CN109359317A - A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection - Google Patents
A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection Download PDFInfo
- Publication number
- CN109359317A CN109359317A CN201810933834.6A CN201810933834A CN109359317A CN 109359317 A CN109359317 A CN 109359317A CN 201810933834 A CN201810933834 A CN 201810933834A CN 109359317 A CN109359317 A CN 109359317A
- Authority
- CN
- China
- Prior art keywords
- model
- lipstick
- face
- color
- user
- 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
- 239000003086 colorant Substances 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000010187 selection method Methods 0.000 title claims abstract description 13
- 238000010191 image analysis Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 7
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 210000000088 lip Anatomy 0.000 claims description 17
- 230000001815 facial effect Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 7
- 210000001508 eye Anatomy 0.000 claims description 7
- 210000004709 eyebrow Anatomy 0.000 claims description 7
- 210000003813 thumb Anatomy 0.000 claims description 5
- 230000003796 beauty Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000036555 skin type Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- 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
- 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
- G06V40/168—Feature extraction; Face representation
Abstract
It matches colors the model building method of selection the invention discloses a kind of lipstick, comprising the following steps: model photo obtaining step: obtaining model picture;Lipstick color extraction step: the color value of the lip in model face region is extracted to obtain lipstick color data;Scene analysis step: by the clothing of personage in image analysis model picture to obtain model usage scenario;Model construction step: learning training is carried out to obtain recommended models to the lipstick color data and model usage scenario got using convolutional neural networks algorithm.The present invention also provides a kind of lipstick color matching selection methods.The user that lipstick color matching selection method of the present invention will acquire selects scene and the recommended models of building to be compared to obtain lipstick color corresponding with the usage scenario, which is recommended user;Greatly improve the accuracy that user selects suitable lipstick.
Description
Technical field
It matches colors the model building method of selection the present invention relates to a kind of machine learning techniques field more particularly to a kind of lipstick
With lipstick color matching selection method.
Background technique
The makeup of lip color is according to everyone makings, shape of face, attends the lipstick that the various factors such as occasion combine and carry out
Collocation of colour.At all times, all in the cosmetic method for pursuing beauty, various information for how making up collocation is filled with miscellaneous people
In the media such as will, book, TV, network.And a kind of lipstick color matching for being suitble to oneself shape of face, attending occasion how is selected, it is often right
The effect of crucial touch is played in the facial dressing of entire people.Ordinary populace selects the lipstick color for being suitble to oneself, and most people is
Recommended according to trends such as star, Fashion Magazines, carries out self hobby as leading subjective selection, the collocation result of this subjectivity is past
Toward not too much suitable owner, because the occasion that everyone colour of skin, shape of face and needs are attended is different, the lipstick resulted in the need for
Diameter is not identical for collocation yet.Also someone listens to the professional advice of beauty and make-up teacher, but the various occasions attended are not in daily life
Together, the collocation of lip color also has different variations, and the suggestion of beautician needs take considerable time and link up, can not be whenever and wherever possible
Easily obtain professional comment.
Summary of the invention
For overcome the deficiencies in the prior art, it matches colors the model of selection one of the objects of the present invention is to provide a kind of lipstick
Construction method.
The second object of the present invention is to provide a kind of computer readable storage medium.
The third object of the present invention is to provide a kind of lipstick color matching selection method.
The fourth object of the present invention is to provide a kind of computer readable storage medium.
An object of the present invention adopts the following technical scheme that realization:
A kind of lipstick is matched colors the model building method of selection, comprising the following steps:
Model photo obtaining step: model picture is obtained;
Lipstick color extraction step: the color value of the lip in model face region is extracted to obtain lipstick color data;
Scene analysis step: by the clothing of personage in image analysis model picture to obtain model usage scenario;
Model construction step: using convolutional neural networks algorithm to the lipstick color data and model usage scenario got
Learning training is carried out to obtain recommended models.
Further, model picture described in the model photo obtaining step is to be thumbed up by what social media was got
Number is more than the picture of preset threshold.
Further, the scene analysis step further include: by analyzing keyword corresponding with model picture to obtain
Model usage scenario.
Further, further comprising the steps of after model photo obtaining step:
Model face analytical procedure: image analysis is carried out to obtain model face region to model picture;
Model skin cluster step: the colour of skin in model face region is extracted to obtain model colour of skin data;
Model shape of face obtaining step: face-image analysis is carried out to obtain model shape of face data to model face region.Into one
Step ground, the model skin cluster step specifically include following sub-step:
Non- area of skin color in identification model facial area, the non-area of skin color include eyes, eyebrow and lip;
Non- area of skin color is rejected to obtain blee region;
It extracts the color in blee region and is averaged to obtain model colour of skin data.
