CN105913389B - Image processing method and device during skin abnormality - Google Patents
Image processing method and device during skin abnormality Download PDFInfo
- Publication number
- CN105913389B CN105913389B CN201610213335.0A CN201610213335A CN105913389B CN 105913389 B CN105913389 B CN 105913389B CN 201610213335 A CN201610213335 A CN 201610213335A CN 105913389 B CN105913389 B CN 105913389B
- Authority
- CN
- China
- Prior art keywords
- skin
- area
- abnormal
- processing method
- information
- 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.)
- Expired - Fee Related
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 42
- 208000006981 Skin Abnormalities Diseases 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 93
- 238000000034 method Methods 0.000 claims abstract description 8
- 208000003351 Melanosis Diseases 0.000 claims description 29
- 206010015150 Erythema Diseases 0.000 claims description 27
- 231100000321 erythema Toxicity 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 10
- 208000024891 symptom Diseases 0.000 abstract description 8
- 210000001061 forehead Anatomy 0.000 description 12
- 230000000694 effects Effects 0.000 description 5
- 230000037311 normal skin Effects 0.000 description 5
- 230000000717 retained effect Effects 0.000 description 5
- 210000000216 zygoma Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001815 facial effect Effects 0.000 description 4
- 235000015123 black coffee Nutrition 0.000 description 3
- 235000013353 coffee beverage Nutrition 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 241000287127 Passeridae Species 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000036074 healthy skin Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention relates to the image processing method and device during a kind of skin abnormality.The method includes the steps：Identification of Images is carried out to picture, obtains portrait area；According to each sub-regions of default feature database, the portrait area is divided into each pending area, wherein default feature database is stored with the information for each abnormal skin characteristic that each sub-regions include, and processing method corresponding with each exception skin characteristic；The information for each abnormal skin characteristic that skin characteristic information in each pending area is included with corresponding subregion respectively is compared, and obtains the abnormal skin feature that each pending area includes；According to the corresponding processing method of each exception skin characteristic, the abnormal skin feature that each pending area includes is handled accordingly.The present invention carries out landscaping treatment for different skin symptoms, allows skin U.S. face to be more nearly nature.
Description
Technical field
The present invention relates to technical field of image processing, image processing method, skin during more particularly to a kind of skin abnormality
Picture processing unit when skin is abnormal.
Background technology
With the development of science and technology, U.S. face instrument is increasingly prevailing, more and more people are when taking pictures, the especially skin of user
When there are abnormal conditions, such as there are whelk or freckle etc. on the face, picture is beautified using U.S. face instrument, so as to obtain skin
The picture of color exquisiteness.But when skin has abnormal, existing U.S.'s face method is that whole facial zone is carried out at Gaussian Blur
Reason, the picture after processing is more false, less natural.In addition, if the red that user occurs on the face is that the ruddy colour of skin is either " high
It is former red " when, Gaussian Blur processing is carried out to whole facial zone can not retain user's healthy Skin Color Information in itself, make processing
Picture afterwards is untrue.
The content of the invention
Based on this, it is necessary in view of the above-mentioned problems, image processing method and device when a kind of skin abnormality is provided, can
Subregion carries out landscaping treatment for different skin symptoms, so that skin U.S. face more natural reality.
In order to achieve the above object, the technical solution that the present invention takes is as follows：
A kind of image processing method during skin abnormality, including step：
Identification of Images is carried out to picture, obtains portrait area；
According to each sub-regions of default feature database, the portrait area is divided into each pending area, wherein in advance
If feature database is stored with the information for each abnormal skin characteristic that each sub-regions include, and corresponding with each abnormal skin characteristic
Processing method；
Each abnormal skin that skin characteristic information in each pending area is included with corresponding subregion respectively is special
The information of sign is compared, and obtains the abnormal skin feature that each pending area includes；
According to the corresponding processing method of each abnormal skin characteristic, the abnormal skin feature included to each pending area into
The corresponding processing of row.
A kind of picture processing unit during skin abnormality, including：
Portrait area acquisition module, for carrying out Identification of Images to picture, obtains portrait area；
Portrait area division module, for each sub-regions according to default feature database, the portrait area is divided into
Each pending area, wherein default feature database is stored with the information for each abnormal skin characteristic that each sub-regions include, and
Processing method corresponding with each exception skin characteristic；
Abnormal skin feature acquisition module, for by the skin characteristic information in each pending area respectively with it is corresponding
The information for each abnormal skin characteristic that subregion includes is compared, and it is special to obtain the abnormal skin that each pending area includes
Sign；
Abnormal skin feature processing block, for according to the corresponding processing method of each exception skin characteristic, waiting to locate to each
The abnormal skin feature that reason region includes is handled accordingly.
Image processing method and device during skin abnormality of the present invention, for the regularity of skin symptom region, with
And the image feature information of skin symptom, establish the correspondences of each sub-regions and the information of each abnormal skin characteristic, and pin
Corresponding U.S. face method is set respectively to each abnormal skin feature, so as to construct default feature database.Need to picture into
During row U.S. face, first the human face region of picture is divided, obtains each pending area, for each pending area,
By being matched with the abnormal skin characteristic information of respective sub-areas in default feature database, the exception included in pending area is detected
Skin characteristic, is then handled each abnormal skin feature of acquisition according to default processing method accordingly.The present invention
Consider the region that skin typical problem occurs, and in the different feature of face, carried out for different skin symptom subregions
Landscaping treatment, allows skin U.S. face to be more nearly nature；Normal skin tone and different can effectively be distinguished according to abnormal skin characteristic information
The normal colour of skin, such as " plateau is red " symptom and erythema, only carry out landscaping treatment to abnormal skin feature, retain the normal skin of user
Feature, makes picture more true nature.
Brief description of the drawings
The flow diagram of image processing method embodiment when Fig. 1 is skin abnormality of the present invention；
The structure diagram of picture processing unit embodiment one when Fig. 2 is skin abnormality of the present invention；
The structure diagram of picture processing unit embodiment two when Fig. 3 is skin abnormality of the present invention；
Fig. 4 is the structure diagram of side face detection module embodiment of the present invention.
Embodiment
It is below in conjunction with the accompanying drawings and preferably real further to illustrate the effect of the technological means of the invention taken and acquirement
Example is applied, to technical scheme, carries out clear and complete description.
As shown in Figure 1, image processing method during a kind of skin abnormality, including step：
S110, carry out Identification of Images to picture, obtains portrait area；
S120, each sub-regions according to default feature database, each pending area is divided into by the portrait area, its
In preset the information that feature database is stored with each abnormal skin characteristic that each sub-regions include, and with each abnormal skin characteristic pair
The processing method answered；
S130, each abnormal skin for including the skin characteristic information in each pending area with corresponding subregion respectively
The information of skin feature is compared, and obtains the abnormal skin feature that each pending area includes；
S140, according to the corresponding processing method of each abnormal skin characteristic, the abnormal skin included to each pending area
Feature is handled accordingly.
In step s 110, picture can be the picture in picture of finding a view when carrying out image taking, such as open mobile phone
When front camera is taken pictures, the picture or completed picture that are shown in mobile phone screen, such as shooting completion
The picture that picture, terminal itself store or the picture from other equipment acquisition etc..Portrait area is obtained by Identification of Images
Method can be realized according to existing mode in the prior art.
In one embodiment, Identification of Images is carried out to picture, after obtaining portrait area, according to each of default feature database
Sub-regions, before the portrait area is divided into each pending area, can also include step：
Obtain the eye information and bridge of the nose information in the portrait area；
Side face angle is obtained according to the angle of eyes and the bridge of the nose；
Detect whether the side face angle is more than predetermined angle；
The step of carrying out Identification of Images if so, returning to picture, obtain portrait area, otherwise enters according to default feature database
Each sub-regions, the step of portrait area is divided into each pending area.
Obtaining the eye information in portrait area and bridge of the nose information can realize according to existing mode in the prior art.Such as
Fruit, which is detected in portrait area, two eyes, then the angle of the line between two eyes and the bridge of the nose can be used to know side face
Angle.If detecting in portrait area there are an eyes, the angle of this eyes and bridge of the nose detection side face angle can be utilized.
Predetermined angle can be configured according to actual conditions.
In the step s 120, abnormal skin feature is to be different from the feature of normal skin, such as freckle, erythema etc..For
It can be levied with subregion dtex and picture is handled, the present invention needs to pre-set feature database.
Consider the regularity that abnormal skin feature occurs in skin area, each abnormal skin for setting each sub-regions to include
Skin feature, for example, freckle is generally present near cheekbone, either red point is generally present in chin or forehead nearby etc. to erythema
Deng.
In order to correctly identify abnormal skin feature, such as distinguish the normal ruddy and erythema of skin, it is also necessary to
The information of each abnormal skin feature is set, if a certain skin characteristic information meets the information of corresponding abnormal skin feature,
It can then determine occur the abnormal skin feature in the skin.
In one embodiment, the information of each abnormal skin characteristic can include each abnormal skin characteristic colour section,
The distance between the magnitude range and adjacent same abnormal skin feature of each exception skin characteristic size etc..For example, facial cheekbone
Bone near zone includes freckle, and the information of freckle includes：Colour is black-coffee color (correspondence RGB scopes), freckle size model
Enclose, the quantifiable data such as the distance between adjacent freckle.When being subsequently detected pending area, wait to locate if detected
The skin characteristic information of reason region septum reset cheekbone near zone meets each condition of freckle, then is assured that facial cheekbone
There is freckle in bone near zone.User can also set the other information of abnormal skin feature, and the present invention is done not to this
Go out to limit.
In order to carry out respective handling for different abnormal skin features, it is also necessary to set the place of each abnormal skin feature
Reason method.The processing method implementation of each abnormal skin feature has many kinds.For example, in one embodiment, each exception
Skin characteristic includes freckle, and processing method corresponding with the freckle includes：Remove black rgb value.The colour of freckle for black-
Coffee color, removes black rgb value, retains the rgb value of coffee color, you can to realize the beautification to freckle, that is, desalinates the freckle, again
The skin detail of user can be retained, obtain more real U.S. face effect.In another embodiment, each abnormal skin characteristic bag
Erythema is included, processing method corresponding with the erythema includes：Remove the colour more than predetermined threshold value.The colour of erythema is also certain
Colour section, remove higher colour in erythema, retain colour relatively low in erythema, can equally desalinate the erythema, again
The skin detail of user can be retained, obtain more real U.S. face effect.
According to above-mentioned design, user can also be according to the processing method for being actually needed the other abnormal skin features of setting, this
Invention no longer carries out example one by one.
In order to subsequently can accurately detect the abnormal skin feature included in each pending area, to portrait area
When being divided, portrait area can be divided accordingly according to the region division rule in default feature database.After division
Each pending area it is corresponding with the subregion in default feature database.
In step s 130, the exception by the skin characteristic information of each pending area with corresponding subregion respectively
Skin characteristic information is matched.For example, forehead region includes freckle and erythema in default feature database, by pending area
The skin characteristic information in forehead region is matched with the information of the freckle that forehead region includes in default feature database, if matching
Unanimously, then confirm that the forehead region in pending area includes freckle；By the skin characteristic in the forehead region in pending area
Information is matched with the information of the erythema that forehead region includes in default feature database, finds the forehead region in pending area
There is no the information that any skin characteristic information meets erythema, then confirm that the forehead region in pending area does not include erythema.That
Obtained result is exactly that the forehead region in pending area includes freckle.
In step S140, according to the corresponding processing method of each exception skin characteristic of default feature library storage, to each
The abnormal skin feature that pending area includes is beautified accordingly.For example, the forehead region in pending area includes sparrow
Spot, then remove the black rgb value in the freckle.
Based on same inventive concept, the present invention also provides picture processing unit during a kind of skin abnormality, with reference to attached
Figure is described in detail the embodiment of apparatus of the present invention.
As shown in Fig. 2, picture processing unit during a kind of skin abnormality, including：
Portrait area acquisition module 110, for carrying out Identification of Images to picture, obtains portrait area；
Portrait area division module 120, for each sub-regions according to default feature database, the portrait area is divided
For each pending area, wherein default feature database is stored with the information for each abnormal skin characteristic that each sub-regions include, with
And processing method corresponding with each exception skin characteristic；
Abnormal skin feature acquisition module 130, for by the skin characteristic information in each pending area respectively with it is right
The information for each abnormal skin characteristic that the subregion answered includes is compared, and obtains the abnormal skin that each pending area includes
Feature；
Abnormal skin feature processing block 140, for according to the corresponding processing method of each exception skin characteristic, being treated to each
The abnormal skin feature that processing region includes is handled accordingly.
The picture that portrait area acquisition module 110 identifies can be the picture in picture of finding a view when carrying out image taking,
It can be completed picture.The method that portrait area acquisition module 110 obtains portrait area by Identification of Images can basis
Existing mode is realized in the prior art.
In one embodiment, as shown in figure 3, apparatus of the present invention can also include being connected to the portrait area acquisition mould
Side face detection module 150 between block 110 and the portrait area division module 120.As shown in figure 4, the side face detection mould
Block 150 can include：
Eyes and bridge of the nose information acquisition unit 1501, for obtaining eye information and bridge of the nose letter in the portrait area
Breath；
Side face angle obtainment unit 1502, for obtaining side face angle according to the angle of eyes and the bridge of the nose；
Side face angle detection unit 1503, for detecting whether the side face angle is more than predetermined angle.
The portrait area acquisition module 110 carries out portrait knowledge to picture again when side face angle is more than predetermined angle
Not, portrait area is obtained.The portrait area division module 120 is when side face angle is less than or equal to predetermined angle, according to default
Each sub-regions of feature database, each pending area is divided into by the portrait area.
Eyes and bridge of the nose information acquisition unit 1501 obtain eye information in portrait area and bridge of the nose information can basis
Existing mode is realized in the prior art.If detecting in portrait area has two eyes, side face angle obtainment unit 1502
The angle of the line between two eyes and the bridge of the nose can be used to know side face angle.If detecting in portrait area has one
Eyes, side face angle obtainment unit 1502 can utilize the angle of this eyes and bridge of the nose detection side face angle.Predetermined angle can
To be configured according to actual conditions.
Consider the regularity that abnormal skin feature occurs in skin area, each abnormal skin for setting each sub-regions to include
Skin feature, for example, freckle is generally present near cheekbone, either red point is generally present in chin or forehead nearby etc. to erythema
Deng.
In order to correctly identify abnormal skin feature, such as distinguish the normal ruddy and erythema of skin, it is also necessary to
The information of each abnormal skin feature is set.In one embodiment, the information of each abnormal skin characteristic can include each exception
The distance between the colour section of skin characteristic, the magnitude range of each abnormal skin characteristic and adjacent same abnormal skin feature
Size etc..User can also set the other information of abnormal skin feature, and the present invention makes restriction not to this.
In order to carry out respective handling for different abnormal skin features, it is also necessary to set the place of each abnormal skin feature
Reason method.The processing method implementation of each abnormal skin feature has many kinds.For example, in one embodiment, each exception
Skin characteristic includes freckle, and processing method corresponding with the freckle includes：Remove black rgb value.The colour of freckle for black-
Coffee color, removes black rgb value, retains the rgb value of coffee color, you can to realize the beautification to freckle, that is, desalinates the freckle, again
The skin detail of user can be retained, obtain more real U.S. face effect.In another embodiment, each abnormal skin characteristic bag
Erythema is included, processing method corresponding with the erythema includes：Remove the colour more than predetermined threshold value.The colour of erythema is also certain
Colour section, remove higher colour in erythema, retain colour relatively low in erythema, can equally desalinate the erythema, again
The skin detail of user can be retained, obtain more real U.S. face effect.According to the design, user can also be according to actual needs
The processing method of other abnormal skin features is set, and the present invention no longer carries out example one by one.
After setting each above- mentioned information, default feature database is just constructed.Then using the default feature database to each figure
Piece is handled.
In order to subsequently can accurately detect the abnormal skin feature included in each pending area, portrait area division
Module 120 can carry out portrait area according to the region division rule in default feature when being divided to portrait area
Corresponding division.Each pending area after division is corresponding with the subregion in default feature database.Abnormal skin feature obtains
Module 130 respectively by the abnormal skin characteristic information of the skin characteristic information of each pending area and corresponding subregion into
Row matching, obtains the abnormal skin feature that each pending area includes.Then abnormal skin feature processing block 140 is according to pre-
If the corresponding processing method of each exception skin characteristic of feature library storage, the abnormal skin feature included to each pending area
Beautified accordingly.
The present invention considers the region that skin typical problem occurs, and in the different feature of face, for different skin
Symptom subregion carries out landscaping treatment, allows skin U.S. face to be more nearly nature.In addition, the present invention is according to abnormal skin characteristic information
Normal skin tone and the abnormal colour of skin, such as " plateau is red " symptom and erythema can be effectively distinguished, only abnormal skin feature is carried out beautiful
Change is handled, and is retained the normal skin feature of user, is made picture more true nature.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply 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, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, its description is more specific and detailed, but simultaneously
Cannot therefore it be construed as limiting the scope of the patent.It should be pointed out that come for those of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. image processing method during a kind of skin abnormality, it is characterised in that including step：
Identification of Images is carried out to picture, obtains portrait area；
According to each sub-regions of default feature database, the portrait area is divided into each pending area, wherein default spy
Sign stock contains the information for each abnormal skin characteristic that each subregion includes, and processing corresponding with each exception skin characteristic
Method；
Each abnormal skin characteristic that skin characteristic information in each pending area is included with corresponding subregion respectively
Information is compared, and obtains the abnormal skin feature that each pending area includes；
According to the corresponding processing method of each exception skin characteristic, the abnormal skin feature included to each pending area carries out phase
The processing answered.
2. image processing method during skin abnormality according to claim 1, it is characterised in that each exception skin characteristic
Information includes the different often colour section of skin characteristic, the magnitude range of each abnormal skin characteristic and adjacent same abnormal skin
The distance between feature size.
3. image processing method during skin abnormality according to claim 1, it is characterised in that each exception skin characteristic bag
Freckle is included, processing method corresponding with the freckle includes：Remove black rgb value.
4. image processing method during skin abnormality according to claim 1, it is characterised in that each exception skin characteristic bag
Erythema is included, processing method corresponding with the erythema includes：Remove the colour more than predetermined threshold value.
5. image processing method during skin abnormality according to any one of claims 1 to 4, it is characterised in that to figure
Piece carries out Identification of Images, and after obtaining portrait area, according to each sub-regions of default feature database, the portrait area is divided
Before each pending area, step is further included：
Obtain the eye information and bridge of the nose information in the portrait area；
Side face angle is obtained according to the angle of eyes and the bridge of the nose；
Detect whether the side face angle is more than predetermined angle；
The step of carrying out Identification of Images if so, returning to picture, obtain portrait area, otherwise enters according to each of default feature database
Sub-regions, the step of portrait area is divided into each pending area.
A kind of 6. picture processing unit during skin abnormality, it is characterised in that including：
Portrait area acquisition module, for carrying out Identification of Images to picture, obtains portrait area；
Portrait area division module, for each sub-regions according to default feature database, the portrait area is divided into each
Pending area, wherein default feature database is stored with the information for each abnormal skin characteristic that each sub-regions include, and with it is each
The corresponding processing method of abnormal skin feature；
Abnormal skin feature acquisition module, for by the skin characteristic information in each pending area respectively with corresponding sub-district
The information for each abnormal skin characteristic that domain includes is compared, and obtains the abnormal skin feature that each pending area includes；
Abnormal skin feature processing block, for according to the corresponding processing method of each abnormal skin characteristic, to each pending district
The abnormal skin feature that domain includes is handled accordingly.
7. picture processing unit during skin abnormality according to claim 6, it is characterised in that each exception skin characteristic
Information includes the different often colour section of skin characteristic, the magnitude range of each abnormal skin characteristic and adjacent same abnormal skin
The distance between feature size.
8. picture processing unit during skin abnormality according to claim 6, it is characterised in that each exception skin characteristic bag
Freckle is included, processing method corresponding with the freckle includes：Remove black rgb value.
9. picture processing unit during skin abnormality according to claim 6, it is characterised in that each exception skin characteristic bag
Erythema is included, processing method corresponding with the erythema includes：Remove the colour more than predetermined threshold value.
10. picture processing unit during skin abnormality according to claim 6 to 9 any one, it is characterised in that also wrap
Include the side face detection module being connected between the portrait area acquisition module and the portrait area division module, the side face
Detection module includes：Eyes and bridge of the nose information acquisition unit, for obtaining eye information and bridge of the nose letter in the portrait area
Breath；Side face angle obtainment unit, for obtaining side face angle according to the angle of eyes and the bridge of the nose；Side face angle detection unit, is used
Whether it is more than predetermined angle in the detection side face angle；
The portrait area acquisition module carries out Identification of Images to picture again when side face angle is more than predetermined angle, obtains
Portrait area；The portrait area division module is when side face angle is less than or equal to predetermined angle, according to each of default feature database
Sub-regions, each pending area is divided into by the portrait area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610213335.0A CN105913389B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device during skin abnormality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610213335.0A CN105913389B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device during skin abnormality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105913389A CN105913389A (en) | 2016-08-31 |
| CN105913389B true CN105913389B (en) | 2018-05-04 |
Family
ID=56745743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610213335.0A Expired - Fee Related CN105913389B (en) | 2016-04-07 | 2016-04-07 | Image processing method and device during skin abnormality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105913389B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106713700A (en) * | 2016-12-08 | 2017-05-24 | 宇龙计算机通信科技(深圳)有限公司 | Picture processing method and apparatus, as well as terminal |
| CN108229389A (en) * | 2017-12-29 | 2018-06-29 | 努比亚技术有限公司 | Facial image processing method, apparatus and computer readable storage medium |
| CN108647566B (en) * | 2018-03-29 | 2021-01-08 | 维沃移动通信有限公司 | Method and terminal for identifying skin characteristics |
| CN109325907B (en) * | 2018-09-18 | 2023-07-04 | 北京旷视科技有限公司 | Image beautifying processing method, device and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426652A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Traditional Chinese medicine face color identifying and retrieving method based on image analysis |
| KR20120042101A (en) * | 2010-10-22 | 2012-05-03 | 한국전자통신연구원 | Apparatus and method for extraction of face feature |
| CN103425985A (en) * | 2013-08-28 | 2013-12-04 | 山东大学 | Method for detecting forehead wrinkles on face |
| CN103456010A (en) * | 2013-09-02 | 2013-12-18 | 电子科技大学 | Human face cartoon generation method based on feature point localization |
| CN104732214A (en) * | 2015-03-24 | 2015-06-24 | 吴亮 | Quantification skin detecting method based on face image recognition |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3872778B2 (en) * | 2002-07-15 | 2007-01-24 | 三星電子株式会社 | Face search method and apparatus using combined component descriptors |
-
2016
- 2016-04-07 CN CN201610213335.0A patent/CN105913389B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120042101A (en) * | 2010-10-22 | 2012-05-03 | 한국전자통신연구원 | Apparatus and method for extraction of face feature |
| CN102426652A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Traditional Chinese medicine face color identifying and retrieving method based on image analysis |
| CN103425985A (en) * | 2013-08-28 | 2013-12-04 | 山东大学 | Method for detecting forehead wrinkles on face |
| CN103456010A (en) * | 2013-09-02 | 2013-12-18 | 电子科技大学 | Human face cartoon generation method based on feature point localization |
| CN104732214A (en) * | 2015-03-24 | 2015-06-24 | 吴亮 | Quantification skin detecting method based on face image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105913389A (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913389B (en) | Image processing method and device during skin abnormality | |
| CN106096526B (en) | A kind of iris identification method and iris authentication system | |
| US10061996B1 (en) | Face recognition method and system for personal identification and authentication | |
| CN110059644A (en) | A kind of biopsy method based on facial image, system and associated component | |
| CN104364798B (en) | System and method for face verification | |
| CN106022209A (en) | Distance estimation and processing method based on face detection and device based on face detection | |
| CN110032915A (en) | A kind of human face in-vivo detection method, device and electronic equipment | |
| CA2867365A1 (en) | Method, system and computer storage medium for face detection | |
| CN109478227A (en) | Calculate the iris in equipment or the identification of other physical feelings | |
| US11270100B2 (en) | Face image detection method and terminal device | |
| CN105279487A (en) | Beauty tool screening method and system | |
| CN105787427B (en) | Lip region localization method | |
| CN107368806A (en) | Image correction method, device, computer-readable recording medium and computer equipment | |
| CN110036407B (en) | System and method for correcting digital image color based on human sclera and pupil | |
| CN111144277A (en) | Face verification method and system with living body detection function | |
| CN110059607B (en) | Living body multiplex detection method, living body multiplex detection device, computer equipment and storage medium | |
| CN107294915A (en) | Image-pickup method, system and terminal | |
| KR100857463B1 (en) | Face Region Detection Device and Correction Method for Photo Printing | |
| CN107846555A (en) | Automatic shooting method, device, user terminal and computer-readable storage medium based on gesture identification | |
| CN110674729A (en) | Method for identifying number of people based on heat energy estimation, computer device and computer readable storage medium | |
| CN105959768A (en) | Video playing parameter configuration method and device | |
| CN106650583B (en) | Method for detecting human face, device and terminal device | |
| CN110020573A (en) | In vivo detection system | |
| CN113920556A (en) | Face anti-counterfeiting method and device, storage medium and electronic equipment | |
| CN108509885A (en) | A kind of efficient identity card picture screening technique |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180504 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |