
Preferably, contouring head region is calculated according to the human face region in the step 20, is by presetting institute
The corresponding facial contour region of human face region stated or the contouring head region are elliptical region, first according to described
Human face region calculates the elliptical center point and two ellipse radiis of the elliptical region, and ellipse according to the elliptical center point and two
The elliptical region is calculated to get to the facial contour region or the contouring head area in radius of circle
Domain.
Preferably, the intrinsic ratio of the body in the step 30 and head, is by collecting different building shape in advance
The body of character contour and the intrinsic ratio on head, and choose when calculating body contour region the wheel of the personage in pending image
The intrinsic ratio of wide corresponding body and head;Or by directly measure the body of the character contour in pending image with
The height dimension and width dimensions on head, to obtain the body of the character contour in pending image and the intrinsic ratio on head
Example.
Preferably, the slope of the body in the step 30 and head is shoulder area and neck regions using body
The slope of obtained two straight lines in domain, the two lines are all the neck area by the same point, and from the neck regions
The point in domain extends to the shoulder area of both sides respectively, the slope of two shoulders of the slope representative figure of the two lines.
Preferably, the point of the neck area uses the central point of the lowermost position of the human face region, from this
Central point extends to obtain two straight lines respectively to the shoulder area of both sides, and the lower zone which forms is body region
Domain, be calculated according to the body region and in conjunction with the intrinsic ratio of the contouring head region and body and head described in
Body contour region.
Preferably, it is obtained according to the contouring head region and the body contour region in the step 40 whole
The character contour region of body, further comprises:
41. obtaining preliminary character contour region according to the contouring head region and the body contour region;
It is calculated 42. the preliminary character contour region described in pair carries out outside extension, obtains final character contour region.
Preferably, outside extension is carried out to the preliminary character contour region in the step 42 to be calculated most
Whole character contour region, mainly calculate all pixels point of the background area other than the preliminary character contour region with
The shortest distance in the preliminary character contour region, and the pixel by the shortest distance less than preset extended range is set as transition
Final character contour region is calculated according to the preliminary character contour region and the transitional region for region.
Also, the present invention also provides a kind of character image weakening methods, according to character contour described in any one of the above embodiments
The character contour region that setting method obtains carries out virtualization processing to the background area other than personage's contour area.
Preferably, the character contour region further comprises preliminary character contour region and transitional region, further includes
Transition virtualization processing is carried out to the transitional region.
Secondly, the present invention also provides a kind of character contours, and system is arranged comprising:
Face detection module obtains human face region for carrying out Face datection to pending image;
Contouring head computing module, for calculating contouring head region according to the human face region;
Body contour computing module, intrinsic ratio for the contouring head region to be combined to body and head and oblique
Body contour region is calculated in rate;
Character contour computing module, for according to the contouring head region and the body contour region, obtaining
Whole character contour region.
Moreover, the present invention also provides a kind of character images to blur system comprising:
System is arranged in character contour, for personage to be calculated according to character contour setting method described in any one of the above embodiments
Contour area;
Processing system is blurred, for carrying out virtualization processing to the background area other than personage's contour area.
In addition, the present invention also provides a kind of camera terminals comprising the described character contour setting system and/or described
Character image blurs system.
Preferably, the camera terminal includes:Mobile phone, digital camera or tablet computer.
The beneficial effects of the invention are as follows:
A kind of character contour setting method, character image weakening method, system and the camera terminal of the present invention, by right
Pending image carries out Face datection, human face region is obtained, and calculate contouring head region according to the human face region, by institute
The contouring head region stated combines the intrinsic ratio and slope on body and head that body contour region is calculated, finally according to institute
The contouring head region and the body contour region stated obtain whole character contour region, to realize intelligent recognition people
Object profile is smeared further to carry out virtualization processing to the background area other than the character contour region without artificial
And selection region, user experience are more preferable.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and constitutes the part of the present invention, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings:
Fig. 1 is the general flow chart of character contour setting method of the present invention;
Fig. 2 is the general flow chart of the present inventor's object image weakening method;
Fig. 3 is the structural schematic diagram of camera terminal of the present invention;
Fig. 4 is the pending image of a specific embodiment of the invention;
Fig. 5 is the corresponding character contour figures of Fig. 4.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.It should be appreciated that specific embodiment described herein is only solving
The present invention is released, is not intended to limit the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained under the premise of creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, a kind of character contour setting method of the present invention comprising following steps:
10. a pair pending image carries out Face datection, human face region is obtained;
20. calculating contouring head region according to the human face region;
30. the contouring head region to be combined to the intrinsic ratio and slope of body and head, body wheel is calculated
Wide region;
40. according to the contouring head region and the body contour region, whole character contour region is obtained.
Contouring head region is calculated according to the human face region in the step 20, is further comprised:
21. calculating facial contour region according to the human face region;
It is calculated 22. the facial contour region described in pair carries out outside extension, obtains contouring head region.
Contouring head region is calculated according to the human face region in the step 20, is by presetting the face
The corresponding facial contour region in region or the contouring head region are elliptical region, first according to the human face region
The elliptical center point and two ellipse radiis of the elliptical region are calculated, and according to the elliptical center point and two ellipse radii meters
It calculates and obtains the elliptical region to get to the facial contour region or the contouring head region.Practical meter
During calculation, facial contour region can first be calculated according to above-mentioned oval computational methods, then carry out to facial contour region
Outside extension calculates, and obtains contouring head region;Alternatively, can also directly be calculated according to above-mentioned oval computational methods
To contouring head region, the only difference in ellipse radii value.
The intrinsic ratio of body and head in the step 30 is the character contour by collecting different building shape in advance
Body and head intrinsic ratio, and the character contour chosen in pending image when calculating body contour region is corresponding
Body and head intrinsic ratio;Or by directly measuring the body of the character contour in pending image and the height on head
Size and width dimensions are spent, to obtain the body of the character contour in pending image and the intrinsic ratio on head.
The slope of body and head in the step 30 is using obtained by the shoulder area of body and neck area
Two straight lines slope, which is all the neck area by the same point, and from the point minute of the neck area
Do not extend to the shoulder area of both sides, the slope of two shoulders of the slope representative figure of the two lines.The present embodiment, for letter
Change and calculate, the point of the neck area uses the central point of the lowermost position of the human face region, from the central point point
Not extending to obtain two straight lines to the shoulder area of both sides, the lower zone which forms is body region, according to
The body is simultaneously calculated in conjunction with the intrinsic ratio of the contouring head region and body and head for the body region
Contour area.The present embodiment assists calculating body contour region using the slope of shoulder, locating speed faster, alternatively, the shoulder
Wing slope can also be measured by pre-setting fixed value without manual intervention;Alternatively, it is also possible to as desired by other bodies
Body region auxiliary calculates.
Whole people is obtained according to the contouring head region and the body contour region in the step 40
Object contour area, further comprises:
41. obtaining preliminary character contour region according to the contouring head region and the body contour region;
It is calculated 42. the preliminary character contour region described in pair carries out outside extension, obtains final character contour region.
Wherein, outside extension is carried out to the preliminary character contour region in the step 42 to be calculated finally
Character contour region, mainly calculate all pixels point of the background area other than the preliminary character contour region with should
The shortest distance in preliminary character contour region, and the pixel by the shortest distance less than preset extended range is set as transition region
Final character contour region is calculated according to the preliminary character contour region and the transitional region for domain.
As shown in Figure 4 and Figure 5, if the shortest distance of pixel is more than preset extended range, which belongs to
Absolute non-personage's contour area, as background area, and it is set to the black region of virtualization processing masking-out;Correspondingly,
The character contour region is set as the white area of virtualization processing masking-out;If the shortest distance of pixel is less than or waits
In preset extended range, then the pixel belongs to transitional region, and the face in the virtualization processing masking-out corresponding to the pixel
Color value is:
Color=minlength*255/length;
Wherein, Color is the color value in the corresponding virtualization processing masking-out of pixel;Minlength is the shortest distance;
Length is preset extended range.
As shown in Fig. 2, the present invention also provides a kind of character image weakening methods, according to personage described in any one of the above embodiments
The character contour region that profile setting method obtains, other than still further comprising step 50. to the character contour region
Background area carries out virtualization processing.
In the present embodiment, the character contour region further comprises preliminary character contour region and transitional region, also
Including carrying out transition virtualization processing to the transitional region.
As shown in figure 3, the present invention also provides a kind of camera terminal, which includes that character contour as described below is set
System 100 is set, alternatively, further including character image virtualization system 300 as described below, the realization with embodiment of the method above-mentioned
Principle is similar with technique effect, may refer to the related record in above-described embodiment in detail, details are not described herein again.
In the present embodiment, character contour setting system 100 includes:
Face detection module 101 obtains human face region for carrying out Face datection to pending image;
Contouring head computing module 102, for calculating contouring head region according to the human face region;
Body contour computing module 103, the intrinsic ratio for the contouring head region to be combined to body and head
And slope, body contour region is calculated;
Character contour computing module 104, for according to the contouring head region and the body contour region, obtaining
To whole character contour region.
In the present embodiment, character image virtualization system 300 includes:
System 100 is arranged in character contour, for being calculated according to character contour setting method described in any one of the above embodiments
Character contour region;
Processing system 200 is blurred, for carrying out virtualization processing to the background area other than personage's contour area.
In addition, the present invention also provides a kind of camera terminals comprising the described character contour setting system and/or described
Character image blurs system.
The camera terminal includes:The equipment that mobile phone, digital camera or tablet computer etc. are configured with camera.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment weight
Point explanation is all difference from other examples, and the same or similar parts between the embodiments can be referred to each other.
For system embodiment and terminal embodiment, since it is basically similar to the method embodiment, so description is fairly simple,
The relevent part can refer to the partial explaination of embodiments of method.Also, herein, the terms "include", "comprise" or its
What his variant is intended to non-exclusive inclusion, so that including the processes of a series of elements, method, article or setting
Standby includes not only those elements, but also includes other elements that are not explicitly listed, or further includes for this process, side
Method, article or the intrinsic element of equipment.In the absence of more restrictions, limited by sentence "including a ..."
Element, it is not excluded that there is also other identical elements in the process, method, article or apparatus that includes the element.Separately
Outside, one of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can be by hardware come complete
At relevant hardware can also being instructed to complete by program, the program can be stored in a kind of computer-readable storage
In medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The preferred embodiment of the present invention has shown and described in above description, it should be understood that the present invention is not limited to this paper institutes
The form of disclosure is not to be taken as excluding other embodiments, and can be used for other combinations, modifications, and environments, and energy
Enough in this paper invented the scope of the idea, modifications can be made through the above teachings or related fields of technology or knowledge.And people from this field
The modifications and changes that member is carried out do not depart from the spirit and scope of the present invention, then all should be in the protection of appended claims of the present invention
In range.
Claims (13)
1. a kind of character contour setting method, which is characterized in that include the following steps:
10. a pair pending image carries out Face datection, human face region is obtained;
20. calculating contouring head region according to the human face region;
30. the contouring head region to be combined to the intrinsic ratio and slope of body and head, body contour area is calculated
Domain;
40. according to the contouring head region and the body contour region, whole character contour region is obtained;
Wherein, the slope of the body in the step 30 and head is using obtained by the shoulder area of body and neck area
The slope of two straight lines arrived, the two lines are all the neck area by the same point, and from the point of the neck area
Extend respectively to the shoulder area of both sides, the slope of two shoulders of the slope representative figure of the two lines.
2. a kind of character contour setting method according to claim 1, it is characterised in that:According to institute in the step 20
The human face region stated calculates contouring head region, further comprises:
21. calculating facial contour region according to the human face region;
It is calculated 22. the facial contour region described in pair carries out outside extension, obtains contouring head region.
3. a kind of character contour setting method according to claim 1 or 2, it is characterised in that:Root in the step 20
Calculate contouring head region according to the human face region, be by preset the corresponding facial contour region of human face region or
Contouring head region described in person is elliptical region, in the first ellipse for calculating the elliptical region according to the human face region
Heart point and two ellipse radiis, and the elliptical region is calculated according to the elliptical center point and two ellipse radiis,
Obtain the facial contour region or the contouring head region.
4. a kind of character contour setting method according to claim 1, it is characterised in that:Body in the step 30
It is the body of the character contour by collecting different building shape in advance and the intrinsic ratio on head with the intrinsic ratio on head, and
The intrinsic ratio of the corresponding body of character contour and head in pending image is chosen when calculating body contour region;Or
By directly measuring the body of the character contour in pending image and the height dimension on head and width dimensions, to be waited for
Handle the intrinsic ratio of the body and head of the character contour in image.
5. a kind of character contour setting method according to claim 1, it is characterised in that:The point of the neck area is adopted
With the central point of the lowermost position of the human face region, extend to obtain two to the shoulder area of both sides respectively from the central point
Straight line, the lower zone which forms is body region, is taken turns according to the body region and in conjunction with the head
The body contour region is calculated in the intrinsic ratio on wide region and body and head.
6. a kind of character contour setting method according to claim 1, it is characterised in that:According to institute in the step 40
The contouring head region and the body contour region stated obtain whole character contour region, further comprise:
41. obtaining preliminary character contour region according to the contouring head region and the body contour region;
It is calculated 42. the preliminary character contour region described in pair carries out outside extension, obtains final character contour region.
7. a kind of character contour setting method according to claim 6, it is characterised in that:To described in the step 42
Preliminary character contour region carry out outside extension final character contour region be calculated, mainly calculate described first
The shortest distance of all pixels point and the preliminary character contour region of the background area other than character contour region is walked, and will most
The pixel that short distance is less than preset extended range is set as transitional region, according to the preliminary character contour region and institute
Final character contour region is calculated in the transitional region stated.
8. a kind of character image weakening method, which is characterized in that it is according to described in any one of described claim 1 to 7
The character contour region that character contour setting method obtains carries out at virtualization the background area other than personage's contour area
Reason.
9. a kind of character image weakening method according to claim 8, which is characterized in that the character contour region into
One step includes preliminary character contour region and transitional region, further includes carrying out transition virtualization processing to the transitional region.
10. system is arranged in a kind of character contour, which is characterized in that including:
Face detection module obtains human face region for carrying out Face datection to pending image;
Contouring head computing module, for calculating contouring head region according to the human face region;
Body contour computing module, intrinsic ratio and slope for the contouring head region to be combined to body and head,
Body contour region is calculated;
Character contour computing module, for according to the contouring head region and the body contour region, obtaining entirety
Character contour region;
Wherein, the slope of the body and head in the body contour computing module is the shoulder area using body and neck
The slope of obtained two straight lines in portion region, the two lines are all the neck area by the same point, and from the neck
The point in portion region extends to the shoulder area of both sides respectively, the slope of two shoulders of the slope representative figure of the two lines.
11. a kind of character image blurs system, which is characterized in that including:
System is arranged in character contour, for the character contour setting method according to any one of described claim 1 to 7
Character contour region is calculated;
Processing system is blurred, for carrying out virtualization processing to the background area other than personage's contour area.
12. a kind of camera terminal, which is characterized in that system and/or right is arranged including character contour according to any one of claims 10
It is required that the character image described in 11 blurs system.
13. camera terminal according to claim 12, which is characterized in that the camera terminal includes:Mobile phone, digital camera
Or tablet computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510682643.3A CN105389801B (en) | 2015-10-20 | 2015-10-20 | Character contour setting method, character image weakening method, system and camera terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510682643.3A CN105389801B (en) | 2015-10-20 | 2015-10-20 | Character contour setting method, character image weakening method, system and camera terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105389801A CN105389801A (en) | 2016-03-09 |
CN105389801B true CN105389801B (en) | 2018-09-21 |
Family
ID=55422050
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510682643.3A Active CN105389801B (en) | 2015-10-20 | 2015-10-20 | Character contour setting method, character image weakening method, system and camera terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105389801B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107038681B (en) * | 2017-05-31 | 2020-01-10 | Oppo广东移动通信有限公司 | Image blurring method and device, computer readable storage medium and computer device |
CN107194363B (en) * | 2017-05-31 | 2020-02-04 | Oppo广东移动通信有限公司 | Image saturation processing method and device, storage medium and computer equipment |
CN107704798B (en) * | 2017-08-09 | 2020-06-12 | Oppo广东移动通信有限公司 | Image blurring method and device, computer readable storage medium and computer device |
CN108009577A (en) * | 2017-11-29 | 2018-05-08 | 南京工业大学 | A kind of implementation method of virtual mirror |
CN107948517B (en) | 2017-11-30 | 2020-05-15 | Oppo广东移动通信有限公司 | Preview picture blurring processing method, device and equipment |
CN108537165A (en) * | 2018-04-08 | 2018-09-14 | 百度在线网络技术(北京)有限公司 | Method and apparatus for determining information |
CN108989839A (en) * | 2018-08-27 | 2018-12-11 | 深圳艺达文化传媒有限公司 | The leading role's selection method and Related product of promotion video |
CN114430495A (en) * | 2022-01-12 | 2022-05-03 | 广州繁星互娱信息科技有限公司 | Object display method and device, storage medium and electronic equipment |
CN115359194B (en) * | 2022-10-20 | 2023-03-14 | 北京百度网讯科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
CN115457644B (en) * | 2022-11-10 | 2023-04-28 | 成都智元汇信息技术股份有限公司 | Picture identification method and device for obtaining target based on expansion space mapping |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751405A (en) * | 2015-03-11 | 2015-07-01 | 百度在线网络技术(北京)有限公司 | Method and device for blurring image |
CN104899575A (en) * | 2015-06-19 | 2015-09-09 | 南京大学 | Human body assembly dividing method based on face detection and key point positioning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4889538B2 (en) * | 2007-03-27 | 2012-03-07 | 三洋電機株式会社 | Image processing device |
-
2015
- 2015-10-20 CN CN201510682643.3A patent/CN105389801B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751405A (en) * | 2015-03-11 | 2015-07-01 | 百度在线网络技术(北京)有限公司 | Method and device for blurring image |
CN104899575A (en) * | 2015-06-19 | 2015-09-09 | 南京大学 | Human body assembly dividing method based on face detection and key point positioning |
Non-Patent Citations (1)
Title |
---|
面向不同距离的实时人体检测与跟踪系统;苑洋等;《模式识别与人工智能》;20141031;第27卷(第10期);939-945 * |
Also Published As
Publication number | Publication date |
---|---|
CN105389801A (en) | 2016-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105389801B (en) | Character contour setting method, character image weakening method, system and camera terminal | |
CN105243371B (en) | A kind of detection method, system and the camera terminal of face U.S. face degree | |
CN105205779B (en) | A kind of eyes image processing method, system and camera terminal based on anamorphose | |
CN107154030A (en) | Image processing method and device, electronic equipment and storage medium | |
CN109858466A (en) | A kind of face critical point detection method and device based on convolutional neural networks | |
CN107798318A (en) | The method and its device of a kind of happy micro- expression of robot identification face | |
CN105117705B (en) | A kind of iris image quality tandem type evaluation method | |
CN102567716B (en) | Face synthetic system and implementation method | |
JP6694465B2 (en) | Display method and electronic device for recommending eyebrow shape | |
CN102930278A (en) | Human eye sight estimation method and device | |
CN103914699A (en) | Automatic lip gloss image enhancement method based on color space | |
CN108197534A (en) | A kind of head part's attitude detecting method, electronic equipment and storage medium | |
CN104680121A (en) | Method and device for processing face image | |
CN104850847B (en) | Image optimization system and method with automatic thin face function | |
CN106447720A (en) | Method for constructing golden-ratio face | |
CN105608448A (en) | LBP characteristic extraction method based on face key points and LBP characteristic extraction device based on face key points | |
CN110348496A (en) | A kind of method and system of facial image fusion | |
CN104574285A (en) | Method for automatically removing image black eyes | |
CN105069745A (en) | face-changing system based on common image sensor and enhanced augmented reality technology and method | |
WO2020252969A1 (en) | Eye key point labeling method and apparatus, and training method and apparatus for eye key point detection model | |
CN110866139A (en) | Cosmetic treatment method, device and equipment | |
CN107274437A (en) | A kind of visual tracking method based on convolutional neural networks | |
CN109117717A (en) | A kind of city pedestrian detection method | |
CN107274452A (en) | A kind of small pox automatic testing method | |
CN112633288A (en) | Face sketch generation method based on drawing stroke guidance |
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 |