Further, the model construction step specifically: using convolutional neural networks algorithm to model usage scenario with
And model colour of skin data, model shape of face data and the lipstick color data got carries out learning training to obtain recommended models.
The second object of the present invention adopts the following technical scheme that realization:
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Realize that lipstick as described in any one of one of the object of the invention is matched colors the model building method of selection when row.
The third object of the present invention adopts the following technical scheme that realization:
A kind of lipstick color matching selection method, comprising the following steps:
Information receiving step: the selected contextual data of user is received;
Lipstick recommendation step: it is matched according to contextual data with recommended models to obtain lipstick color suggested design.
Further, further include following steps after information receiving step:
Face analysis step: image analysis is carried out to obtain user's facial area to the user picture got;
Skin cluster step: skin cluster is carried out to obtain user colour data to user's face region;
Shape of face obtaining step: face-image analysis is carried out to obtain user's shape of face data to user's face region;
And the lipstick recommendation step specifically: according to contextual data, user's shape of face data and user colour data with push away
Model is recommended to be matched to obtain lipstick color suggested design.
The fourth object of the present invention adopts the following technical scheme that realization:
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The color matching selection method of the lipstick as described in the three of the object of the invention is realized when row.
Compared with prior art, the beneficial effects of the present invention are:
The user that lipstick color matching selection method of the present invention will acquire selects scene to be compared with the recommended models of building
To obtain lipstick color corresponding with the usage scenario, which is recommended into user;It is suitable to greatly improve user's selection
The accuracy of lipstick.
Detailed description of the invention
Fig. 1 is the flow chart of the lipstick color matching selection method of embodiment one.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
As shown in Figure 1, present embodiments providing a kind of computer readable storage medium, it is stored thereon with computer program,
The computer program realizes following steps when being executed by processor:
S1: the selected contextual data of user is received;
S2: image analysis is carried out to obtain user's facial area to the user picture got;This stage mainly obtains
The photo of user, user can upload taking pictures certainly for oneself, or special by the current face of user that camera is got
Sign, to get the current photo of user;
S3: skin cluster is carried out to obtain user colour data to user's face region;Skin cluster is carried out to facial area.
The facial area in photo is judged, after the uneven region of eyes, eyebrow, lip is removed, to remaining facial area skin
Color is averaged, and obtains the HSB value of blee.Step S3 specifically includes following sub-step:
S31: the non-area of skin color in identification user's face region, the non-area of skin color includes eyes, eyebrow and lip;
S32: non-area of skin color is rejected to obtain blee region;
S33: it extracts the color in blee region and is averaged to obtain user colour data.
S4: face-image analysis is carried out to obtain user's shape of face data to user's face region;Row face is shone into user's self-timer
Portion's image analysis judges the shape of face of user.The color cluster of user's face image-region is analyzed, the edge for extracting color lump cluster is special
Sign carries out classified description using line segment to shape of face, judges shape of face generic, particularly belong to state's word face, oval face, in round face
Which classification.
S5: it is matched according to user's shape of face data, user colour data and contextual data with recommended models to obtain mouth
Red suggested design, the usage scenario select to obtain by user.The quantity of the lipstick color suggested design have it is multiple, it is described
Lipstick color suggested design includes lipstick color and usage scenario corresponding with lipstick color.According to the shape of face of user, the colour of skin and
Usage scenario compares recommended models and judges the lipstick Color scheme that user is suitble to, and result be presented to user and check.Alternatively, such as
Fruit user does not submit usage scenario, then judges lipstick face that user is suitble to recommended models according to the shape of face of user, ratio of skin tone
Color scheme is shown to user in conjunction with the usage scenario that each scheme is suitble to together and selects.
Mass users, which are obtained, by various social medias thumbs up several high star's dressing photos;By learn various shapes of face,
The colour of skin, the combination for attending scene and lipstick color matching, obtain the recommended models of lipstick colour matching selection;The building master of recommended models
Want the following steps are included:
S51: obtaining model picture, and the model picture is that the number that thumbs up got by social media is more than preset threshold
Picture;It obtains and thumbs up more star's photo on a large amount of social networks.The model picture that is to say the photo of star, due to
The lipstick of star was designed by Specialty Design teacher, more standby certain so for ordinary people
Reference value, but the acquisition of this content is also not all photos of all stars, but choose the photograph being wherein well received by the public
Piece, since the person of thumbing up is from more ordinary peoples, so some tentative dressings of some stars can also be screened out,
More meet the aesthetic of general masses sieve;
S52: image analysis is carried out to obtain model face region to model picture;
S53: the colour of skin in model face region is extracted to obtain model colour of skin data;Obtain photo in star facial area into
Row skin cluster.When skin cluster, first determine whether the facial area in photo, then by eyes, eyebrow, lip it is uneven
After region is removed, the remaining facial area colour of skin is averaged, obtains the HSB value of blee.Due to eyes, eyebrow and mouth
The color of lip and human face's colour of skin are inconsistent, so can be made if extracting corresponding color when carrying out skin cluster
At certain color difference, so first screening out the information of this part in advance;S53 specifically includes following sub-step:
Non- area of skin color in identification model facial area, the non-area of skin color include eyes, eyebrow and lip;
Non- area of skin color is rejected to obtain blee region;
It extracts the color in blee region and is averaged to obtain model colour of skin data.
S54: face-image analysis is carried out to obtain model shape of face data to model face region;The present invention is according to different faces
The shape of face of people is divided into state's word face, oval face, round face three types, is retouched using curve classification, that is, curve+line segment by type feature
It states mode and classified description, respectively state's word face, oval face, the types such as round face is carried out to different shapes of face.To star photo into
The analysis of row face-image is carried out color cluster to each facial area, extracts the edge feature of color lump cluster, retouched using above-mentioned line segment
It states mode the edge feature of shape of face is described, corresponding each description result establishes shape of face classification based training collection.
S55: the color value of the lip in model face region is extracted to obtain lipstick color data;Judge the mouth of star's photo
Lip portion carries out dominant hue extraction, obtains the lipstick color mean value of lip.
S56: using convolutional neural networks algorithm to model usage scenario and the model colour of skin data got, model face
Type data and lipstick color data carry out learning training, to obtain recommended models;The model usage scenario passes through image analysis
The clothing of personage to be in model picture to obtain, or by obtaining keyword corresponding to model picture to obtain.
Using shape of face feature, the colour of skin, scene tag as input item, lipstick color utilizes convolutional Neural net as output item
Network algorithm carries out learning training, completes the training of lipstick color recommended models, corrects recommendation results by repetition training.Judge star
The lip portion of photo carries out dominant hue extraction, obtains the lipstick color mean value of lip.About star's photo in social networks
The step of text content analysis, progress scene keyword extraction, can also establish usage scenario by analyzing the dressing of star
Label, such as dressing be evening dress, then usage scenario corresponds to dinner party, if dressing be show solicitude for, then usage scenario corresponds to stop
Spare time etc..Due to participating in different activity, makings and the dressing for the people for needing to embody be also it is different, participation dinner party just should be able to
It is more serious, need the color of lipstick may be darker, and lie fallow usually, then it may be more cheerful and more light-hearted, it needs
Apply brighter color;
S6: it is shown by display screen counterpart red color suggested design;Taking a picture certainly for user's upload is obtained, face is carried out
Portion's image analysis obtains the shape of face and colour of skin type of user, while obtaining the usage scenario of user's selection, compares recommended models,
The corresponding lipstick color selection scheme for providing recommendation;User can also select without usage scenario, when not getting user
Usage scenario when, system by multiple lipstick color selection schemes combine each scheme applicable scene be supplied to user select, give
The more independences of user.
The main application process of the present invention are as follows: the social networks that system first passes through acquisition magnanimity in advance thumbs up more star's dressing
Photo carries out learning training, analyzes the facial area in photo, extracts the lipstick face that the colour of skin, shape of face and lip in photo use
Color, while obtaining photo and correspond to content of text in social networks and carrying out text analyzing, extract wherein about attend occasion phase
Usage scenario label of the content of text of pass as the photo, using the colour of skin, shape of face, usage scenario as input item, lipstick color
As output item, learning training is carried out using convolutional neural networks algorithm, establishes lipstick color recommended models, and be stored in service
Device.
User uploads from after taking a picture, and the self-timer that system obtains user shines into capable pretreatment, analyzes shape of face, the skin of user
Color, after getting the usage scenario of user, the recommended models prestored in Compare System judge the lipstick color that user is suitble to, and
It result be presented to user.If user does not submit or select usage scenario, system makes up multiple lipstick colors scheme knot
The applicable scene for closing the lipstick color is supplied to user's selection.
The above embodiment is only the preferred embodiment of the present invention, and the scope of protection of the present invention is not limited thereto,
The variation and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed range.
Claims (10)
- The model building method of selection 1. a kind of lipstick is matched colors, which comprises the following steps:Model photo obtaining step: model picture is obtained;Lipstick color extraction step: the color value of the lip in model face region is extracted to obtain lipstick color data;Scene analysis step: by the clothing of personage in image analysis model picture to obtain model usage scenario;Model construction step: the lipstick color data and model usage scenario got is carried out using convolutional neural networks algorithm Learning training is to obtain recommended models.
- The model building method of selection 2. lipstick as described in claim 1 is matched colors, which is characterized in that the model photo obtains Model picture described in step thumbs up the picture that number is more than preset threshold for what is got by social media.
- The model building method of selection 3. lipstick as described in claim 1 is matched colors, which is characterized in that the scene analysis step Further include: by analyzing keyword corresponding with model picture to obtain model usage scenario.
- The model building method of selection 4. lipstick as described in claim 1 is matched colors, which is characterized in that obtain and walk in model photo It is further comprising the steps of after rapid:Model face analytical procedure: image analysis is carried out to obtain model face region to model picture;Model skin cluster step: the colour of skin in model face region is extracted to obtain model colour of skin data;Model shape of face obtaining step: face-image analysis is carried out to obtain model shape of face data to model face region.
- The model building method of selection 5. lipstick as claimed in claim 4 is matched colors, which is characterized in that the model skin cluster Step specifically includes following sub-step:Non- area of skin color in identification model facial area, the non-area of skin color include eyes, eyebrow and lip;Non- area of skin color is rejected to obtain blee region;It extracts the color in blee region and is averaged to obtain model colour of skin data.
- The model building method of selection 6. lipstick as described in claim 4 or 5 is matched colors, which is characterized in that the model construction Step specifically: using convolutional neural networks algorithm to model usage scenario and the model colour of skin data got, model face Type data and lipstick color data carry out learning training to obtain recommended models.
- 7. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program quilt Processor realizes that lipstick as claimed in any one of claims 1 to 6 is matched colors the model building method of selection when executing.
- The selection method 8. a kind of lipstick is matched colors, which comprises the following steps:Information receiving step: the selected contextual data of user is received;Lipstick recommendation step: it is matched according to contextual data with recommended models to obtain lipstick color suggested design.
- The selection method 9. lipstick as claimed in claim 8 is matched colors, which is characterized in that after information receiving step further include as Lower step:Face analysis step: image analysis is carried out to obtain user's facial area to the user picture got;Skin cluster step: skin cluster is carried out to obtain user colour data to user's face region;Shape of face obtaining step: face-image analysis is carried out to obtain user's shape of face data to user's face region;And the lipstick recommendation step specifically: according to contextual data, user's shape of face data and user colour data and recommend mould Type is matched to obtain lipstick color suggested design.
- 10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program Lipstick color matching selection method as claimed in claim 8 or 9 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810933834.6A CN109359317A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711063517.5A CN107944093A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
CN201810933834.6A CN109359317A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711063517.5A Division CN107944093A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109359317A true CN109359317A (en) | 2019-02-19 |
Family
ID=61934151
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711063517.5A Pending CN107944093A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
CN201810933834.6A Pending CN109359317A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711063517.5A Pending CN107944093A (en) | 2017-11-02 | 2017-11-02 | A kind of lipstick color matching system of selection, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN107944093A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109948548A (en) * | 2019-03-20 | 2019-06-28 | 齐鲁工业大学 | A kind of the lipstick recommended method and system of the match colors based on machine learning |
CN110162541A (en) * | 2019-05-24 | 2019-08-23 | 京东方科技集团股份有限公司 | Lipstick method for detecting color and system |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145724B (en) * | 2018-07-09 | 2022-04-01 | 上海工程技术大学 | Four-season-type person automatic distinguishing method based on person face image feature analysis |
CN110909566A (en) * | 2018-09-14 | 2020-03-24 | 奇酷互联网络科技(深圳)有限公司 | Health analysis method, mobile terminal and computer-readable storage medium |
CN109636513A (en) * | 2018-11-29 | 2019-04-16 | 北京小米移动软件有限公司 | A shield recommended method, device and storage medium based on travel information |
CN109712090A (en) * | 2018-12-18 | 2019-05-03 | 维沃移动通信有限公司 | A kind of image processing method, device and mobile terminal |
CN111460910A (en) * | 2020-03-11 | 2020-07-28 | 深圳市新镜介网络有限公司 | Face type classification method and device, terminal equipment and storage medium |
CN112801737A (en) * | 2021-01-27 | 2021-05-14 | 广州微框物联科技有限公司 | Lipstick shopping guide method and device of intelligent mirror |
CN112749996B (en) * | 2021-01-29 | 2024-02-20 | 吉林大学 | Automatic commodity recommendation method and system for unmanned lipstick vending machine |
CN113570674A (en) * | 2021-07-30 | 2021-10-29 | 精诚工坊电子集成技术(北京)有限公司 | Skin-beautifying product recommendation method and system and color matching sheet used by same |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000194835A (en) * | 1998-12-28 | 2000-07-14 | Kao Corp | Makeup advice system |
CN1292492A (en) * | 1999-10-01 | 2001-04-25 | 资生堂股份有限公司 | Method for selecting cosmetics |
CN101339612A (en) * | 2008-08-19 | 2009-01-07 | 陈建峰 | Face contour checking and classification method |
CN101668451A (en) * | 2007-03-08 | 2010-03-10 | 惠普开发有限公司 | Method and system for recommending a product based upon skin color estimated from an image |
TW201301147A (en) * | 2011-06-16 | 2013-01-01 | Jian-Wen Peng | An intelligent system and algorithms of facial analysis and hairstyle fitting |
CN104331417A (en) * | 2014-10-09 | 2015-02-04 | 深圳码隆科技有限公司 | Matching method for personnel garments of user |
CN104574310A (en) * | 2014-12-31 | 2015-04-29 | 深圳市金立通信设备有限公司 | Terminal |
CN105809461A (en) * | 2014-12-30 | 2016-07-27 | Tcl集团股份有限公司 | Method, system and intelligent device for recommending jewelry |
CN105956150A (en) * | 2016-05-12 | 2016-09-21 | 张家港索奥通信科技有限公司 | Method and apparatus for generating hair style and makeup matching suggestions of a user |
CN106055893A (en) * | 2016-05-27 | 2016-10-26 | 杭州土网络科技有限公司 | Clothes matching scheme generation method based on fashion template database and automatic matching |
CN106108523A (en) * | 2016-08-22 | 2016-11-16 | 陈云 | A kind of portable intelligent cosmetic mirror, cosmetic aid system and method |
CN106203263A (en) * | 2016-06-27 | 2016-12-07 | 辽宁工程技术大学 | A kind of shape of face sorting technique based on local feature |
CN107123027A (en) * | 2017-04-28 | 2017-09-01 | 广东工业大学 | A kind of cosmetics based on deep learning recommend method and system |
CN107153805A (en) * | 2016-03-02 | 2017-09-12 | 北京美到家科技有限公司 | Customize makeups servicing unit and method |
CN109165428A (en) * | 2018-08-08 | 2019-01-08 | 浙江敦奴联合实业股份有限公司 | A kind of intelligent clothing customization platform |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030064350A1 (en) * | 2001-10-01 | 2003-04-03 | Gilles Rubinstenn | Beauty advisory system and method |
US20040125996A1 (en) * | 2002-12-27 | 2004-07-01 | Unilever Home & Personal Care Usa, Division Of Conopco, Inc. | Skin diagnostic imaging method and apparatus |
KR20120051342A (en) * | 2010-11-12 | 2012-05-22 | 한국전자통신연구원 | System and method for recommending sensitive make-up based on user color sense |
CN104873197B (en) * | 2014-02-28 | 2020-01-17 | 花王株式会社 | Skin evaluation method and recommendation method for skin care product or cosmetic |
CN106649465A (en) * | 2016-09-26 | 2017-05-10 | 珠海格力电器股份有限公司 | Recommendation and acquisition method and device of cosmetic information |
-
2017
- 2017-11-02 CN CN201711063517.5A patent/CN107944093A/en active Pending
- 2017-11-02 CN CN201810933834.6A patent/CN109359317A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000194835A (en) * | 1998-12-28 | 2000-07-14 | Kao Corp | Makeup advice system |
CN1292492A (en) * | 1999-10-01 | 2001-04-25 | 资生堂股份有限公司 | Method for selecting cosmetics |
CN101668451A (en) * | 2007-03-08 | 2010-03-10 | 惠普开发有限公司 | Method and system for recommending a product based upon skin color estimated from an image |
CN101339612A (en) * | 2008-08-19 | 2009-01-07 | 陈建峰 | Face contour checking and classification method |
TW201301147A (en) * | 2011-06-16 | 2013-01-01 | Jian-Wen Peng | An intelligent system and algorithms of facial analysis and hairstyle fitting |
CN104331417A (en) * | 2014-10-09 | 2015-02-04 | 深圳码隆科技有限公司 | Matching method for personnel garments of user |
CN105809461A (en) * | 2014-12-30 | 2016-07-27 | Tcl集团股份有限公司 | Method, system and intelligent device for recommending jewelry |
CN104574310A (en) * | 2014-12-31 | 2015-04-29 | 深圳市金立通信设备有限公司 | Terminal |
CN107153805A (en) * | 2016-03-02 | 2017-09-12 | 北京美到家科技有限公司 | Customize makeups servicing unit and method |
CN105956150A (en) * | 2016-05-12 | 2016-09-21 | 张家港索奥通信科技有限公司 | Method and apparatus for generating hair style and makeup matching suggestions of a user |
CN106055893A (en) * | 2016-05-27 | 2016-10-26 | 杭州土网络科技有限公司 | Clothes matching scheme generation method based on fashion template database and automatic matching |
CN106203263A (en) * | 2016-06-27 | 2016-12-07 | 辽宁工程技术大学 | A kind of shape of face sorting technique based on local feature |
CN106108523A (en) * | 2016-08-22 | 2016-11-16 | 陈云 | A kind of portable intelligent cosmetic mirror, cosmetic aid system and method |
CN107123027A (en) * | 2017-04-28 | 2017-09-01 | 广东工业大学 | A kind of cosmetics based on deep learning recommend method and system |
CN109165428A (en) * | 2018-08-08 | 2019-01-08 | 浙江敦奴联合实业股份有限公司 | A kind of intelligent clothing customization platform |
Non-Patent Citations (2)
Title |
---|
冯晓冉;: "浅析服装流行的传播媒介", 山东纺织经济, no. 07, pages 31 - 34 * |
项杨雪;陈雪颂;陈劲;: "服装流行趋势预测网络技术演进路径:基于科学计量学的分析", 图书情报工作, no. 2, pages 119 - 126 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109948548A (en) * | 2019-03-20 | 2019-06-28 | 齐鲁工业大学 | A kind of the lipstick recommended method and system of the match colors based on machine learning |
CN110162541A (en) * | 2019-05-24 | 2019-08-23 | 京东方科技集团股份有限公司 | Lipstick method for detecting color and system |
Also Published As
Publication number | Publication date |
---|---|
CN107944093A (en) | 2018-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109359317A (en) | A kind of lipstick is matched colors the model building method and lipstick color matching selection method of selection | |
US10799010B2 (en) | Makeup application assist device and makeup application assist method | |
CN108121957B (en) | Method and device for pushing beauty material | |
US10529115B2 (en) | Generating cartoon images from photos | |
JP7020626B2 (en) | Makeup evaluation system and its operation method | |
CN108898579A (en) | A kind of image definition recognition methods, device and storage medium | |
CN108182232B (en) | Personage's methods of exhibiting, electronic equipment and computer storage media based on e-book | |
CN108765268A (en) | A kind of auxiliary cosmetic method, device and smart mirror | |
WO2015122195A1 (en) | Impression analysis device, game device, health management device, advertising support device, impression analysis system, impression analysis method, program, and program recording medium | |
CN108182714A (en) | Image processing method and device, storage medium | |
US11010894B1 (en) | Deriving a skin profile from an image | |
JP7242848B2 (en) | Systems and methods for providing personalized product recommendations using deep learning | |
CN110235169A (en) | Evaluation system of making up and its method of operating | |
CN106951448A (en) | A kind of personalization, which is worn, takes recommendation method and system | |
US20220202168A1 (en) | Digital makeup palette | |
CN107729380A (en) | Clothing matching method, terminal, terminal | |
Park et al. | An automatic virtual makeup scheme based on personal color analysis | |
CN107317974A (en) | A kind of makeups photographic method and device | |
CN107609487B (en) | User head portrait generation method and device | |
US11657553B2 (en) | Digital makeup artist | |
CN109284666A (en) | A kind of dress ornament suggested design based on image recognition and big data | |
CN112083863A (en) | Image processing method and device, electronic equipment and readable storage medium | |
KR101757184B1 (en) | System for automatically generating and classifying emotionally expressed contents and the method thereof | |
US11321882B1 (en) | Digital makeup palette | |
CN109376661A (en) | Method and apparatus for output information |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |