CN107392110A - Beautifying faces system based on internet - Google Patents
Beautifying faces system based on internet Download PDFInfo
- Publication number
- CN107392110A CN107392110A CN201710498941.6A CN201710498941A CN107392110A CN 107392110 A CN107392110 A CN 107392110A CN 201710498941 A CN201710498941 A CN 201710498941A CN 107392110 A CN107392110 A CN 107392110A
- Authority
- CN
- China
- Prior art keywords
- face
- unit
- image
- internet
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000001815 facial effect Effects 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 230000003796 beauty Effects 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 10
- 230000014509 gene expression Effects 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 12
- 210000000887 face Anatomy 0.000 description 19
- 230000006870 function Effects 0.000 description 11
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000013102 re-test Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of beautifying faces system based on internet, including image and video acquisition unit, Face datection unit and landscaping treatment unit, there is provided a kind of and be based on internet platform, using the beautifying faces system of " deep learning " technology, the prediction of face face value and automatic beautification are fused together, realize the beautification of facial image, and avoid damage to image, the trouble that user carries out the picture beautification operation of complexity manually can be removed from, also provide between user and exchange simultaneously, share the community of viewpoint and show the personal space of self, meets the needs of user is multi-level.
Description
Technical field
The present invention relates to internet, machine learning and living creature characteristic recognition system field, more particularly to one kind is based on interconnection
The beautifying faces system of net.
Background technology
At present, as the development of smart mobile phone and Internet technology, social media have been to be concerned by more and more people, in society
Hand over and personal lifestyle photo is uploaded on media, tourism photo turns into a part indispensable in people's life, but is in order to original
" not self-confident " of the dissatisfied or personal appearance of beginning image image quality, before image is uploaded into social media often
First carry out repairing figure, to improve the visual effect of image.First, people recognize deficiency for oneself personal beautiful degree, lack
Quantitative analysis and contrast；Secondly, although can carry out beautifying picture using Software tool improves appreciation effect, the generally skilled palm
Hold it is a repair figure software and to realize that the workload of figure is repaiied in perfection very big, it is necessary to put into substantial amounts of time and efforts, and image passes through
After landscaping treatment, the problems such as local detail handles undesirable and overall display distortion is usually present.People in existing solution
Face image is beautified and the prediction of face face value is separated, is realized in different software.Moreover, existing face value marking software is only
Carry out marking anticipation for facial image, not for specific face and anticipation fraction provide scoring height judging basis and
There is provided improves the beautification scheme of visual effect, when repairing figure using beautification software, still need by personal subjective understanding and
It is constantly trying to adjust the aesthetic feeling of face.How the prediction of face face value and beautifying faces are fused together, according to appraising in advance
Several height is provided by system to be beautified automatically with targetedly beautification scheme pedestrian's face of going forward side by side, and avoids causing picture quality
Damage turns into urgent problem.
The content of the invention
To solve the above, it is an object of the invention to provide a kind of beautifying faces system based on internet platform,
The prediction of face face value and automatic beautification are fused together, realize the beautification of facial image, and avoid damage to image.
Technical scheme is used by the present invention solves its problem：
Beautifying faces system based on internet, including：
Image and video acquisition unit, for obtaining image and video in the client, handling and end of uploading onto the server；
Face datection unit, for being detected to the information of described image and the upload of video acquisition unit, and by result
Feed back to client or landscaping treatment unit；
Landscaping treatment unit, face information is detected for handling Face datection unit, and result is fed back into face inspection
Survey unit or client.
Further, the original image that described image and video acquisition unit photographs arrive is stored using RAW high-definition formats, and is adjusted
Resolution ratio is reduced to it with image processing algorithm, improve sharpening and strengthens contrast, obtains low definition image, software processing is complete
Cheng Hou, two images are uploaded onto the server through internet, and after server receives image, low definition image is examined for face
Survey, face verification and face critical point detection, high-definition image are used for beautifying faces.
Further, described image and video acquisition unit are used for storage image resource, including are locally stored and server end
Two ways is stored, is locally stored for the storaging medium of image storage to client, server end to be stored then by image
Resource is stored onto public cloud storage platform and server storage platform, and wherein network cloud storage cloud platform storage resource is defined to
1000M, server storage platform storage resource are defined to 200M.
Further, the Face datection unit includes the detection of place remote facial image, by by Face datection algorithm portion
Affix one's name on remote server, the reserved api interface of algorithm is called on local client, and realization is handled on the remote server, bag
Include client image to upload, pass three processes under high in the clouds Face datection and server images, the client image, which uploads, to be used for
Client uploads images onto server, and the Face datection unit is used to call the Face datection algorithm pair of deployment on the server
The image that receives carries out Face datection processing, and the server images are passed the image after processing, face down for server
Coordinates feedback returns client.
Further, the Face datection unit includes high in the clouds face critical point detection, is detected for place remote and characterizes people
68 key feature points of face face shape, to determine face face face region and to carry out feature extraction, the algorithm is low
Resolution chart picture is carried out, and the key point coordinates feedback extracted is returned into client and is sent on beautifying faces algorithm.
Further, the Face datection unit includes high in the clouds face verification function, for judging original facial image and warp
Whether the image after the beautification of beautifying faces unit is same person, if beautifying faces parameter adjustment is excessive, causes similar spend
It is low, and less than system default similarity threshold 0.4 when, then re-start landscaping treatment
Further, the landscaping treatment unit use based on " deep learning " and face beauty prediction algorithm to facial image
Prejudge beautiful degree, obtain the anticipation fraction for representing face beauty degree, beauty anticipation fraction uses hundred-mark system, from 1 to 100 point
Into 100 score values, it is most ugly to be assessed as 1 expression, is assessed as that 100 expressions are most beautiful, and the more high beautiful degree of fraction is higher, otherwise lower.
Further, the landscaping treatment unit is predicted including face beauty face value, and the prediction of described face beauty face value is
On the basis of the prediction of face face value, by face beauty prediction algorithm according to 68 keys of the face characteristic and face extracted
Characteristic point, human face five-sense-organ shape is extracted, and carry out beautiful degree anticipation, beauty anticipation uses hundred-mark system, and 100 are divided into from 1 to 100
Individual score value, it is most ugly to be assessed as 1 expression, is assessed as that 100 expressions are most beautiful, and the more high beautiful degree of fraction is higher, otherwise lower.Herein only
Choose the eyes in facial face, eyebrow, face, the official of nose four are evaluated and tested.
Further, the landscaping treatment unit includes face beauty database, face beauty database purchase Asia
Zhou Ge major countries and the human face structure shape in area, face distribution, the colour of skin, skin quality exquisiteness degree, male's face beauty master die
The data such as version, women face beauty standard masterplate, male's face beauty standard masterplate and women face beauty standard masterplate, as right
Face beauty predicts the priori judged, and the prediction of many facial images training based on different regions is saved in database
Model.
Further, the landscaping treatment unit includes beautification implementation unit and automatic beautification unit, and the beautification is implemented single
Member is used to instruct beautifying faces algorithm to select beautiful master pattern from face beauty database.The automatic beautification unit, which refers to, is
System realizes that human face five-sense-organ smoothly adjusts automatically according to beautification embodiment, and does not change the texture original appearance on face surface.
Further, the system also includes：
Basis of software functional unit, including user's registration, log in personalized application set function, pass through recognition of face skill
Art and fingerprint identification technology realize logging in and safeguarding for software account；
Instant messaging unit, including third party's social media account log in instant chat and chatted for internet dating, addition
Other users are good friend, using grouping management pattern, receive the evaluation of system information and online friend in individual subscriber cyberspace
Information；
Personal homepage unit, including personal homepage and EXE network albums displaying, can carry out individual space dress up, word record
Enter, EXE network albums play automatically, possess EXE network albums and make online, and support download online function.
Beneficial effects of the present invention：This invention realizes the beautifying faces of " deep learning " on internet platform, leads to
After crossing the facial image of client collection user and being compressed processing, upload onto the server through internet, enter on the server
Row Face datection, face verification, face critical point detection and beautifying faces algorithm process, avoiding handset capability difference can not run
The drawbacks of deep learning network.Meanwhile face beauty prediction and beautifying faces are fused together, complete the same of beautiful prediction
When, according to the relevant parameter of user's setting, prioritization scheme is automatically recommended by system, passes through the image processing techniques such as affine and depth
The machine learning algorithms such as degree study, popular study, the local smoothing method adjustment of shape of face, face is carried out, realizes face to higher beauty
Score value changes.Whole process is automatically performed by system, and the smooth adjustment of local aesthetics is carried out just for face location, will not be to figure
Impacted as overall, after the completion of processing, processing vestige will not be left.
The present invention is used as a software, realizes and combines internet and biometrics identification technology, possesses intelligence
Energyization and full-automatic processing function, it is possible to increase the processing speed and beautification quality of image.
Brief description of the drawings
Fig. 1 is the system block diagram of the present invention；
Fig. 2 is a kind of picture beautification flow chart shown by the present invention.
Embodiment
In order that technical problems, technical solutions and advantages to be solved are more clearly understood, tie below
Embodiment is closed, the present invention is described in detail.Specific embodiment described herein only to explain the present invention, is not used to
Limit the present invention.
The embodiment of the present application provides a kind of system based on internet, applied to the beautifying faces APP of mobile terminal, this face
Beautify APP include image taking and video record, image and video storage, high in the clouds Face datection, high in the clouds face critical point detection,
High in the clouds face verification, high in the clouds face face value prediction, high in the clouds face face value prediction, face beauty database, beautifying faces scheme and
Face beautifies automatically, instant chat and personal network place function；The beautifying faces APP also include software registration, log in and
Personalized application sets function,
After software opens operation, acquiescence opening system logs in and enrollment page, if for the first time using this software, it is necessary to note
It could enter system after volume, otherwise can not use any function of system, the software support third party social media account
Register and log in.Acquiescence uses phone number registration, E-mail address can also be used to register.Succeed in registration, into after system,
The page is set, software PIN code, graphical passwords, fingerprint recognition and recognition of face landing approach can be set, and software automatically step on by record
Land account and password.
Further, the software section function is realized by the algorithm of " deep learning " technological development, due to mobile phone
Deep learning network poor can not be run, the software is using configuration Face datection, face verification, people on server beyond the clouds
Face critical point detection and beautifying faces algorithm, gather image on the client, and the api interface for calling algorithm reserved passes image
Progress algorithm realization is sent on cloud server, after detection algorithm processing terminates, result is fed back to client by server, and
Shown in client.Because algorithm is realized on the server, it is related to the process that image is uploaded and downloaded, therefore preferably
Network condition, it is critically important for the usage experience for improving software.
Further, client is collected after image uploads onto the server, and is entered on the server using " deep learning " algorithm
Row Face datection, if it is possible to detect face, algorithm returns to face ROI coordinates, and returns to client, client by server
Drawing algorithm is called, frame selects human face region in the form of red frame on image；If can't detect face, system will return wrong
Prompt by mistake, and require that changing image retests.Detection algorithm detects 68 spies also detected while face on face
Point is levied, the feedback of the information detected is returned client and sends other algorithms to by server.In the beautifying faces stage, client is passed back
68 key points at end can't mark out on facial image to be come, and is checked if desired, is then needed to open inside software design patterns
Open corresponding function.
Further, after " deep learning " Face datection algorithm detects face and 68 characteristic points, then using image at
Reason technology, human face five-sense-organ region is split, orient particular location and the region of face, and the image submitted according to user
Parameter, such as native place, sex, age, system transfer what corresponding region, sex and age level had trained from database
" deep learning " beautiful model, carries out face beauty prediction and the beautiful prediction of face, if user does not provide the image ginseng of individual
Number, system default carries out sex and age test, and calls public training pattern to carry out fuzz testing, due to country variant and ground
There is difference in the people in area, the beautiful result of fuzzy algorithmic approach prediction there may be relatively large deviation, also may be used in appearance and aesthetic standards
The beautification scheme mismatch that the system later stage provides can be caused, such as：The face beautification scheme of people from Xinjiang is recommended into people from Jiangsu and Zhejiang Provinces.
Further, after system prejudges out the beautiful degree of face and face, feedback of the information returns client, and in client
Screen on shown, the beautiful anticipation fraction of face and face use hundred-mark system, wherein 1 represents most ugly, 100 expressions are most
U.S., fraction is higher, and beautiful degree is higher, otherwise lower.After user receives beautiful scoring, can then beautifying faces be set to join
Number, the beautiful fraction that such as setting to be reached, the age level to be reached, so as to system automatically selected according to the parameter of setting it is excellent
Change model and optimization reference scheme is provided.After system obtains the parameter that user submits, the beauty in beauty analytical database is called
Model, using the affine change technique in manifold learning, deep learning and image procossing, face are mapped to U.S. of setting
On beautiful Degree Model, then the details such as illumination brightness is carried out using deep learning method and merged, face organ after realization processing and
Face is perfectly combined, and user can also be not provided with parameter, and algorithm acquiescence is standardized, to less than standard beauty degree
Face are micro-adjusted.
Further, after image landscaping treatment, then using " " face verification algorithm judges after landscaping treatment deep learning
Image and original image whether be still same person.Algorithm is measured using similarity, because human face five-sense-organ is adjusted
Afterwards, face features details changes, and the characteristic point for retesting extraction has a difference, algorithm do not directly give whether
The result of determination of same person, but a judge similarity is provided, similarity uses hundred-mark system, 100 is divided into from 0 to 100
Score value, wherein 0 represents entirely different, 100 represent identical, and fraction is higher, and similarity degree is higher, otherwise lower.System is write from memory
Recognize and be provided with a human face similarity degree threshold value, i.e., 0.4, if after image procossing, similarity is less than the value, then re-starts beautification
Processing.The threshold value can be changed in system setting.Also be integrated with face verification function in the software, user can simultaneously on
Pass two images verified, now system processing after, provide be same person or whether the evaluation result of same person.
Further, user can upload the original image of oneself and the image of processingization and be shown to software common platform, and
Receive the scoring of other users, points-scoring system sets 10 score values, and from 1 to 10, wherein 1 represents most ugly, 10 represent most beautiful, fraction
More high beautiful degree is higher, otherwise lower, while online friend gives a mark, can also answer default with face is beautiful is determined with
The problem of pass, it can also be left a message below image.System can calculate scoring statistics according to participation situation, the score value of online friend
Histogram, face value average value and score value variance, facilitate user to refer to, to investigate the validity of scoring.User can also
The PK with other users is participated in, by collecting the form praised, within the time of restriction, collects winning more than praising, and enter higher one wheel
PK match.
Further, user can also upload image, video and EXE electron albums, electronics phase in the personal space of oneself
Volume supports online make to be uploaded with local, and the electron album made online is supported to download.Image branch inside personal space photograph album
The marking of batch face value and landscaping treatment operation are held, user can select to retain scoring vestige.
Further, in order to facilitate the communication between user with exchange, the software has opened instant chat function, Yong Hufang
Receive the image-receptive of ballot marking on public display platform to after new ballot and comment, vote information and comment information meeting
By system forwards to chat feature area, user can obtain related consultation information at any time.
Further, it is described post with follow-up title examination be used for specification software using, advocate civilization speech and forbid delivering
Damage national interests and encroach on the speech of other people legitimate rights and interests, realized and detected by third party's algorithm, it is found that illegal software uses rule
Speech then, according to situation of a serious nature, carry out deleting note and forbid the punishment such as speech.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the invention, all originals in the present invention
Then with all any modification, equivalent and improvement made within spirit etc., it is included within protection scope of the present invention.
Claims (11)
- A kind of 1. beautifying faces system based on internet, it is characterised in that including：Image and video acquisition unit, for obtaining Take image and video, handle and end of uploading onto the server；Face datection unit, for described image and video acquisition unit The information of biography is detected, and result is fed back into client or landscaping treatment unit；Landscaping treatment unit, for handling face Detection unit detects face information, and result is fed back into Face datection unit or client.
- 2. the beautifying faces system according to claim 1 based on internet, it is characterised in that described image and video obtain Take the original image that unit photographs arrive to be stored using RAW high-definition formats, and call image processing algorithm to reduce resolution ratio to it, carry Height sharpens and enhancing contrast, acquisition low definition image, and after the completion of software processing, two images upload to service through internet Device, after server receives image, low definition image is used for Face datection, high-definition image is used for beautifying faces.
- 3. the beautifying faces system based on internet according to claim 2, it is characterised in that described image and video acquisition Unit is additionally operable to storage image resource, including is locally stored and stores two ways with server end, is locally stored and is used for image Store in the storaging medium of client, image resource storage is then arrived public cloud storage platform and server by server end storage In storage platform.
- 4. according to any described beautifying faces systems based on internet of claim 1-3, it is characterised in that the face inspection Surveying unit will be deployed to Face datection algorithm on remote server, and the reserved api interface of algorithm is called on local client, Image procossing is carried out on the remote server, and the Face datection unit includes client image uploading unit, high in the clouds face is examined Survey leaflet member, the client image uploading unit under unit and server images and upload images onto server for client, The high in the clouds Face datection unit is used to call the Face datection algorithm of deployment on the server to enter pedestrian to the image received Face detection process, leaflet member is used for server the image after processing, face coordinates feedback is returned into client under the server images End.
- 5. the beautifying faces system according to claim 4 based on internet, it is characterised in that the Face datection unit Also include high in the clouds face critical point detection unit, 68 key features for characterizing face face shape are detected for place remote Point, to determine face face face region and to carry out feature extraction, said process is carried out in low definition image, and will extraction To key point coordinates feedback return client and be sent on beautifying faces algorithm.
- 6. the beautifying faces system according to claim 5 based on internet, it is characterised in that the Face datection unit Also include high in the clouds face verification unit, for judge original facial image and through beautifying faces unit beautification after image whether be Same person, if similarity is too low, and less than system default similarity threshold when, then re-start landscaping treatment.
- 7. the beautifying faces system according to claim 4 based on internet, it is characterised in that the landscaping treatment unit Beautiful degree is prejudged to facial image using Face datection algorithm, obtains the anticipation fraction for representing face beauty degree, it is beautiful pre- Number of appraising uses hundred-mark system, and 100 score values are divided into from 1 to 100, and it is most ugly to be assessed as 1 expression, and it is most beautiful to be assessed as 100 expressions, fraction More high beautiful degree is higher, otherwise lower.
- 8. the beautifying faces system according to claim 7 based on internet, it is characterised in that the landscaping treatment unit Also include face beauty face value predicting unit, described face beauty face value predicting unit is on the basis of face face value prediction On, by face beauty prediction algorithm according to 68 key feature points of the face characteristic and face extracted, extract human face five-sense-organ Shape, and beautiful degree anticipation is carried out, beauty anticipation uses hundred-mark system, and 100 score values are divided into from 1 to 100, are assessed as 1 expression It is most ugly, it is assessed as that 100 expressions are most beautiful, and the more high beautiful degree of fraction is higher, on the contrary it is lower.
- 9. the beautifying faces system according to claim 8 based on internet, it is characterised in that the landscaping treatment unit Also include face beauty database, the face beauty database purchase human face structure shape of each major country in Asia and area Shape, face distribution, the colour of skin, skin quality exquisiteness degree, male's face beauty standard masterplate, women face beauty standard masterplate, male's face Beautiful standard masterplate and women face beauty standard masterplate data.
- 10. the beautifying faces system according to claim 9 based on internet, it is characterised in that the landscaping treatment list Member includes beautification implementation unit and automatic beautification unit, and the beautification implementation unit is used to instruct beautifying faces algorithm beautiful from face Beautiful master pattern is selected in beautiful database, the automatic beautification unit refers to system and realizes face automatically according to beautification embodiment Face smoothly adjust, and do not change the texture original appearance on face surface.
- 11. the beautifying faces system according to claim 1 based on internet, it is characterised in that the system also includes： Basis of software functional unit, including user's registration, log in personalized application set function, pass through face recognition technology and fingerprint Identification technology realizes logging in and safeguarding for software account；Instant messaging unit, including third party's social media account log in instant chat and chatted for internet dating, add other User is good friend, using grouping management pattern, receives the evaluation information of system information and online friend in individual subscriber cyberspace；Personal homepage unit, including personal homepage and EXE network albums displaying, can carry out individual space dress up, words input, EXE network albums play automatically, possess EXE network albums and make online, and support download online function.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710498941.6A CN107392110A (en) | 2017-06-27 | 2017-06-27 | Beautifying faces system based on internet |
| PCT/CN2017/109834 WO2019000777A1 (en) | 2017-06-27 | 2017-11-08 | Internet-based face beautification system |
| JP2019501994A JP6773883B2 (en) | 2017-06-27 | 2017-11-08 | Internet-based facial system |
| KR1020197000965A KR102195922B1 (en) | 2017-06-27 | 2017-11-08 | Internet-based facial beautification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710498941.6A CN107392110A (en) | 2017-06-27 | 2017-06-27 | Beautifying faces system based on internet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107392110A true CN107392110A (en) | 2017-11-24 |
Family
ID=60333671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710498941.6A Pending CN107392110A (en) | 2017-06-27 | 2017-06-27 | Beautifying faces system based on internet |
Country Status (4)
| Country | Link |
|---|---|
| JP (1) | JP6773883B2 (en) |
| KR (1) | KR102195922B1 (en) |
| CN (1) | CN107392110A (en) |
| WO (1) | WO2019000777A1 (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107995428A (en) * | 2017-12-21 | 2018-05-04 | 广东欧珀移动通信有限公司 | Image processing method, device and storage medium and mobile terminal |
| CN108040296A (en) * | 2017-12-25 | 2018-05-15 | 北京奇虎科技有限公司 | Live dress ornament based on the segmentation of adaptive tracing frame is dressed up method and device |
| CN108629296A (en) * | 2018-04-17 | 2018-10-09 | 广州视源电子科技股份有限公司 | Image processing method and device |
| CN109145865A (en) * | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Face standard level calculating method and device |
| CN109508620A (en) * | 2018-08-01 | 2019-03-22 | 上海晨鱼网络科技有限公司 | Cosmetic method, system, electric terminal and storage medium based on augmented reality |
| CN109712082A (en) * | 2018-12-05 | 2019-05-03 | 厦门美图之家科技有限公司 | The method and device of figure is repaired in cooperation |
| CN110188652A (en) * | 2019-05-24 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Processing method, device, terminal and the storage medium of facial image |
| CN110414489A (en) * | 2019-08-21 | 2019-11-05 | 五邑大学 | A kind of face beauty prediction technique based on multi-task learning |
| CN110688946A (en) * | 2019-09-26 | 2020-01-14 | 上海依图信息技术有限公司 | Public cloud silence in-vivo detection device and method based on picture identification |
| CN110889352A (en) * | 2019-11-18 | 2020-03-17 | 珠海全志科技股份有限公司 | Image blurring processing method, computer device, and computer-readable storage medium |
| CN112233014A (en) * | 2020-10-16 | 2021-01-15 | 陈晶晶 | Face processing method and face processing platform based on big data and artificial intelligence |
| CN113421197A (en) * | 2021-06-10 | 2021-09-21 | 杭州海康威视数字技术股份有限公司 | Processing method and processing system of beautifying image |
| WO2021218729A1 (en) * | 2020-04-26 | 2021-11-04 | 华为技术有限公司 | Method for displaying skin details in augmented reality mode, and electronic device |
| CN113688708A (en) * | 2021-08-12 | 2021-11-23 | 北京数美时代科技有限公司 | Face recognition method, system and storage medium based on probability characteristics |
| WO2021237736A1 (en) * | 2020-05-29 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Image processing method, apparatus and system, and computer-readable storage medium |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110933354B (en) * | 2019-11-18 | 2023-09-01 | 深圳传音控股股份有限公司 | Customizable multi-style multimedia processing method and terminal thereof |
| CN111274919A (en) * | 2020-01-17 | 2020-06-12 | 桂林理工大学 | Method, system, server and medium for detecting five sense organs based on convolutional neural network |
| CN111343472B (en) * | 2020-02-21 | 2023-05-26 | 腾讯科技（深圳）有限公司 | Image processing effect adjusting method, device, equipment and medium |
| CN111489311B (en) * | 2020-04-09 | 2023-08-08 | 北京百度网讯科技有限公司 | Face beautifying method and device, electronic equipment and storage medium |
| CN111598818B (en) * | 2020-04-17 | 2023-04-28 | 北京百度网讯科技有限公司 | Training method and device for face fusion model and electronic equipment |
| CN113643417B (en) * | 2021-08-17 | 2023-06-27 | 腾讯科技（深圳）有限公司 | Image adjustment method, device, electronic equipment and storage medium |
| TW202416066A (en) | 2022-10-04 | 2024-04-16 | 倍利科技股份有限公司 | System for remotely controlling microscopic machinery and method thereof |
| CN116074618B (en) * | 2023-03-31 | 2023-07-25 | 广州翼拍联盟网络技术有限公司 | Intelligent photographing service method, system and storage medium for preventing portrait information leakage |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714351A (en) * | 2013-12-18 | 2014-04-09 | 五邑大学 | Depth self learning-based facial beauty predicting method |
| CN103761536A (en) * | 2014-01-28 | 2014-04-30 | 五邑大学 | Human face beautifying method based on non-supervision optimal beauty features and depth evaluation model |
| CN104503749A (en) * | 2014-12-12 | 2015-04-08 | 广东欧珀移动通信有限公司 | Photo processing method and electronic equipment |
| CN104537612A (en) * | 2014-08-05 | 2015-04-22 | 华南理工大学 | Method for automatically beautifying skin of facial image |
| CN104574306A (en) * | 2014-12-24 | 2015-04-29 | 掌赢信息科技（上海）有限公司 | Face beautifying method for real-time video and electronic equipment |
| CN105931211A (en) * | 2016-04-19 | 2016-09-07 | 中山大学 | Face image beautification method |
| CN105979194A (en) * | 2016-05-26 | 2016-09-28 | 努比亚技术有限公司 | Video image processing apparatus and method |
| CN106296701A (en) * | 2016-08-15 | 2017-01-04 | 北京小米移动软件有限公司 | Image processing method and device |
| CN106507021A (en) * | 2015-09-07 | 2017-03-15 | 腾讯科技（深圳）有限公司 | Method for processing video frequency and terminal device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004246673A (en) * | 2003-02-14 | 2004-09-02 | Fuji Photo Film Co Ltd | Face image processing device and system |
| KR100596498B1 (en) * | 2004-06-30 | 2006-07-03 | 전자부품연구원 | Online face recognition system based on multi frame |
| KR101254177B1 (en) * | 2011-10-07 | 2013-04-19 | 위아코퍼레이션 주식회사 | A system for real-time recognizing a face using radial basis function neural network algorithms |
| KR101901591B1 (en) * | 2011-11-01 | 2018-09-28 | 삼성전자주식회사 | Face recognition apparatus and control method for the same |
| US9087273B2 (en) * | 2011-11-15 | 2015-07-21 | Facebook, Inc. | Facial recognition using social networking information |
| CN104346136B (en) * | 2013-07-24 | 2019-09-13 | 腾讯科技（深圳）有限公司 | A kind of method and device of picture processing |
| JP2016085579A (en) * | 2014-10-24 | 2016-05-19 | 大学共同利用機関法人情報・システム研究機構 | Image processing apparatus and method for interactive device, and the interactive device |
| CN106558025B (en) * | 2015-09-29 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Picture processing method and device |
| CN105469081B (en) * | 2016-01-15 | 2019-03-22 | 成都品果科技有限公司 | A kind of face key independent positioning method and system for U.S. face |
| CN105787878B (en) * | 2016-02-25 | 2018-12-28 | 杭州格像科技有限公司 | A kind of U.S. face processing method and processing device |
-
2017
- 2017-06-27 CN CN201710498941.6A patent/CN107392110A/en active Pending
- 2017-11-08 KR KR1020197000965A patent/KR102195922B1/en active IP Right Grant
- 2017-11-08 WO PCT/CN2017/109834 patent/WO2019000777A1/en active Application Filing
- 2017-11-08 JP JP2019501994A patent/JP6773883B2/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714351A (en) * | 2013-12-18 | 2014-04-09 | 五邑大学 | Depth self learning-based facial beauty predicting method |
| CN103761536A (en) * | 2014-01-28 | 2014-04-30 | 五邑大学 | Human face beautifying method based on non-supervision optimal beauty features and depth evaluation model |
| CN104537612A (en) * | 2014-08-05 | 2015-04-22 | 华南理工大学 | Method for automatically beautifying skin of facial image |
| CN104503749A (en) * | 2014-12-12 | 2015-04-08 | 广东欧珀移动通信有限公司 | Photo processing method and electronic equipment |
| CN104574306A (en) * | 2014-12-24 | 2015-04-29 | 掌赢信息科技（上海）有限公司 | Face beautifying method for real-time video and electronic equipment |
| CN106507021A (en) * | 2015-09-07 | 2017-03-15 | 腾讯科技（深圳）有限公司 | Method for processing video frequency and terminal device |
| CN105931211A (en) * | 2016-04-19 | 2016-09-07 | 中山大学 | Face image beautification method |
| CN105979194A (en) * | 2016-05-26 | 2016-09-28 | 努比亚技术有限公司 | Video image processing apparatus and method |
| CN106296701A (en) * | 2016-08-15 | 2017-01-04 | 北京小米移动软件有限公司 | Image processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| 丁轶峰等: "《掌纹掌脉融合识别技术及其在泛地铁环境中的应用》", 31 January 2017 * |
| 王少标: "基于个性与共性探讨的人脸美化", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107995428B (en) * | 2017-12-21 | 2020-02-07 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and mobile terminal |
| CN107995428A (en) * | 2017-12-21 | 2018-05-04 | 广东欧珀移动通信有限公司 | Image processing method, device and storage medium and mobile terminal |
| CN108040296A (en) * | 2017-12-25 | 2018-05-15 | 北京奇虎科技有限公司 | Live dress ornament based on the segmentation of adaptive tracing frame is dressed up method and device |
| CN108040296B (en) * | 2017-12-25 | 2020-08-28 | 北京奇虎科技有限公司 | Live-broadcast dress decorating method and device based on self-adaptive tracking frame segmentation |
| CN108629296A (en) * | 2018-04-17 | 2018-10-09 | 广州视源电子科技股份有限公司 | Image processing method and device |
| CN109508620A (en) * | 2018-08-01 | 2019-03-22 | 上海晨鱼网络科技有限公司 | Cosmetic method, system, electric terminal and storage medium based on augmented reality |
| CN109145865A (en) * | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Face standard level calculating method and device |
| CN109712082A (en) * | 2018-12-05 | 2019-05-03 | 厦门美图之家科技有限公司 | The method and device of figure is repaired in cooperation |
| CN109712082B (en) * | 2018-12-05 | 2020-08-07 | 厦门美图之家科技有限公司 | Method and device for collaboratively repairing picture |
| CN110188652A (en) * | 2019-05-24 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Processing method, device, terminal and the storage medium of facial image |
| CN110414489A (en) * | 2019-08-21 | 2019-11-05 | 五邑大学 | A kind of face beauty prediction technique based on multi-task learning |
| CN110688946A (en) * | 2019-09-26 | 2020-01-14 | 上海依图信息技术有限公司 | Public cloud silence in-vivo detection device and method based on picture identification |
| CN110889352A (en) * | 2019-11-18 | 2020-03-17 | 珠海全志科技股份有限公司 | Image blurring processing method, computer device, and computer-readable storage medium |
| WO2021218729A1 (en) * | 2020-04-26 | 2021-11-04 | 华为技术有限公司 | Method for displaying skin details in augmented reality mode, and electronic device |
| WO2021237736A1 (en) * | 2020-05-29 | 2021-12-02 | 深圳市大疆创新科技有限公司 | Image processing method, apparatus and system, and computer-readable storage medium |
| CN112233014A (en) * | 2020-10-16 | 2021-01-15 | 陈晶晶 | Face processing method and face processing platform based on big data and artificial intelligence |
| CN113421197A (en) * | 2021-06-10 | 2021-09-21 | 杭州海康威视数字技术股份有限公司 | Processing method and processing system of beautifying image |
| CN113688708A (en) * | 2021-08-12 | 2021-11-23 | 北京数美时代科技有限公司 | Face recognition method, system and storage medium based on probability characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20190018483A (en) | 2019-02-22 |
| KR102195922B1 (en) | 2020-12-29 |
| JP2019523489A (en) | 2019-08-22 |
| JP6773883B2 (en) | 2020-10-21 |
| WO2019000777A1 (en) | 2019-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107392110A (en) | Beautifying faces system based on internet | |
| CN111344712B (en) | System and method for image de-identification | |
| KR101733512B1 (en) | Virtual experience system based on facial feature and method therefore | |
| US20220147781A1 (en) | Signature-based unique identifier | |
| US20140153832A1 (en) | Facial expression editing in images based on collections of images | |
| CN109173263A (en) | A kind of image processing method and device | |
| CN106778584A (en) | A kind of face age estimation method based on further feature Yu shallow-layer Fusion Features | |
| CN106557726A (en) | A kind of band is mourned in silence the system for face identity authentication and its method of formula In vivo detection | |
| US9286706B1 (en) | Editing image regions based on previous user edits | |
| US11501564B2 (en) | Mediating apparatus and method, and computer-readable recording medium thereof | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN109559362B (en) | Image subject face replacing method and device | |
| CN110135262A (en) | The anti-peeping processing method of sensitive data, device, equipment and storage medium | |
| CN104951940A (en) | Mobile payment verification method based on palmprint recognition | |
| CN109903291A (en) | Image processing method and relevant apparatus | |
| AU2014339827B2 (en) | Generating image compositions | |
| CN109598210A (en) | A kind of image processing method and device | |
| WO2020181706A1 (en) | Plant species identification method and apparatus | |
| CN106326823A (en) | Method and system for acquiring head image in picture | |
| CN112819718A (en) | Image processing method and device, electronic device and storage medium | |
| KR20100025862A (en) | Facial physiognomic judgment of fortune and face avatar generation system using a face recognition | |
| CN106650555A (en) | Real person verifying method and system based on machine learning | |
| CN107146275A (en) | A kind of method and device of setting virtual image | |
| KR101827998B1 (en) | Virtual experience system based on facial feature and method therefore | |
| CN109872282A (en) | A kind of image desensitization method based on computer vision and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |
|
| RJ01 | Rejection of invention patent application after publication |