CN110069716A - A kind of makeups recommended method, system and computer readable storage medium - Google Patents
A kind of makeups recommended method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN110069716A CN110069716A CN201910357049.5A CN201910357049A CN110069716A CN 110069716 A CN110069716 A CN 110069716A CN 201910357049 A CN201910357049 A CN 201910357049A CN 110069716 A CN110069716 A CN 110069716A
- Authority
- CN
- China
- Prior art keywords
- makeups
- feature
- individualized feature
- facial
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of makeups recommended method, system and computer readable storage medium, this method comprises: S1. obtains the individualized feature of user;S2. the individualized feature is input in decision matrix, generates recommendation results through operation;The decision matrix includes the set of the decision function of multiple adjustable dimensions of facial single-element, and the recommendation results include the set of the makeups means of multiple adjustable dimensions of facial single-element.In the decision matrix that collection by the way that the individualized feature of user to be input to the decision function of multiple adjustable dimensions including facial single-element is combined into; to which operation generates the recommendation results of the set of the makeups means of multiple adjustable dimensions including facial single-element; it can generate finer makeups and recommend, and efficiently and effectively can provide individual instructions for the daily makeup activity of ordinary populace.
Description
Technical field
The present invention relates to human-computer interaction technique field more particularly to a kind of makeups recommended methods, system and computer-readable
Storage medium.
Background technique
In recent years, people produce frightened to the pursuit of a beautiful face so that cosmetics and lift face industry flourish
The economic benefit of people.Makeup is basis and important a part in personal image design, and public used study side of making up
Method is mainly to watch the video and article that makeups bloger provides on network, or kith and kin instruct in words and by deeds at one's side.These methods are not
The quality of Knowledge Source is only depended critically upon, and does not have the specific aim to personal appearance condition, therefore people generally require to lead to
It crosses and finds out the dressing for being suitble to oneself up to several months even more long time.
For ordinary populace, the source that more profession and feasible personalized makeup are recommended at present is mainly under line
Charged counsel or training service;With internet relevant method be send oneself photo to makeups bloger, shape-designing teacher, specially
The professionals such as industry make up artist reply corresponding text by them or picture makeup are suggested.But these methods are at present also much
Not enough specification, the Specialized Quality of attendant is very different, but universal higher, the counseling services especially under line of charging, often
It is not that general public can be born easily.
Currently, essence and feature about high attraction face, scholars proposed many hypothesis and standard.Such as west
As the age of recent antiquity allusion quotation rule, golden ratio rule, " three five, the front yards " of ancient Chinese etc.;That delivers both at home and abroad sets about personal image
Meter and academic paper, the periodicals and magazines of dressing are less;In computer field, research relevant to makeup is but really many, such as
Virtual makeup, dressing effect migration etc..
(1) human face photo beautification is directly changed the physiology of face in photo using traditional images method and deep learning method
Feature is with the beautiful face that is near the mark.
(2) virtual makeup, which mainly has, is divided into the scheme based on two dimensional image and two kinds of the scheme based on 3-D image.User
A target human face photo is uploaded, is operated after being selected in the makeup virtual tool (such as foundation cream, lipstick, eyebrow pencil) that system provides,
Effect after system output makeup.
(3) dressing effect migration is intended to that target facial image will be moved to reference to the dressing effect in facial image, but still
So retain the feature of target image.
These researchs only reside within the generation of high attraction face, attraction prediction, photo beautification, virtual makeup at present
In the fields such as effect preview, current practical application also only has the reference role of lift face doctor, in daily life for people
There is no substantive helps for the promotion of personal image.It is noted that existing virtual make-up technique is only in original image
Texture processing and map overlay effect are carried out as on the basis of, primarily serve uniform color and enhances the effect of face, with reality
Dressing effect and difference in life, can not provide effective reference for masses.Also lacking at present to be efficiently and effectively common
Public daily makeup activity provides the recommender system of individual instructions.
Summary of the invention
To solve the above problems, the present invention proposes a kind of makeups recommended method, system and computer readable storage medium.
The present invention provides a kind of makeups recommended method, includes the following steps: that S1. obtains the individualized feature of user;S2. will
The individualized feature is input in decision matrix, generates recommendation results through operation;The decision matrix includes the single member of face
The set of the decision function of multiple adjustable dimensions of element, the recommendation results include multiple adjustable dimensions of facial single-element
The set of makeups means.
In some embodiments, the individualized feature for obtaining user includes: the facial image for acquiring user, and to institute
It states facial image and carries out feature identification the first individualized feature of acquisition.The facial image includes two dimensional image or 3-D image;
First individualized feature includes color characteristic, the distance feature based on two dimensional image and angle character, is based on 3-D image
Depth characteristic.
In some embodiments, the individualized feature for obtaining user further include: pass through the interrogation reply system of human-computer interaction
Obtain the first individualized feature and second individual character feature of supplement.The second individual character feature includes: that the makings of hobby is inclined
It is biased to adornment sense.
Wherein, the decision function of the single adjustable dimension of facial single-element includes: to influence the facial single-element
The individualized feature of single adjustable dimension and the set of weight.
In some embodiments, further includes: S3. is polished and presented to the recommendation results, and during presentation
Receive the feedback result of user;The polishing includes the explanation increased to recommendation results, and described explain includes picture and text, note or reality
Trample simulation drawing.S4. the decision matrix is adjusted according to the feedback result, while carries out popularization propagation.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer journey
Makeups recommended method as described above is realized when sequence is executed by processor.
The present invention also provides a kind of makeups recommender systems, comprising: feature obtains module, and the personalization for obtaining user is special
Sign;Decision matrix module, for the individualized feature to be input to decision matrix and generates recommendation results through operation;It is described to determine
Plan matrix includes the set of the decision function of multiple adjustable dimensions of facial single-element, and the recommendation results include that face is single
The set of the makeups means of multiple adjustable dimensions of element.
Beneficial effects of the present invention: can including the multiple of facial single-element by being input to the individualized feature of user
In the decision matrix for adjusting the collection of the decision function of dimension to be combined into, so that it includes the multiple adjustable of facial single-element that operation, which generates,
The recommendation results of the set of the makeups means of dimension can generate finer makeups and recommend, can efficiently and effectively be common
Public daily makeup activity provides individual instructions.
Detailed description of the invention
Fig. 1 is the flow diagram of makeups recommended method in the embodiment of the present invention.
Fig. 2 is the first individualized feature schematic diagram in the embodiment of the present invention on facial image.
Fig. 3 is that the adjustable dimension of eyebrow in the embodiment of the present invention splits schematic diagram.
Fig. 4 is that the adjustable dimension of lip in the embodiment of the present invention splits schematic diagram.
Fig. 5 is that the adjustable dimension of eyes in the embodiment of the present invention splits schematic diagram.
Fig. 6 is the frame diagram of makeups recommender system in the embodiment of the present invention.
Fig. 7 is each functional flow diagram of the makeups recommender system of user perspective in the embodiment of the present invention.
Fig. 8 a-8c is that the makeups of the embodiment of the present invention are reported.
Specific embodiment
With reference to embodiment and compares attached drawing invention is further described in detail, it should be emphasised that,
Following the description is only exemplary, the range and its application being not intended to be limiting of the invention.Based on the embodiment of the present invention,
Every other embodiment obtained by those of ordinary skill in the art without making creative efforts, belongs to this hair
The range of bright protection.
The present embodiment provides a kind of makeups recommended methods, as shown in Figure 1, including the following steps:
Step 100, the individualized feature for obtaining user.
Acquisition for user individual feature can acquire the facial image (two of user with multi-angle by camera
Tie up image or 3-D image) and pass through the interrogation reply system of human-computer interaction and supplement and obtain.Individualized feature includes by acquisition people
Face image simultaneously carries out the first individualized feature that feature identification obtains and needs to obtain by the interrogation reply system of human-computer interaction
The first individualized feature and second individual character feature of supplement.
It may include: color characteristic (such as the colour of skin, color development, whether there is black eye etc.), base for the first individualized feature
In the distance feature and angle character of two dimensional image, the depth characteristic based on 3-D image.If the facial image of acquisition is two
Image is tieed up, then can not directly obtain the first individualized feature (such as depth characteristic) of part, then collected first is personalized special
Sign may only include: color characteristic, distance feature and angle character, but can be supplemented and be obtained by the interrogation reply system of human-computer interaction
The first partial individualized feature;If the facial image of acquisition is 3-D image, can obtain more than including but not limited to
Each feature.
Signal of the first individualized feature of part on facial image is as shown in Fig. 2, include the distance based on two dimensional image
Feature (D1-D18, B3, B6) and angle character (A1), color characteristic (B1), and based on 3-D image depth characteristic (B2,
B4, B5), specific as follows:
One first individualized feature of table
Feature serial number | Symbol indicates | Characterizing definition |
1 | D1 | The longitudinal length of whole face |
2 | D2 | The transverse width of whole face |
3 | D3 | Fore-and-aft distance of the hair line top to place between the eyebrows |
4 | D4 | Fore-and-aft distance of the place between the eyebrows to nose pillar |
5 | D5 | Fore-and-aft distance of the nose pillar to chin minimum point |
6 | D6 | The width of face at temple height |
7 | D7 | When amimia at the corners of the mouth height face width |
8 | D8 | The lateral distance (face intensity can be embodied) of two inner eye corners |
9 | D9 | The width of nose the widest part |
10 | D10 | The lateral distance at tail of the eye face edge at tail of the eye height |
11 | D11 | Lateral distance of the inner eye corner to the tail of the eye |
12 | D12 | The transverse width of palpebral fissure |
13 | D13 | Fore-and-aft distance of the minimum point to eyes highest point in the middle part of eyebrow |
14 | D14 | Longitudinal height of eyes |
15 | D15 | Length in people |
16 | D16 | The thickness in upper lip thickness |
17 | D17 | The thickness in lower lip thickness |
18 | D18 | The longitudinal length of chin |
19 | A1 | The average value for the angle that the connecting line and horizontal line of two inner eye corners to the tail of the eye are formed |
20 | B1 | The color of hair |
21 | B2 | The three-dimensional degree of brow ridge |
22 | B3 | Width (for example single-edge eyelid, then for 0) of double-edged eyelid |
23 | B4 | The height at mountain root |
24 | B5 | Temporal recess degree |
25 | B6 | Width in people |
The first individualized feature of part as above, can be it is quantitative, be also possible to qualitatively.Such as: the width of double-edged eyelid
Degree, the width in people, temple recess degree etc..If facial image clarity is high, it can be known by feature and be obtained otherwise
Obtain the quantitative feature;If facial image clarity is low, the spy for being relatively difficult to obtain quantification otherwise is known by feature
Sign self can perceive some feature by the interrogation reply system of human-computer interaction acquisition user qualitative as a result, such as:
The wider width of double-edged eyelid/narrow/nothing, wider width/narrow/nothing in people, temple are with/without recess etc..
The obtaining step of first individualized feature can be closed using method more mature in the prior art, such as face
Key point detection etc..
It may include the adornment at age, gender, skin quality type, the makings of hobby deviation, hobby for second individual character feature
Sense deviation etc.;It also may include the feature of user's autognosis, such as: up/down half opens that face is good-looking, and face concentration degree is high/low, eyebrow
At random/rule of hair etc..
Individualized feature is input in decision matrix by step 200, generates recommendation results through operation.
Decision matrix be include facial single-element multiple adjustable dimensions decision function set, recommendation results are packets
Include the set of the makeups means of multiple adjustable dimensions of facial single-element.
Building for decision matrix, detailed process is as follows:
1) the high attraction faceform based on makeups alterable features
Fig. 2 is high attraction faceform, and each first individualized feature has corresponding reference value.In order to by the people of user
Face, which carries out makeups, to be recommended so as to high attraction faceform snap, the thinking of major makeups bloger is typically all to be directed to people on network
The single facial elements (such as eyebrow, eyes, lip, nose) of face carry out makeups modification.Therefore the present embodiment uses for reference this think of
Road, carries out that the feature based on single facial elements is corresponding with makeups means first, and each single facial elements of analyzing influence
Makeups gimmick corresponding to factor (individualized feature) and each factor.
Whether can interact as between each facial single-element of face, due to the improvement space of makeups and little, cause
Effect mostly made up to " defect ", the degree made up is not enough to cause entire facial geometry that big change occurs;Therefore
It can not have to consider the influence between each facial single-element of face.
By taking the eyebrow of facial single-element as an example, the factor (individualized feature) and the corresponding beauty of each factor of eyebrow are influenced
Adornment gimmick such as following table two.
The factor and the corresponding makeups gimmick of each factor of the influence eyebrow of table two
2) the adjustable dimension of single facial elements is split
In order to which the quantitative criterion of face attraction and matched makeups gimmick are parameterized, code, with
Executable decision matrix is formed, all features of face are distinguished by the methods of organ, region in the present embodiment and are split into one
It is a influence face attraction facial single-element (such as eyebrow, glasses, lip, nose), it is each face single-element again from
Geometric angle splits into not interactional several adjustable dimensions.
The method of exhaustion is used to adjustable dimension split process in the present embodiment, that is, enumerates that change facial single-element all several
The adjustable dimension that has an impact to face attraction and can be effectively improved by makeup means on what.Such as the thickness of lip
It is an adjustable dimension influential on face attraction, the value for dimension that this is adjustable can be changed (benefit by makeup means
Change the thickness in lip perception with lipstick and bottom adornment product);Width in lip transverse direction is also to have an impact to face attraction
An adjustable dimension, but the value of the adjustable dimension can not be changed by makeup means, therefore this adjustable dimension is disregarded
Enter considering for recommender system;It is independent of each other between each adjustable dimension, such as the thickness of upper lip and lower lip can change respectively, it is right
The change of upper lip thickness will not directly result in the variation of lower lip thickness.
To " eyebrow ", this single facial elements is split as 9 adjustable dimensions being independent of each other in one of them embodiment
Degree: eyebrow peak position, length, brows distance, rugosity looks spacing, eyebrow tail height, degree of choosing, concentration, marginal definition.Eyebrow can
Dimension is adjusted to split schematic diagram as shown in figure 3, shown in the definition of adjustable dimension table three specific as follows:
The adjustable dimension of three eyebrow of table splits definition
In another embodiment, the adjustable dimension of feature that 9 are independent of each other is split as to " lip " this facial elements:
Upper lip thickness, lower lip thickness, upper lip corners of the mouth shape, lower lip corners of the mouth shape, lip peak depth, lip peak width, color, texture, edge
Clarity.The adjustable dimension of lip splits schematic diagram as shown in figure 4, shown in the definition of adjustable dimension table four specific as follows:
The adjustable dimension of four lip of table splits definition
Serial number | Symbol | Adjustable dimension description/characterizing definition |
1 | Z1 | The thickness in upper lip thickness |
2 | Z2 | The thickness in lower lip thickness |
3 | Z3 | Lip peak width |
4 | Z4 | Lip peak depth |
5 | Z5 | Color |
6 | Z6 | Texture |
7 | Z7 | Marginal definition |
8 | Z8 | Upper lip corners of the mouth shape |
9 | Z9 | Lower lip corners of the mouth shape |
In another embodiment, the adjustable dimension of feature that 9 are independent of each other is split as to " eyes " this facial elements:
Informer is thick/and thin, informer hang down/chooses, informer elongates degree, eye head informer, eyelashes, eye shadow shape, eye shadow depth, sleeping silkworm, U.S. pupil.Eye
The adjustable dimension of eyeball splits schematic diagram as shown in figure 5, shown in the definition of adjustable dimension table five specific as follows:
The adjustable dimension of five eyes of table splits definition
Serial number | Symbol | Adjustable dimension description/characterizing definition |
1 | Y1 | The lateral distance that eye tail informer elongates |
2 | Y2 | Angle is chosen at eye tail informer's elongation |
3 | Y3 | The depth of eye shadow |
4 | Y4 | The thickness of informer |
5 | Y5 | U.S. pupil |
6 | Y6 | Eye head informer |
7 | Y7 | Sleeping silkworm |
8 | Y8 | Eye shadow shape |
9 | Y9 | Eyelashes |
3) decision matrix is constructed
As unit of single facial elements, after each element is carried out adjustable dimension fractionation, next will according to for
It is personalized special by which to sort out each adjustable dimension for the single adoptable makeups gimmick of facial elements to high attraction face
Difference beauty corresponding in situation above and below the influence of sign, the corresponding level threshold value of each individualized feature and eigenvalue threshold
Adornment gimmick.The same adjustable dimension of the facial elements may be corresponded between different individualized features different, even opposite
Makeup gimmick, therefore also need to assign different weights for each individualized feature, so that recommender system is when calculating comprehensive point
The optimal solution under restrictive condition is precipitated.
By taking " eyebrow " this single facial elements as an example, the adjustable each individualized feature of dimension of difference of eyebrow is for final
The influence of recommendation results is as shown in following table six:
The decision function of the adjustable dimension of six eyebrow of table
From table six it is known that for " thick/thin " of eyebrow this adjustable dimension, it is (or a that there are four individualized features
Ratio between property feature) this adjustable dimension is had an impact, wherein " B2 (the three-dimensional degree of brow ridge) " and " D14 (height of eyes
Degree) " it provides constraints to the thickness of eyebrow, the threshold of the two features of " D1/D2 (face length/face is wide) " and " looks distance/eye is high "
Value is 2 and 1 respectively, and when calculating, the weight of the two features is respectively 2/3 and 1/3.
In other examples, for " lip " this single facial elements, the decision function of each adjustable dimension is such as
Shown in following table seven:
The decision function of the adjustable dimension of seven lip of table
Serial number | Adjustable dimension | The decision function of single adjustable dimension |
1 | Lip peak significant degree | 0.7* (0.6*D18/D15)+0.3*D9/D8=obvious degree |
2 | Upper lip thickness | The upper lip thickness of 0.7* (1.7D15/D18)+0.3*D8/D9= |
3 | Lower lip thickness | (0.6*D18/D15)=lower lip thickness |
4 | Upper lip corners of the mouth shape | (1.4*D16/D17)=acuity |
5 | Lower lip corners of the mouth shape | (0.7*D17/D16)=acuity |
6 | Color | It is gentle sweet |
7 | Texture | Pure and honest dumb light |
8 | Clarity | Clarity |
In another embodiment, for " eyes " this single facial elements, the decision function of each adjustable dimension is such as
Shown in following table eight:
The decision function of the adjustable dimension of eight eyes of table
Serial number | Adjustable dimension | Decision function |
1 | Informer is thick/thin | B3 (limitation);1.2*D10/D8=emphasizes a tail |
2 | Informer hang down/chooses | A1/10 °=degree of choosing in itself |
3 | Informer elongates degree | D12 (limitation);1.2*D10/D8=elongates degree |
4 | Eye head informer | D11/D8=head informers |
5 | Eyelashes | 0.8*D13/D14=mascara/false eyelashes necessity |
6 | Eye shadow shape | 1.2*D10/B2+D14/0.8*D13=elongates degree |
7 | Eye shadow depth | Eye socket depth (limitation) 0.8*D13/D14 |
8 | Sleeping silkworm | Black eye depth (limitation) crouches silkworm necessity degree |
9 | U.S. pupil | The necessary degree of U.S. pupil |
The different adjustable each individualized features of dimension of influence situation according to to(for) consequently recommended result, with the thinking of mathematics
These influence situations are arranged into the decision function of the adjustable dimension for exportable single value, then by the decision of each adjustable dimension
Function integration, forms the decision matrix of the face single-element.
By step 100 collected first individualized feature be correspondingly input to the decision square of each facial single-element
In battle array, recommendation results are generated through operation.
In addition, also obtaining the second individual character feature for having user in step 100 other than the first individualized feature.To fill
Divide the personal charm demand for considering user, to the adjustable dimension of each of each single facial elements in the building process of recommendation results
Such as " makings deviation " and " adornment sense deviation " considering in terms of the two is all added.And to different adjustable dimensions, due to not
It is different for the influence of " makings " and " attraction " in terms of the two with makeups gimmick, therefore given not on the two subjective items
Same weight.
Different score values are arranged to represent the different hobby makings deviation of user and adornment in this facial single-element for eyebrow
It is biased to, in following table nine, is set as -2, -1,0,1,2, value is lower, represents user and is more partial to soft natural makings wind
Lattice, value is higher, represents user and is more partial to the exquisite makings style for having gas field.
The makings of each adjustable dimension/adornment sense score value in nine eyebrow of table
It is to be transported for the weighting function of the makings weight of each adjustable dimension in decision matrix in eyebrow such as following table ten
After the recommendation for calculating adjustable dimension a certain for eyebrow, " makings addition " weighted value of the adjustable dimension is multiplied with result,
Obtain the final makeups recommendation results that the adjustable dimension comprehensively considered user's subjective preferences.
The makings weight of the adjustable dimension of each of ten eyebrow of table
Based on makeups recommended method as above, by being input to the individualized feature of user including facial single-element
In the decision matrix that the collection of the decision function of multiple adjustable dimensions is combined into, so that it includes the more of facial single-element that operation, which generates,
The recommendation results of the set of the makeups means of a adjustable dimension can generate finer makeups and recommend, can be efficiently and effectively
Individual instructions are provided for the daily makeup activity of ordinary populace.
Makeups recommended method as above, include thes steps that as follows:
Step 300 is polished and is presented to the recommendation results, and the feedback knot of user is received during presentation
Fruit;The polishing includes the explanation increased to recommendation results, described to explain to include picture and text, explain or practice simulation drawing.
Step 400 adjusts the decision matrix according to the feedback result, while carrying out popularization propagation.
The present embodiment also provides a kind of system, as shown in Figure 6, comprising: individualized feature obtains module, decision matrix mould
Block, polishing module, user feedback module and popularization propagation module.
It is obtained by way of progress man face image acquiring and human-computer interaction question and answer being obtained in module in individualized feature
Then individualized feature is input to decision matrix and generates recommendation results through operation by the individualized feature of user;Decision matrix
The set of the decision function of multiple adjustable dimensions including facial single-element, recommendation results include the multiple of facial single-element
The set of the makeups means of adjustable dimension.Then recommendation results are polished by polishing module (including increase to recommending to tie
The explanation of fruit, such as: simulation drawing is explained or practiced to picture and text) and be presented to the user, user is submitted by feedback module to feed back and leads to
It crosses popularization propagation module and carries out popularization propagation, obtain more incomes and help the popularization of product, more users is caused to use production
The input of product progress data.
For user perspective, each functional flow diagram of the makeups recommender system is as shown in Figure 7.For the makeups report after polishing
It accuses, part is illustrated as shown by figures 8 a-8 c.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The part that technology contributes can be embodied in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, calculate
Machine, server or network equipment etc.) execute the embodiment of the present invention method.
The above content is combine it is specific/further detailed description of the invention for preferred embodiment, cannot recognize
Fixed specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs,
Without departing from the inventive concept of the premise, some replacements or modifications can also be made to the embodiment that these have been described,
And these substitutions or variant all shall be regarded as belonging to protection scope of the present invention.
Claims (10)
1. a kind of makeups recommended method, which comprises the steps of:
S1. the individualized feature of user is obtained;
S2. the individualized feature is input in decision matrix, generates recommendation results through operation;The decision matrix includes face
The set of the decision function of multiple adjustable dimensions of portion's single-element, the recommendation results include the multiple of facial single-element can
Adjust the set of the makeups means of dimension.
2. makeups recommended method as described in claim 1, which is characterized in that it is described obtain user individualized feature include:
The facial image of user is acquired, and feature identification is carried out to the facial image and obtains the first individualized feature.
3. makeups recommended method as claimed in claim 2, which is characterized in that the facial image includes two dimensional image or three-dimensional
Image;First individualized feature includes color characteristic, the distance feature based on two dimensional image and angle character, based on three-dimensional
The depth characteristic of image.
4. makeups recommended method as claimed in claim 2, which is characterized in that the individualized feature for obtaining user also wraps
It includes: obtaining the first individualized feature and second individual character feature of supplement by the interrogation reply system of human-computer interaction.
5. makeups recommended method as claimed in claim 4, which is characterized in that the second individual character feature includes: hobby
Makings is biased to and adornment sense is biased to.
6. makeups recommended method as described in claim 1, which is characterized in that the single adjustable dimension of the face single-element
Decision function include: the individualized feature for the single adjustable dimension for influencing the facial single-element and the set of weight.
7. makeups recommended method as described in claim 1, which is characterized in that further include:
S3. the recommendation results are polished and is presented, and receive the feedback result of user during presentation;The polishing
It is described to explain to include picture and text, explain or practice simulation drawing including increasing the explanation to recommendation results.
8. makeups recommended method as claimed in claim 7, which is characterized in that further include:
S4. the decision matrix is adjusted according to the feedback result, while carries out popularization propagation.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Claim 1-8 described in any item makeups recommended methods are realized when processor executes.
10. a kind of makeups recommender system characterized by comprising
Individualized feature obtains module, for obtaining the individualized feature of user;
Decision matrix module, for the individualized feature to be input to decision matrix and generates recommendation results through operation;It is described
Decision matrix includes the set of the decision function of multiple adjustable dimensions of facial single-element, and the recommendation results include that face is single
The set of the makeups means of multiple adjustable dimensions of one element.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910357049.5A CN110069716B (en) | 2019-04-29 | 2019-04-29 | Beautiful makeup recommendation method and system and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910357049.5A CN110069716B (en) | 2019-04-29 | 2019-04-29 | Beautiful makeup recommendation method and system and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110069716A true CN110069716A (en) | 2019-07-30 |
CN110069716B CN110069716B (en) | 2022-03-18 |
Family
ID=67369571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910357049.5A Active CN110069716B (en) | 2019-04-29 | 2019-04-29 | Beautiful makeup recommendation method and system and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110069716B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553219A (en) * | 2020-04-21 | 2020-08-18 | 海信集团有限公司 | Data processing method and intelligent equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108229415A (en) * | 2018-01-17 | 2018-06-29 | 广东欧珀移动通信有限公司 | Information recommendation method, device, electronic equipment and computer readable storage medium |
KR20180110842A (en) * | 2017-03-30 | 2018-10-11 | 최진은 | Customized semi-permanent make-up recommendation system based on virtual experience and its service method |
CN108682050A (en) * | 2018-08-16 | 2018-10-19 | Oppo广东移动通信有限公司 | U.S. face method and apparatus based on threedimensional model |
CN108920490A (en) * | 2018-05-14 | 2018-11-30 | 京东方科技集团股份有限公司 | Assist implementation method, device, electronic equipment and the storage medium of makeup |
CN109671142A (en) * | 2018-11-23 | 2019-04-23 | 南京图玩智能科技有限公司 | A kind of intelligence makeups method and intelligent makeups mirror |
-
2019
- 2019-04-29 CN CN201910357049.5A patent/CN110069716B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
KR20180110842A (en) * | 2017-03-30 | 2018-10-11 | 최진은 | Customized semi-permanent make-up recommendation system based on virtual experience and its service method |
CN108229415A (en) * | 2018-01-17 | 2018-06-29 | 广东欧珀移动通信有限公司 | Information recommendation method, device, electronic equipment and computer readable storage medium |
CN108920490A (en) * | 2018-05-14 | 2018-11-30 | 京东方科技集团股份有限公司 | Assist implementation method, device, electronic equipment and the storage medium of makeup |
CN108682050A (en) * | 2018-08-16 | 2018-10-19 | Oppo广东移动通信有限公司 | U.S. face method and apparatus based on threedimensional model |
CN109671142A (en) * | 2018-11-23 | 2019-04-23 | 南京图玩智能科技有限公司 | A kind of intelligence makeups method and intelligent makeups mirror |
Non-Patent Citations (1)
Title |
---|
李阳帆: "东方女性人脸妆容推荐算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553219A (en) * | 2020-04-21 | 2020-08-18 | 海信集团有限公司 | Data processing method and intelligent equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110069716B (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guo et al. | Face authentication with makeup changes | |
US10799010B2 (en) | Makeup application assist device and makeup application assist method | |
KR101109793B1 (en) | Eye form classifying method, form classification map, and eye cosmetic treatment method | |
CN107506559B (en) | Star face shaping makeup recommendation method and device based on face similarity analysis | |
CN109840825A (en) | The recommender system of physical features based on user | |
WO2014119242A1 (en) | Makeup application assistance device, makeup application assistance method, and makeup application assistance program | |
Kagian et al. | A machine learning predictor of facial attractiveness revealing human-like psychophysical biases | |
CN105118082A (en) | Personalized video generation method and system | |
CN107784630B (en) | Method, device and terminal for turning attributes of face image | |
CN101779218A (en) | Makeup simulation system, makeup simulation apparatus, makeup simulation method, and makeup simulation program | |
CN106293362A (en) | A kind of guiding cosmetic equipment | |
CN104331564B (en) | Adorn guidance method and terminal device based on terminal device | |
Roth et al. | Quantifying the arch position of the female eyebrow | |
Mao et al. | Automatic classification of chinese female facial beauty using support vector machine | |
Matsushita et al. | Eye shape illusions induced by eyebrow positions | |
CN102376051A (en) | Computer try-on glass matching system in coincidence with human engineering and method thereof | |
CN110069716A (en) | A kind of makeups recommended method, system and computer readable storage medium | |
CN109376661A (en) | Method and apparatus for output information | |
Dantcheva et al. | Assessment of female facial beauty based on anthropometric, non-permanent and acquisition characteristics | |
Xia et al. | Semantic translation of face image with limited pixels for simulated prosthetic vision | |
Choi | Korean fashion media, beauty ideals, and colorism: Examining the prominence of whiteness between 2013 and 2017 in Céci magazine | |
CN112270221A (en) | Garment personalized recommendation method fusing four-season color theory | |
Zhao et al. | Data-driven facial attractiveness of Chinese male with epoch characteristics | |
Choudhary et al. | Indexing facial attractiveness and well beings using machine learning | |
CN109965493A (en) | A kind of split screen interactive display method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |