CN105913374B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN105913374B CN105913374B CN201610213357.7A CN201610213357A CN105913374B CN 105913374 B CN105913374 B CN 105913374B CN 201610213357 A CN201610213357 A CN 201610213357A CN 105913374 B CN105913374 B CN 105913374B
- Authority
- CN
- China
- Prior art keywords
- colour
- skin color
- color value
- skin
- abnormal
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 136
- 238000001514 detection method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims 2
- 238000000034 method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000003796 beauty Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002087 whitening effect Effects 0.000 description 1
Classifications
-
- G06T3/04—
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of image processing method and devices.The method includes the steps: recognition of face is carried out to image, obtains human face region；Obtain each colour of skin color value of the human face region；Obtaining from each colour of skin color value has overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section；Abnormal area of skin color is obtained from the human face region, wherein the difference of the abnormal colour of skin color value of the color value and acquisition of the exception area of skin color is within a preset range；The colour of skin color value of adjacent area is filled to the abnormal area of skin color, wherein the adjacent area is less than pre-determined distance at a distance from the abnormal area of skin color.Since the present invention carries out desalt processing to the abnormal colour of skin before grinding skin, is not in skin blockiness when so carrying out subsequent mill skin, ensure that the beautiful Yan Xiaoguo of image, the image after mill skin is allowed to become naturally beautiful.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method, image processing apparatus.
Background technique
With the development of science and technology, especially self-timer is prevailing, U.S. face tool is more and more widely used the daily of people
In life.U.S. face tool can carry out whitening and mill skin processing to image, to obtain the preferable image of effect.But for skin
Matter is not particularly preferred user, such as when user has more whelk on the face, when carrying out mill skin using U.S. face tool, due to red
Will become after the whelk mill skin of color it is a piece of red, so the image after mill skin is it is possible that one piece of red one piece of white situation,
Influence the beautiful Yan Xiaoguo of image.
Summary of the invention
Based on this, it is necessary in view of the above-mentioned problems, provide a kind of image processing method and device, can to abnormal skin into
Row filtering, to obtain preferable image beauty Yan Xiaoguo.
In order to achieve the above object, the technical solution adopted by the present invention is as follows:
A kind of image processing method, comprising steps of
Recognition of face is carried out to image, obtains human face region；
Obtain each colour of skin color value of the human face region；
Obtaining from each colour of skin color value has overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section；
Abnormal area of skin color is obtained from the human face region, wherein the color value of the exception area of skin color and acquisition is different
The difference of normal colour of skin color value is within a preset range；
The colour of skin color value of adjacent area is filled to the abnormal area of skin color, wherein the adjacent area and the exception
The distance of area of skin color is less than pre-determined distance.
A kind of image processing apparatus, comprising:
Human face region obtains module, for carrying out recognition of face to image, obtains human face region；
Colour of skin color value obtains module, for obtaining each colour of skin color value of the human face region；
Abnormal colour of skin color value obtains module, has for obtaining from each colour of skin color value with preset abnormal colour of skin color value section
The abnormal colour of skin color value of overlapping；
Abnormal area of skin color obtains module, for obtaining abnormal area of skin color from the human face region, wherein described different
The difference of the abnormal colour of skin color value of the color value and acquisition of normal area of skin color is within a preset range；
Color value fills module, for filling the colour of skin color value of adjacent area to the abnormal area of skin color, wherein described
Adjacent area is less than pre-determined distance at a distance from the abnormal area of skin color.
Image processing method and device of the present invention are found different in human face region according to preset abnormal colour of skin color value section
Normal colour of skin color value, then determines the abnormal area of skin color in human face region according to abnormal colour of skin color value, finally by normal color
The mode for being worth filling carries out desalt processing to the colour of skin of abnormal area of skin color, to complete the unification of face complexion tone.Due to
The present invention carries out desalt processing to the abnormal colour of skin before grinding skin, so carrying out is not in that skin piecemeal is existing when subsequent mill skin
As ensure that the beautiful Yan Xiaoguo of image, the image after mill skin allowed to become naturally beautiful.
Detailed description of the invention
Fig. 1 is the flow diagram of image processing method embodiment of the present invention；
Fig. 2 is the structural schematic diagram of image processing apparatus embodiment one of the present invention；
Fig. 3 is the structural schematic diagram of image processing apparatus embodiment two of the present invention；
Fig. 4 is the structural schematic diagram of image processing apparatus embodiment three of the present invention；
Fig. 5 is the structural schematic diagram of image processing apparatus example IV of the present invention.
Specific embodiment
It is with reference to the accompanying drawing and preferably real for the effect for further illustrating technological means adopted by the present invention and acquirement
Example is applied, to technical solution of the present invention, carries out clear and complete description.
As shown in Figure 1, a kind of image processing method, comprising steps of
S110, recognition of face is carried out to image, obtains human face region；
S120, each colour of skin color value for obtaining the human face region；
S130, it is obtained from each colour of skin color value and has overlapping abnormal colour of skin color value with preset exception colour of skin color value section；
S140, abnormal area of skin color is obtained from the human face region, wherein the color value of the exception area of skin color with obtain
The difference of the abnormal colour of skin color value taken is within a preset range；
S150, the colour of skin color value of adjacent area is filled to the abnormal area of skin color, wherein the adjacent area and institute
The distance for stating abnormal area of skin color is less than pre-determined distance.
In step s 110, image can be the image in picture of finding a view when carrying out image taking using terminal, such as open
When opening the front camera of mobile phone and being taken pictures, the image shown in mobile phone screen is also possible to completed image, such as clap
Take the photograph the image of completion, the image of terminal itself storage or the image obtained from other equipment etc..People is obtained by recognition of face
The method in face region can be realized according to existing mode in the prior art.
In the step s 120, the mode for obtaining each colour of skin color value can be realized according to existing mode in the prior art.
In step s 130, preset abnormal colour of skin color value section can be red color value section, or black color
It is worth section etc., the present invention makes restriction not to this.
In view of some special situations, such as preset abnormal colour of skin color value section is black color value section, but is worked as
When user is black race, black is just no longer the abnormal colour of skin, does not need the processing for carrying out the abnormal colour of skin.So implementing at one
In example, after each colour of skin color value for obtaining the human face region, obtained from each colour of skin color value and preset abnormal colour of skin color value
Before there is the abnormal colour of skin color value of overlapping in section, can with comprising steps of
The maximum main colour of skin color value section of colour of skin area is determined according to each colour of skin color value；
Main colour of skin color value section is detected whether in abnormal colour of skin color value section；
The step of recognition of face is carried out to image, obtains human face region if so, returning；Otherwise enter from each colour of skin color value
Obtaining has the step of overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section.
The main colour of skin is the most important colour of skin in human face region.Such as the yellow of a long whelk on the face, it is main
The colour of skin be yellow.Main colour of skin color value section can be obtained according to colour circle in the prior art etc..If main colour of skin color value area
Between in abnormal colour of skin color value section, it is meant that user colour belongs to abnormal colour of skin scope, without subsequent processing.If main
Colour of skin color value section is had any different with abnormal colour of skin color value section, i.e. main colour of skin color value section is outside abnormal colour of skin color value section, meaning
Taste the main colour of skin of user have any different with the preset abnormal colour of skin, then need to carry out the detection of abnormal area of skin color, avoid shadow
There is a piece of red a piece of white situation after ringing the effect of U.S. face, such as mill skin.
After determining that the main colour of skin of user is not belonging to preset abnormal colour of skin scope, the colour of skin color value in human face region is carried out
The user colour section Chong Die with abnormal colour of skin color value is found in detection.It is true in view of image, in one embodiment, from
It is obtained in each colour of skin color value after having overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section, from the face area
Before obtaining abnormal area of skin color in domain, can with comprising steps of
Whether the quantity for detecting the abnormal colour of skin color value obtained is greater than preset threshold；
If so, otherwise returning into the step of obtaining abnormal area of skin color from the human face region and carrying out people to image
The step of face identification, acquisition human face region.
Preset threshold can need sets itself according to user.If the quantity of the abnormal colour of skin color value in human face region compared with
Few, then skin tone is more unified, without processing.If the quantity of the abnormal colour of skin color value in human face region is more, the colour of skin
Tone difference is more, needs to be implemented subsequent step.
In step S140, according to the abnormal colour of skin color value of acquisition, entire human face region is scanned, is found different in human face region
Normal colour of skin coordinate filters out exception area of skin color similar in color value and abnormal colour of skin color value.Color value it is close i.e. colour of skin color value with it is different
The difference of normal colour of skin color value is within a preset range.Preset range can need sets itself according to user.
In one embodiment, the area of the abnormal area of skin color is greater than preset area.Preset area can according to
Family needs sets itself.When the area of abnormal area of skin color is smaller, subsequent step is not executed.When the face of abnormal area of skin color
When product is larger, subsequent step is executed.
In step S150, after getting the abnormal area of skin color in human face region, abnormal area of skin color neighboring area is taken
Colour of skin color value replace the colour of skin color value of abnormal area of skin color, to carry out desalt processing to abnormal area of skin color, complete face
The unification of skin tone.
In one embodiment, the colour of skin color value of adjacent area is filled to the abnormal area of skin color, it can be with
Comprising steps of carrying out mill skin to the human face region, conventional mill skin is carried out for example, by using Gaussian Blur algorithm.Due to will be different
The phenomenon that normal colour of skin carries out desalt processing, is not in piecemeal when so carrying out mill skin at this time, image compares naturally, real after grinding skin
Preferable image beauty Yan Xiaoguo is showed.
Based on the same inventive concept, the present invention also provides a kind of image processing apparatus, fill with reference to the accompanying drawing to the present invention
The specific embodiment set is described in detail.
As shown in Fig. 2, a kind of image processing apparatus, comprising:
Human face region obtains module 110, for carrying out recognition of face to image, obtains human face region；
Colour of skin color value obtains module 120, for obtaining each colour of skin color value of the human face region；
Abnormal colour of skin color value obtains module 130, for obtaining from each colour of skin color value and preset abnormal colour of skin color value area
Between have the abnormal colour of skin color value of overlapping；
Abnormal area of skin color obtains module 140, for obtaining abnormal area of skin color from the human face region, wherein described
The difference of the abnormal colour of skin color value of the color value and acquisition of abnormal area of skin color is within a preset range；
Color value fills module 150, for filling the colour of skin color value of adjacent area to the abnormal area of skin color, wherein institute
It states adjacent area and is less than pre-determined distance at a distance from the abnormal area of skin color.
Human face region, which obtains the image that module 110 identifies, to be the image in picture of finding a view when carrying out image taking,
It can be completed image.Human face region obtains module 110 can basis by the method that recognition of face obtains human face region
Existing mode is realized in the prior art.The mode that colour of skin color value acquisition module 120 obtains each colour of skin color value can also be according to existing
There is existing mode in technology to realize.
Preset exception colour of skin color value section can be red color value section, or black color value section etc., this hair
It is bright that restriction is made not to this.In view of some special situations, such as preset abnormal colour of skin color value section is black color value
Section, but when user is black race, black is just no longer the abnormal colour of skin, does not need the processing for carrying out the abnormal colour of skin.So
In one embodiment, as shown in figure 3, apparatus of the present invention can also include be connected to the colour of skin color value obtain module 120 with
The exception colour of skin color value obtains the main skin tone detection module 160 between module 130, and the main skin tone detection module 160 is used for
The maximum main colour of skin color value section of colour of skin area is determined according to each colour of skin color value, whether detects main colour of skin color value section in abnormal skin
In color color value section.Main colour of skin color value section can be obtained according to colour circle in the prior art etc..
When main colour of skin color value section is in abnormal colour of skin color value section, the human face region obtains module 110 again to figure
As carrying out recognition of face, human face region is obtained.When main colour of skin color value section is outside abnormal colour of skin color value section, the exception colour of skin
Color value, which obtains module 130 and obtains from each colour of skin color value, has overlapping abnormal colour of skin color with preset abnormal colour of skin color value section
Value.
After determining that the main colour of skin of user is not belonging to preset abnormal colour of skin scope, it is right that abnormal colour of skin color value obtains module 130
Colour of skin color value in human face region is detected, and the user colour section Chong Die with abnormal colour of skin color value is found.In view of image
It is true, as shown in figure 4, in one embodiment, apparatus of the present invention can also include being connected to the abnormal colour of skin color value obtain
Modulus block 130 and the abnormal area of skin color obtain the abnormal colour of skin color value detection module 170 between module 140, the exception
Whether the quantity that colour of skin color value detection module 170 is used to detect the abnormal colour of skin color value obtained is greater than preset threshold.
When quantity is greater than preset threshold, the exception area of skin color acquisition module 140 obtains different from the human face region
Normal area of skin color.When quantity is less than or equal to preset threshold, the human face region obtains module 110 and carries out face knowledge to image again
Not, human face region is obtained.
Abnormal area of skin color obtains module 140 according to the abnormal colour of skin color value of acquisition, scans entire human face region, finds people
Abnormal colour of skin coordinate in face region filters out exception area of skin color similar in color value and abnormal colour of skin color value.The close i.e. skin of color value
The difference of color color value and abnormal colour of skin color value is within a preset range.Preset range can need sets itself according to user.
In one embodiment, the area of the abnormal area of skin color is greater than preset area.Preset area can according to
Family needs sets itself.
After getting the abnormal area of skin color in human face region, color value filling module 150 takes abnormal area of skin color peripheral region
The colour of skin color value in domain replaces the colour of skin color value of abnormal area of skin color, to carry out desalt processing to abnormal area of skin color, completes people
The unification of face skin tone.
In one embodiment, as shown in figure 5, apparatus of the present invention can also include filling 150 phase of module with the color value
Mill skin module 180 even, the mill skin module 180 are calculated for carrying out mill skin to the human face region for example, by using Gaussian Blur
Method carries out conventional mill skin.It is not in piecemeal when so carrying out mill skin at this time since the abnormal colour of skin is carried out desalt processing
The phenomenon that, image compares naturally, realizing preferable image beauty Yan Xiaoguo after grinding skin.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (12)
1. a kind of image processing method, which is characterized in that comprising steps of
Recognition of face is carried out to image, obtains human face region；
Obtain each colour of skin color value of the human face region；
Obtaining from each colour of skin color value has overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section；
Abnormal area of skin color is obtained from the human face region, wherein the exception color value of area of skin color and the abnormal skin of acquisition
The difference of color color value is within a preset range；
The colour of skin color value of adjacent area is filled to the abnormal area of skin color, wherein the adjacent area and the abnormal colour of skin
The distance in region is less than pre-determined distance；
Wherein, preset abnormal colour of skin color value section is red color value section or black color value section；
After each colour of skin color value for obtaining the human face region, obtained from each colour of skin color value and preset abnormal colour of skin color
Before there is the abnormal colour of skin color value of overlapping in value section, further comprise the steps of:
The maximum main colour of skin color value section of colour of skin area is determined according to each colour of skin color value；
If the main colour of skin color value section in abnormal colour of skin color value section, returns and carries out recognition of face to image, face is obtained
The step of region；Otherwise enter from each colour of skin color value to obtain and have the overlapping abnormal colour of skin with preset abnormal colour of skin color value section
The step of color value.
2. image processing method according to claim 1, which is characterized in that determine colour of skin area most according to each colour of skin color value
After big main colour of skin color value section, further comprise the steps of:
Main colour of skin color value section is detected whether in abnormal colour of skin color value section.
3. image processing method according to claim 1, which is characterized in that from each colour of skin color value obtain with it is preset different
After there is the abnormal colour of skin color value of overlapping in normal colour of skin color value section, before obtaining abnormal area of skin color in the human face region,
It further comprises the steps of:
Whether the quantity for detecting the abnormal colour of skin color value obtained is greater than preset threshold；
If so, otherwise returning into the step of obtaining abnormal area of skin color from the human face region and carrying out face knowledge to image
Not, the step of obtaining human face region.
4. image processing method according to claim 1, which is characterized in that the area of the exception area of skin color is greater than pre-
If area.
5. image processing method as claimed in any of claims 1 to 4, which is characterized in that by the skin of adjacent area
Color color value is filled to the abnormal area of skin color, is further comprised the steps of:
Mill skin is carried out to the human face region.
6. a kind of image processing apparatus characterized by comprising
Human face region obtains module, for carrying out recognition of face to image, obtains human face region；
Colour of skin color value obtains module, for obtaining each colour of skin color value of the human face region；
Abnormal colour of skin color value obtains module, for obtained from each colour of skin color value with preset exception colour of skin color value section have it is overlapping
Abnormal colour of skin color value；
Abnormal area of skin color obtains module, for obtaining abnormal area of skin color from the human face region, wherein the exception skin
The difference of the abnormal colour of skin color value of the color value and acquisition in color region is within a preset range；
Color value fills module, for filling the colour of skin color value of adjacent area to the abnormal area of skin color, wherein described adjacent
Region is less than pre-determined distance at a distance from the abnormal area of skin color；
Wherein, preset abnormal colour of skin color value section is red color value section or black color value section；
It further include being connected to the main colour of skin that the colour of skin color value obtains between module and the abnormal colour of skin color value acquisition module to examine
Module is surveyed, the main skin tone detection module is used to determine the maximum main colour of skin color value section of colour of skin area according to each colour of skin color value；
When main colour of skin color value section is in abnormal colour of skin color value section, the human face region obtains module and carries out people to image again
Face identification, obtains human face region；When main colour of skin color value section is outside abnormal colour of skin color value section, the exception colour of skin color value is obtained
Module is obtained from each colour of skin color value has overlapping abnormal colour of skin color value with preset abnormal colour of skin color value section.
7. image processing apparatus according to claim 6, which is characterized in that the main skin tone detection module is also used to detect
Whether main colour of skin color value section is in abnormal colour of skin color value section.
8. image processing apparatus according to claim 6, which is characterized in that further include being connected to the abnormal colour of skin color value
Obtain the abnormal colour of skin color value detection module between module and the abnormal area of skin color acquisition module, the exception colour of skin color value
Whether the quantity that detection module is used to detect the abnormal colour of skin color value obtained is greater than preset threshold；
When quantity is greater than preset threshold, the exception area of skin color obtains module and obtains abnormal colour of skin area from the human face region
Domain；When quantity is less than or equal to preset threshold, the human face region obtains module and carries out recognition of face to image again, obtains face
Region.
9. image processing apparatus according to claim 6, which is characterized in that the area of the exception area of skin color is greater than pre-
If area.
10. according to image processing apparatus described in claim 6 to 9 any one, which is characterized in that further include and the color value
The connected mill skin module of module is filled, the mill skin module is for carrying out mill skin to the human face region.
11. a kind of storage medium, is stored thereon with computer program, which is characterized in that can when described program is executed by processor
Realize the image processing method as described in any one of claims 1 to 5.
12. a kind of terminal device, including storage medium, processor and storage can be run on a storage medium and on a processor
Computer program, the processor realize the image processing method as described in any one of claims 1 to 5 when executing described program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610213357.7A CN105913374B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610213357.7A CN105913374B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105913374A CN105913374A (en) | 2016-08-31 |
| CN105913374B true CN105913374B (en) | 2019-08-16 |
Family
ID=56745727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610213357.7A Active CN105913374B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105913374B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392841B (en) * | 2017-06-16 | 2020-04-24 | Oppo广东移动通信有限公司 | Method and device for eliminating black eye in face area and terminal |
| CN107507128B (en) * | 2017-08-08 | 2021-02-09 | 北京小米移动软件有限公司 | Image processing method and apparatus |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102006421A (en) * | 2009-09-01 | 2011-04-06 | 华晶科技股份有限公司 | Processing method for image with face |
| CN103325089A (en) * | 2012-03-21 | 2013-09-25 | 腾讯科技（深圳）有限公司 | Method and device for processing skin color in image |
| CN103927718A (en) * | 2014-04-04 | 2014-07-16 | 北京金山网络科技有限公司 | Picture processing method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2115662B1 (en) * | 2007-02-28 | 2010-06-23 | Fotonation Vision Limited | Separating directional lighting variability in statistical face modelling based on texture space decomposition |
-
2016
- 2016-04-07 CN CN201610213357.7A patent/CN105913374B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102006421A (en) * | 2009-09-01 | 2011-04-06 | 华晶科技股份有限公司 | Processing method for image with face |
| CN103325089A (en) * | 2012-03-21 | 2013-09-25 | 腾讯科技（深圳）有限公司 | Method and device for processing skin color in image |
| CN103927718A (en) * | 2014-04-04 | 2014-07-16 | 北京金山网络科技有限公司 | Picture processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105913374A (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105243371B (en) | A kind of detection method, system and the camera terminal of face U.S. face degree | |
| TWI686774B (en) | Human face live detection method and device | |
| US8983152B2 (en) | Image masks for face-related selection and processing in images | |
| US11138695B2 (en) | Method and device for video processing, electronic device, and storage medium | |
| JP6287047B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| KR101662846B1 (en) | Apparatus and method for generating bokeh in out-of-focus shooting | |
| KR101554403B1 (en) | Image processing device, image processing method, and recording medium for control program | |
| WO2016180224A1 (en) | Method and device for processing image of person | |
| EP2962278B1 (en) | Multi-spectral imaging system for shadow detection and attenuation | |
| WO2015070723A1 (en) | Eye image processing method and apparatus | |
| WO2012036669A1 (en) | Smile detection systems and methods | |
| CN104966266A (en) | Method and system to automatically blur body part | |
| TWI731503B (en) | Live facial recognition system and method | |
| CN105787427B (en) | Lip region localization method | |
| CN111079688A (en) | Living body detection method based on infrared image in face recognition | |
| CN111259757B (en) | Living body identification method, device and equipment based on image | |
| Alabbasi et al. | Human face detection from images, based on skin color | |
| CN105913374B (en) | Image processing method and device | |
| KR101344851B1 (en) | Device and Method for Processing Image | |
| CN105447827A (en) | Image noise reduction method and system thereof | |
| Ma et al. | A face detection algorithm based on modified skin-color model | |
| Powar et al. | Skin detection for forensic investigation | |
| EP3273437A1 (en) | Method and device for enhancing readability of a display | |
| CN105160329B (en) | A kind of tooth recognition methods, system and camera terminal based on YUV color spaces | |
| US11779264B2 (en) | Dark circle detection and evaluation method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |