CN106446207A - Makeup database creating method, personalized makeup aiding method and personalized makeup aiding device - Google Patents
Makeup database creating method, personalized makeup aiding method and personalized makeup aiding device Download PDFInfo
- Publication number
- CN106446207A CN106446207A CN201610873350.8A CN201610873350A CN106446207A CN 106446207 A CN106446207 A CN 106446207A CN 201610873350 A CN201610873350 A CN 201610873350A CN 106446207 A CN106446207 A CN 106446207A
- Authority
- CN
- China
- Prior art keywords
- makeups
- scheme
- key word
- document
- knowledge
- 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- 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
- G06F16/93—Document management systems
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)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
An embodiment of the invention provides a makeup database creating method, a personalized makeup aiding method and a personalized makeup aiding device. The makeup database creating method includes extracting makeup keywords from collected makeup schemes, generating makeup description files according to content structures of the makeup schemes, and giving different weights to the makeup keywords at different positions in the content structures of the makeup description files. Known making-up skills are implemented practically and effectively in reality, and personalized making-up schemes are recommended.
Description
Technical field
The present embodiments relate to Internet technical field, more particularly to a kind of makeups storehouse banking process, personalized makeups
Householder methods and its device.
Background technology
With cosmetics and instrument, step and skill, control mirror and the manual behaviour that places one's entire reliance upon in accordance with rule is taken
Making the face to human body, face and other positions carries out rendering, draws, arranges, and strengthens three-dimensional print as adjusting shape and color, covering up scarce
Fall into, expression is showed, so as to reach the purpose of beautification visual experience.
Make up and can be divided into foundation make up and emphasis cosmetic.Foundation make up refers to that color is applied on the basis of whole face, including：Clearly
Clean, moist, convergence, bottoming and face powder etc., the function with skin protection.Emphasis is made up and refers to the thin of the organs such as eye, eyelash, eyebrow, cheek, lip
Portion makes up, including：Plus eye shadow, draw informer, brushing eyelash, apply nose shadow, wipe and kermes and smear lip pomade etc., the beautiful of appearance can be increased and be in
Third dimension, can change with different occasions.The method of cosmetic has daily general cosmetic method, adapts to the special of various occasion needs
Cosmetic method, and simple and direct quick rapid-result cosmetic method etc..
And so far, except passing through, in addition to study makeup skill TV, network and magazine, there is no other more preferable canals
Road；Furthermore, numerous steps and disposal skill are related in itself by above-mentioned visible cosmetic, and for a user, even if user knows
Some makeup skills, but in practical application, as actual cosmetic environment such as cosmetics, cosmetic applicators there occurs change
Change, cause the makeup skill for being also difficult in reality efficiently and effectively implement to know, and using the real cosmetic scheme being suitable for.
Content of the invention
In view of this, one of technical problem that the embodiment of the present invention is solved be to provide a kind of makeups storehouse banking process,
Personalized makeups householder methods and its device, in order to overcome above-mentioned technical problem in prior art.
The embodiment of the present invention provides a kind of makeups storehouse banking process, and which includes：
Makeups key word is extracted from the makeups scheme of collection, makeups is generated according to the content structure of the makeups scheme and is retouched
State document；
It is to describe, in the makeups, the makeups key word that in the content structure of document, diverse location occurs to give difference
Weight.
Alternatively, in one embodiment of this invention, extracting makeups key word in the makeups scheme of collection includes：From collection
To cosmetic knowledge in extract cosmetic knowledge key word, the makeups scheme includes the cosmetic knowledge；
Document being described according to the generation makeups of the content structure of the makeups scheme includes：Content according to the cosmetic knowledge
Structural generation cosmetic knowledge description document；
It is that the makeups key word that diverse location occurs in the content structure of the cosmetic knowledge description document gives
Different weights include：It is the cosmetic knowledge of diverse location appearance in the content structure of the cosmetic knowledge description document
Key word gives different weights.
Alternatively, in one embodiment of this invention, extracting makeups key word from the makeups scheme of collection includes：From adopting
Modeling scheme key word is extracted in the modeling scheme of collection, and the makeups scheme includes the modeling scheme；
Document being described according to the generation makeups of the content structure of the makeups scheme includes：Content according to the modeling scheme
Structural generation modeling scheme describes document；
It is that the makeups key word that diverse location occurs in the content structure of the cosmetic knowledge description document gives
Different weights include：It is to describe, in the modeling scheme, the modeling scheme key word that in document, diverse location occurs to give
Different weights.
Alternatively, in one embodiment of this invention, the cosmetic knowledge includes：Knowledge entry and dressing data, described
Knowledge entry is used for characterizing the static description that makes up, and the dressing data are used for characterizing the Dynamic profiling that makes up.
Alternatively, in one embodiment of this invention, the knowledge entry includes makeup skill, cosmetic region, cosmetic handss
One of method or multiple combinations,；The dressing data include one of dressing description, cosmetic step and content of multimedia or
Multiple combinations.
Alternatively, in one embodiment of this invention, methods described also includes：Generate the management training coarse of the knowledge entry
And the management training coarse of the dressing data, and the management class of the management training coarse to the knowledge entry and the dressing data
Cheng Jinhang Data Integration.
Alternatively, in one embodiment of this invention, methods described also includes：According to tree hierarchy structure to the knowledge
The management training coarse of the management training coarse of entry and the dressing data carries out Content Management.
Alternatively, in one embodiment of this invention, also include：The makeups key word for extracting is normalized.
Alternatively, in one embodiment of this invention, also include：According to the mode of concurrent type frog retrieval can be carried out to multiple U.S.s
Adornment describes document and is stored.
Alternatively, in one embodiment of this invention, describing document to multiple makeups carries out burst storage, concurrent to carry out
Formula is retrieved.
The embodiment of the present invention provides a kind of personalization makeups householder methods, and which includes：
Coupling is carried out in the face feature classification model for pre-building to the facial image of user in real obtains use
The personalized makeups label at family；
According to described personalization data base of the makeups label described in any embodiment in carry out makeups key word
Join；
According to the different weights that the makeups key word for matching describes document diverse location and give in corresponding makeups, to bag
The makeups scheme for including the makeups key word for matching carries out the recommendation index that weight statistics obtains makeups scheme, according to the recommendation
Index assumes makeups scheme to the user.
Alternatively, in one embodiment of this invention, methods described also includes：Feature mark is carried out to sample facial image
With extract and set up faceform, with to face feature carry out classification generate feature classification model.
Alternatively, in one embodiment of this invention, feature mark is carried out to sample facial image and face is set up in extraction
Model, is included with carrying out classification generation feature classification model to face feature：
Face characteristic according to extracting carries out face shape modeling and the modeling of face texture respectively obtains face shape model
With face texture model；
Faceform is set up according to the face shape model and face texture model, classification life is carried out to face feature
Become feature classification model.
Alternatively, in one embodiment of this invention, methods described also includes：Preference information, Yong Husuo according to user
The personalized auxiliary makeups label of the birthday by information of Weather information, user on the ground combination producing of any one or more；
Makeups key word is carried out in data base according to the personalized auxiliary makeups label is in any embodiment
Coupling.
Alternatively, in one embodiment of this invention, methods described also includes：To including the makeups key word for matching
Makeups scheme carries out one-level and secondary merger sequence respectively.
The embodiment of the present invention provides a kind of makeups storehouse and builds storehouse device, and which includes：
Unit set up by document, for extracting makeups key word from the makeups scheme of collection, according to the makeups scheme
Content structure generates makeups and describes document；
Weight-assigning unit, for for describing described U.S. that in the content structure of document, diverse location occurs in the makeups
Adornment key word gives different weights.
Alternatively, in one embodiment of this invention, the document is set up unit and is further used for from the cosmetic for collecting
Cosmetic knowledge key word is extracted in knowledge, and the makeups scheme includes the cosmetic knowledge；Content according to the cosmetic knowledge
Structural generation cosmetic knowledge description document；
The weight-assigning unit is further used for being different positions in the content structure of the cosmetic knowledge description document
The makeups key word for putting appearance gives different weights and includes：Be in the content structure of the cosmetic knowledge description document
The cosmetic knowledge key word that diverse location occurs gives different weights.
Alternatively, in one embodiment of this invention, the document is set up unit and is further used for from the moulding side for gathering
Modeling scheme key word is extracted in case, and the makeups scheme includes the modeling scheme, ties according to the content of the modeling scheme
Structure generates modeling scheme and describes document；
The weight-assigning unit is further used for being different positions in the content structure of the cosmetic knowledge description document
The makeups key word for putting appearance gives different weights and includes：It is to describe diverse location in document in the modeling scheme to go out
The existing modeling scheme key word gives different weights.
The embodiment of the present invention provides a kind of personalization makeups auxiliary device, and which includes：
Tag match unit, for the face figure in the face feature classification model for pre-building to user in real
As carrying out mating the personalized makeups label for obtaining user；
Keywords matching unit, for according to described personalization makeups label in any embodiment described in data base in enter
The coupling of row makeups key word；
Makeups recommendation unit, assigns for describing document diverse location according to the makeups key word for matching in corresponding makeups
The different weights that gives, the makeups scheme to including the makeups key word for matching carries out the recommendation that weight statistics obtains makeups scheme
Index, assumes makeups scheme according to the recommendation index to the user.
Alternatively, in one embodiment of this invention, also include：Assisted tag unit, for believing according to the preference of user
Breath, the on-site Weather information of user, the birthday by information combination producing personalization auxiliary makeups mark of any one or more of user
Sign；
The Keywords matching unit is further used for according to the personalized auxiliary makeups label in any embodiment institute
The coupling of makeups key word is carried out in the data base for stating.
From above technical scheme, in the embodiment of the present invention, by extracting makeups key from the makeups scheme of collection
Word, generates makeups according to the content structure of the makeups scheme and describes document；It is the content knot for describing document in the makeups again
The makeups key word that in structure, diverse location occurs gives different weights, builds storehouse so as to complete makeups storehouse, when need to
When user recommends makeups scheme, in the face feature classification model for pre-building, the facial image of user in real is carried out
Coupling obtains the personalized makeups label of user, describes document diverse location according to the makeups key word for matching in corresponding makeups
And the different weights for giving, to including that the makeups scheme of makeups key word for matching carries out weight and count obtaining makeups scheme
Recommend index, makeups scheme is assumed to the user according to the recommendation index, to realize efficiently and effectively implementing in reality
The makeup skill that knows, the cosmetic scheme for completing personalization is recommended.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Accompanying drawing to be used needed for technology description is had to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments described in inventive embodiments, for those of ordinary skill in the art, can also obtain according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is one makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；
Fig. 2 is two makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；
Fig. 3 is three makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；
Fig. 4 is the personalized makeups aided process flow sheet schematic diagram of the embodiment of the present invention four；
Fig. 5 is the personalized makeups aided process flow sheet schematic diagram of the embodiment of the present invention five；
Fig. 6 builds storehouse apparatus structure schematic diagram for six makeups storehouse of the embodiment of the present invention；
Fig. 7 is the personalized makeups assistant apparatus structure schematic diagram of the embodiment of the present invention seven.
Specific embodiment
Certainly, the arbitrary technical scheme for implementing the embodiment of the present invention must be not necessarily required to while reaching above all excellent
Point.
In order that those skilled in the art more fully understand the technical scheme in the embodiment of the present invention, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described reality
It is only a part of embodiment of the embodiment of the present invention to apply example, rather than whole embodiments.Based on the enforcement in the embodiment of the present invention
Example, the every other embodiment obtained by those of ordinary skill in the art, should all belong to the scope of embodiment of the present invention protection.
The embodiment of the present invention is further illustrated with reference to embodiment of the present invention accompanying drawing to implement.
Fig. 1 is one makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；As shown in figure 1, which includes：
S101, from collection makeups scheme extract makeups key word, according to the content structure of the makeups scheme generate
Makeups describe document；
In the present embodiment, specifically from the cosmetic knowledge for collecting extract cosmetic knowledge key word, such as by two-way most
Major term matching algorithm is extracting.The makeups scheme includes the cosmetic knowledge；The cosmetic knowledge includes：Knowledge entry and adornment
Hold data, the knowledge entry is for characterizing the static description that makes up, the such as makeup skill of personalization, cosmetic region, cosmetic
Maneuver etc..The dressing data are used for characterizing the Dynamic profiling that makes up, such as dressing description, cosmetic step and content of multimedia
Information such as (subsidiary voice, animations etc.), wherein dressing description can include scene, applicable crowd and the dressing to being suitable for
Feature introduce etc..
In the present embodiment, describing document according to the generation makeups of the content structure of the makeups scheme can specifically include：Root
Cosmetic knowledge description document is generated according to the content structure of the cosmetic knowledge；Storage form of the various cosmetic knowledge in data base
For file structure, it is easy to subsequent user retrieval to browse, it should be noted that the document can be conventional editable text text
Shelves, or multimedia document.
In the present embodiment, in order to reduce the complexity of subsequent query, retrieval and storage, the makeups key word for extracting is carried out
Normalized.Further, when storage makeups describe document on the database, according to the mode pair that can carry out concurrent type frog retrieval
Multiple makeups describe document and are stored.Specifically, can describe document to multiple makeups carries out burst storage, concurrent to carry out
Formula is retrieved, so as to improve follow-up recall precision.
S102, it is to describe, in the makeups, the makeups key word that diverse location in the content structure of document occurs to give
Different weights.
In the present embodiment, step S102 is specifically as follows in the content structure of the cosmetic knowledge description document different positions
The cosmetic knowledge key word for putting appearance gives different weights.As a example by describing document principal mode as editable text,
If makeups key word is occurred in the exercise question of document, show that the document is more close with the relation of the makeups key word, permissible
Give higher weight；And if there is relatively low weight in the body matter part of document, then can be given, by that analogy may be used
With the position for occurring in description document by makeups key word, the substantial connection of the document and makeups key word, relation is judged
Closer, corresponding weight is also larger, and other more detailed weight allocative decisions are similar to, and repeat no more in detail.
Fig. 2 is two makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；As shown in Fig. 2 which includes：
S201, from the modeling scheme of collection, modeling scheme key word is extracted, the makeups scheme includes the moulding side
Case；
In the present embodiment, unlike the embodiments above, in the present embodiment, moulding is extracted from the modeling scheme of collection
Scheme key word, modeling scheme can be a whole set of the complete content for recommending user, including rationale for the recommendation or user
Property neutralizing reading, knowledge entry, dressing data etc..
S202, according to the content structure of the modeling scheme generate modeling scheme document is described；
Above-mentioned cosmetic knowledge description document is similar to, in the present embodiment, is also generated modeling scheme and document is described, the moulding side
It can be editable text document, or multimedia document that case describes document, can also be text document and multimedia
The combination of document.
S203, it is to describe, in the modeling scheme, the modeling scheme key word that diverse location in document occurs to give not
Same weight.
Similar above-described embodiment one, according to diverse location of the modeling scheme key word in description document, so as to give not
Same weight, the imparting principle of weight size is similar to the substantial connection of above-mentioned judgement the document and modeling scheme key word, relation
Closer, corresponding weight is also larger, otherwise then less.
It should be noted that in an other embodiment, while including modeling scheme and change in above-described embodiment one and two
Adornment knowledge, and corresponding modeling scheme key word and cosmetic knowledge key word, modeling scheme describes document and cosmetic knowledge is retouched
Document is stated, is repeated no more in detail.
Fig. 3 is three makeups storehouse banking process schematic flow sheet of the embodiment of the present invention；As shown in figure 3, which includes：
S301, from collection makeups scheme extract makeups key word, according to the content structure of the makeups scheme generate
Makeups describe document；
In the present embodiment, makeups scheme can include one of modeling scheme and cosmetic knowledge kind in above-described embodiment one and two
Or both, and corresponding modeling scheme key word and cosmetic knowledge key word, modeling scheme describes document and cosmetic knowledge
Description document.
S302, it is to describe, in the makeups, the makeups key word that diverse location in the content structure of document occurs to give
Different weights.
Modeling scheme key word gives different weights when modeling scheme describes diverse location in document；Cosmetic knowledge key
Word gives different weights in cosmetic knowledge description document during diverse location, the concrete distribution principle of weight is similar to above-described embodiment
First, two, repeat no more in detail.
S303, the generation management training coarse of knowledge entry and the management training coarse of the dressing data, and to the knowledge bar
The management training coarse of purpose management training coarse and the dressing data carries out Data Integration.
In the present embodiment, specifically, can be according to tree hierarchy structure to the management training coarse of the knowledge entry and institute
The management training coarse for stating dressing data carries out Content Management.Such as by the management of dressing data, dressing data are organized into an adornment
Hold-》Cosmetic region-》One tree hierarchy structure of dressing step, this level of dressing mainly includes：Title, description, secondary mark
Topic, the information such as crowd, difficulty on probation.One dressing can to should have multiple cosmetic regions, generally include bottom adornment, eye shadow, informer,
Eyelashes, eyebrow, rouge, lip, repair appearance etc. 8 cosmetic regions.Each cosmetic region depending on dressing theme need situation comprising several not
Deng region step, by taking eye shadow as an example, eye shadow region can include upper eye shadow, superposition eye shadow, several steps such as lower eye shadow, dressing
There are the data such as subsidiary cosmetic region, animation, track, official documents and correspondence, voice in step.
In the present embodiment, for the recommendation of modeling scheme, the management training coarse to the knowledge entry and the dressing number
According to management training coarse carry out Data Integration.
Fig. 4 is the personalized makeups aided process flow sheet schematic diagram of the embodiment of the present invention four；As shown in figure 4, which includes：
S401, in the face feature classification model for pre-building, coupling is carried out to the facial image of user in real and obtain
Take the personalized makeups label at family；
In the present embodiment, by carrying out feature mark to sample facial image and extracting and set up faceform, with to sample
Face feature in this facial image carries out classification and generates feature classification model.
In the present embodiment, feature mark is carried out to sample facial image and faceform is set up in extraction, with to sample face
Face feature in image carries out classification generation feature classification model and can specifically include：Face characteristic according to extracting enters pedestrian
Face shape modeling and the modeling of face texture respectively obtain face shape model and face texture model；According to the face shape mould
Type and face texture model set up faceform, generate feature classification mould to carry out classification to face feature in sample facial image
Type.
In the present embodiment, the generation of feature classification model can be completed by aam model, detailed process is as follows：
(1) facial image sample is selected as learning sample；
(2) manual characteristic point labelling is carried out to the learning sample for selecting so that the set of v good characteristic point position of labelling
Can constitute shape S, S=(x1, y1, x2, y2 ... xv, yv)；
(3) shape is normalized, refers to all face shape for learning to remove rotation, scaling by normalization
With global changes such as translations；
(4) principal component analysiss (Principal Component Analysis, abbreviation PCA) are carried out to normalized shape
Conversion, obtains average shape S0 and the corresponding shape eigenvectors Si of front n eigenvalue of corresponding training set.
(5) arbitrarily face shape S just can be expressed with linear equation：
This completes the modeling to face shape.
B) texture modeling：
(1) by the face shape in S0 and training set, difference Delaunay trigonometric ratio；
(2) texture information in sample set face shape is mapped to by average shape S0 by the affine method of piecewise linearity
In, realize to texture normalization；
(3) PCA conversion is carried out to the texture information after normalization, obtains average texture A0 and front m eigenvalue is corresponding
Texture feature vector Ai (x).
(4) texture is closely similar with shape, and the texture information of any face can also be represented with linear representation:
A (x) represents texture example, and A0 represents average texture,
γ i represents parametric texture, and Ai (x) represents i-th texture feature vector.
Modeling to texture is so also just completed.
C) AAM faceform example is generated
The generation step of AAM faceform's example is as follows, after first obtaining any one group of form parameter p, is entered with shape
Row linear expression, it becomes possible to obtain corresponding shape S, after then obtaining one group of parametric texture γ i, is carried out with texture model
Linear expression, obtains corresponding texture example A (x).Finally texture example A (x) in average shape S0 is mapped to currently
Shape S in, thus generate the model instance of an AAM.In addition to AAM model, can also be known using other models
Others' face and face such as Hmax+ neural network classification.
68 region point are obtained by AAM model, including ocular or so is each 6, each 5 of supercilium region or so,
Lip-region 20, nasal region 9, face area 17.After identification facial feature localization, need to carry out human face five-sense-organ feature to divide
Class, using svm disaggregated model.
By taking eye-shaped disaggregated model training as an example,
(1) first by facial feature points normalization：Two-dimensional coordinate is translated in three dimensions, rotates, is scaled so that face spy
Normalizing is levied for just forward-facing；
(2) characteristic point of impact eye-shaped is chosen；
(3) feature extraction is carried out to characteristic point, such as：Eye height, eye width, canthus and eye head relative position.
(4) using the feature of all labeled data as the input of svm, model is produced.Svm principle of classification, be by mark
1 and -1 classification being carried out to sample, seeks a linear algorithm, two class vector maximum degree is separated and clearance space is bigger,
Basis vector computing formula is as follows, and in following formula, w is that to represent be the plane that can separate, and s.t represents restrictive condition and belt restraining
Quadratic programming, b represents intercept, and y represents classification：.Basis vector computing formula is as follows：
Each face characteristic has respective classification foundation feature, and each face characteristic will carry out svm classification, and these are special
Levying mainly includes image texture characteristic, face ratio characteristic, face's Aspect Ratio, eyes eye head and eye tail ratio, eyeball high point
Same with nose to chin ratio, eyebrow peak and eyebrow tail and brows gradient, eyebrow length with eye tail terminal and eye head starting slope, nose length
Eyebrow gradient etc..Final output is accurately and recall rate meets feature classification model.
S402, according to described personalization data base of the makeups label described in any embodiment in carry out makeups key word
Coupling；
In the present embodiment, the face feature of personalized makeups tagging user, for example, such as shape of face：Oval face, square
Face, rhombus face, triangle face, heart-shaped face, circular face and elongated face；Such as chin：Square jaw, pointed chin and circle chin；Than
As eye-shaped：Almond-eyed, birdeye, circle eye, slot mesh, telecentricity eye, loser and vertical eye；Such as camber：Arched eyebrows, slanted eyebrows, one
Word eyebrow, on choose eyebrow and standard eyebrow etc..
According to these exemplary personalized makeups labels above-mentioned, mate in the data that is set up according to above-mentioned Fig. 1-Fig. 3
Makeups key word, includes the description document of these makeups key words with retrieval, including the description text of modeling scheme and cosmetic knowledge
Shelves, such as round face is suitable for the makeups scheme of that type, and arched eyebrows is suitable for which type of makeups scheme, by that analogy.
S403, the different power for being described document diverse location and giving in corresponding makeups according to the makeups key word for matching
Weight, the makeups scheme to including the makeups key word for matching carries out the recommendation index that weight statistics obtains makeups scheme, according to
The recommendation index assumes makeups scheme to the user.
In the present embodiment, if makeups key word only includes cosmetic knowledge key word, as data include multiple cosmetics
Knowledge document, including the cosmetic knowledge key word description document may have multiple, therefore, in order to suitable to user exactly
Makeups scheme, according to the weight that the key word for matching occurs giving in description document diverse location, count corresponding makeups
The weight of scheme, such as, can carry out letter to the weight for describing the same cosmetic knowledge key word that diverse location occurs in document
Single adds and computing, obtains the comprehensive weight of corresponding makeups scheme, obtains the recommendation index of makeups scheme according to the comprehensive weight,
Comprehensive weight is bigger, it is recommended that index is higher, higher with the personalized makeups tag match degree of user.
In other embodiments, the situation for only including modeling scheme key word for makeups key word is similar to above-mentioned only including
The situation of cosmetic knowledge key word, is repeated no more in detail.
And in other embodiments, if makeups key word is while include cosmetic knowledge key word and modeling scheme key
Word, corresponding makeups scheme includes modeling scheme and cosmetic knowledge, then when the weight of makeups scheme is generated, to modeling scheme and
The comprehensive weight of cosmetic knowledge is fitted, and the comprehensive weight of the comprehensive weight of such as the two modeling schemes and cosmetic knowledge is asked
With the comprehensive weight of acquisition makeups scheme；Can also be carried out according to the weight of modeling scheme and the weight of cosmetic knowledge respectively
Modeling scheme and the recommendation of makeup knowledge.
Fig. 5 is the personalized makeups aided process flow sheet schematic diagram of the embodiment of the present invention five；As shown in figure 5, which includes：
S501, in the face feature classification model for pre-building, coupling is carried out to the facial image of user in real and obtain
Take the personalized makeups label at family；
In the present embodiment, step S501 is similar to the related record of above-described embodiment, will not be described here.
S502, the preference information according to user, the on-site Weather information of user, user birthday by information any one or many
The combination producing personalization auxiliary makeups label that plants；
Unlike the embodiments above, in the present embodiment, except the personalization for having face feature, also add user's
The personalized auxiliary makeups label that preference information, the on-site Weather information of user, the birthday by information of user are characterized.
In the present embodiment, different users has different styles of wearing the clothes, and collects this kind of preference information of user and is returned
One change is processed, and style of such as wearing the clothes style of wearing the clothes is classified as：Extremely simple neutral, pure and fresh literature and art, vigor maiden, former place unusual charm, mixed
Take changeable, intellectual, charming imperial elder sister, makings gently ripe.
The on-site weather of user is obtained according to the geographical position of the user for reflecting on intelligent terminal and is normalized
Process is obtained：Fine day, cloudy day, rainy day etc..
Birthday by information according to user judges red-letter day situation, while the lucky color of dynamic access user's constellation, is sorted out, than
It is such as：Brown, redness, yellow, green, navy blue, white, blueness, gold, black, pink, aeruginouss, Lycoperdon polymorphum Vitt, dark brown
Color, purple, orange etc..
S503, according to described personalization data base of the makeups label described in any embodiment in carry out makeups key word
Coupling；
Relevant personalization makeups label is will not be described here referring to above-mentioned related embodiment.
Makeups key is carried out in S504, the data base according to the personalized auxiliary makeups label is in any embodiment
The coupling of word；
In the present embodiment, the coupling of above-mentioned personalization makeups label is similar to, retrieving includes and personalization U.S. in data base
The description document of the makeups key word of adornment tag match, is such as suitable for the makeups scheme at cloudy day, is suitable for lucky color for red makeups
Scheme etc..
Matching process in above-mentioned steps S503 and 504 can be realized using KMP algorithm, repeated no more in detail.
S505, the different power for being described document diverse location and giving in corresponding makeups according to the makeups key word for matching
Weight, the makeups scheme to including the makeups key word for matching carries out the recommendation index that weight statistics obtains makeups scheme；
In the present embodiment, the weight statistics of makeups scheme is similar to above-mentioned related embodiment and records, and will not be described here.When same
When determining makeups scheme according to personalized auxiliary makeups label and personalized makeups label, can be according in same makeups scheme
While the weight of the personalized auxiliary makeups label for including and personalized makeups label generates the comprehensive weight of the makeups scheme.
S506, the makeups scheme to including the makeups key word for matching carry out one-level and secondary merger sequence respectively, with
Makeups scheme is assumed to the user according to the recommendation index.
In the present embodiment, can arrange a retrieval trunk module carries out two grades of merger sequences to makeups scheme, removes and repeats
Document, improves recall precision.
Fig. 6 builds storehouse apparatus structure schematic diagram for six makeups storehouse of the embodiment of the present invention；As shown in fig. 6, which includes：
Unit 601 set up by document, for extracting makeups key word from the makeups scheme of collection, according to the makeups scheme
Content structure generate makeups document is described；
Weight-assigning unit 602, for for describing the institute that in the content structure of document, diverse location occurs in the makeups
State makeups key word and give different weights.
Alternatively, in one embodiment of this invention, the document is set up unit 601 and is further used for from the change for collecting
Cosmetic knowledge key word is extracted in adornment knowledge, and the makeups scheme includes the cosmetic knowledge；According in the cosmetic knowledge
Hold structural generation cosmetic knowledge description document；
The weight-assigning unit 602 is further used for being different in the content structure of the cosmetic knowledge description document
The makeups key word that position occurs gives different weights to be included：It is the content structure in the cosmetic knowledge description document
The cosmetic knowledge key word that middle diverse location occurs gives different weights.
Alternatively, in one embodiment of this invention, the document is set up unit 601 and is further used for from the moulding for gathering
Modeling scheme key word is extracted in scheme, the makeups scheme includes the modeling scheme, according to the content of the modeling scheme
Structural generation modeling scheme describes document；
The weight-assigning unit 602 is further used for being different in the content structure of the cosmetic knowledge description document
The makeups key word that position occurs gives different weights to be included：It is to describe diverse location in document in the modeling scheme
The modeling scheme key word for occurring gives different weights.
Fig. 7 is the personalized makeups assistant apparatus structure schematic diagram of the embodiment of the present invention seven；As shown in fig. 7, which includes：
Tag match unit 701, for the people in the face feature classification model for pre-building to user in real
Face image carries out mating the personalized makeups label for obtaining user；
Keywords matching unit 702, for according to described personalization makeups label in any embodiment described in data base
In carry out the coupling of makeups key word；
Makeups recommendation unit 703, for describing document diverse location according to the makeups key word for matching in corresponding makeups
And the different weights for giving, to including that the makeups scheme of makeups key word for matching carries out weight and count obtaining makeups scheme
Recommend index, makeups scheme is assumed to the user according to the recommendation index.
Alternatively, in one embodiment of this invention, also include：Assisted tag unit 704, for the preference according to user
Information, the on-site Weather information of user, the birthday by information combination producing of any one or more the personalized auxiliary makeups of user
Label；
The Keywords matching unit 702 is further used for according to the personalized auxiliary makeups label in any embodiment
The coupling of makeups key word is carried out in described data base.
It will be understood by those skilled in the art that the embodiment of the embodiment of the present invention can be provided as method, device (equipment) or
Computer program.Therefore, the embodiment of the present invention can adopt complete hardware embodiment, complete software embodiment or combine soft
The form of the embodiment of part and hardware aspect.And, the embodiment of the present invention can be adopted and wherein include calculating one or more
Computer-usable storage medium (including but not limited to disk memory, CD-ROM, the optical memory of machine usable program code
Deng) form of the upper computer program that implements.
The embodiment of the present invention be with reference to method according to embodiments of the present invention, device (equipment) and computer program
Flow chart and/or block diagram are describing.It should be understood that can be by every in computer program instructions flowchart and/or block diagram
One flow process and/or the combination of square frame and flow chart and/or the flow process in block diagram and/or square frame.These computers can be provided
Programmed instruction is to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device
To produce a machine so that produce use by the instruction of computer or the computing device of other programmable data processing device
Dress in the function of realizing specifying in one flow process of flow chart or multiple flow processs and/or one square frame of block diagram or multiple square frames
Put.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing device with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory is produced to be included to refer to
Make the manufacture of device, the command device realize in one flow process of flow chart or multiple flow processs and/or one square frame of block diagram or
The function of specifying in multiple square frames.
These computer program instructions can be also loaded in computer or other programmable data processing device so that in meter
Series of operation steps is executed on calculation machine or other programmable devices to produce computer implemented process, so as in computer or
The instruction for executing on other programmable devices is provided for realizing in one flow process of flow chart or multiple flow processs and/or block diagram one
The step of function of specifying in individual square frame or multiple square frames.
The preferred embodiment of the embodiment of the present invention is although had been described for, but those skilled in the art once know base
This creative concept, then can make other change and modification to these embodiments.So, claims are intended to be construed to
Including preferred embodiment and fall into being had altered and changing for range of embodiment of the invention.Obviously, those skilled in the art
The spirit and scope of various changes and modification without deviating from the embodiment of the present invention can be carried out to the embodiment of the present invention.So, if
If these modifications of the embodiment of the present invention and modification belong within the scope of embodiment of the present invention claim and its equivalent technologies,
Then the embodiment of the present invention is also intended to comprising these changes and modification.
Claims (20)
1. a kind of makeups storehouse banking process, it is characterised in that include：
Makeups key word is extracted from the makeups scheme of collection, and makeups description text is generated according to the content structure of the makeups scheme
Shelves；
It is to describe, in the makeups, the makeups key word that in the content structure of document, diverse location occurs to give different power
Weight.
2. method according to claim 1, it is characterised in that extract makeups key word bag from the makeups scheme of collection
Include：Cosmetic knowledge key word is extracted from the cosmetic knowledge for collecting, and the makeups scheme includes the cosmetic knowledge；
Document being described according to the generation makeups of the content structure of the makeups scheme includes：Content structure according to the cosmetic knowledge
Generate cosmetic knowledge description document；
It is that the makeups key word that diverse location occurs in the content structure of the cosmetic knowledge description document gives difference
Weight include：It is that the cosmetic knowledge that diverse location occurs in the content structure of the cosmetic knowledge description document is crucial
Word gives different weights.
3. method according to claim 1 and 2, it is characterised in that extract makeups key word from the makeups scheme of collection
Including：Modeling scheme key word is extracted from the modeling scheme of collection, and the makeups scheme includes the modeling scheme；
Document being described according to the generation makeups of the content structure of the makeups scheme includes：Content structure according to the modeling scheme
Generate modeling scheme and describe document；
It is that the makeups key word that diverse location occurs in the content structure of the cosmetic knowledge description document gives difference
Weight include：It is to describe, in the modeling scheme, the modeling scheme key word that in document, diverse location occurs to give difference
Weight.
4. method according to claim 1, it is characterised in that the cosmetic knowledge includes：Knowledge entry and dressing data,
The knowledge entry is used for characterizing the static description that makes up, and the dressing data are used for characterizing the Dynamic profiling that makes up.
5. method according to claim 4, it is characterised in that the knowledge entry includes the makeup skill of personalization, change
One of adornment region, cosmetic maneuver or multiple combinations；The dressing data include that dressing description, cosmetic step and correspondence are many
One of media content or multiple combinations.
6. method according to claim 5, it is characterised in that also include：Generate the management training coarse of the knowledge entry with
And the management training coarse of the dressing data, and the management training coarse of the management training coarse to the knowledge entry and the dressing data
Carry out Data Integration.
7. method according to claim 6, it is characterised in that also include：According to tree hierarchy structure to the knowledge bar
The management training coarse of purpose management training coarse and the dressing data carries out Content Management.
8. the method according to any one of claim 1-7, it is characterised in that also include：The makeups key word for extracting is entered
Row normalized.
9. method according to claim 8, it is characterised in that also include：According to the mode pair that can carry out concurrent type frog retrieval
Multiple makeups describe document and are stored.
10. method according to claim 9, it is characterised in that describing document to multiple makeups carries out burst storage, to enter
Row concurrent type frog is retrieved.
11. a kind of personalization makeups householder methods, it is characterised in that include：
In the face feature classification model for pre-building, the facial image of user in real is carried out mating and obtain user's
Personalized makeups label；
Makeups key word is carried out in data base according to the personalization makeups label is in any one of claim 1-10
Coupling；
According to the different weights that the makeups key word for matching describes document diverse location and give in corresponding makeups, to including
The makeups scheme of the makeups key word being fitted on carries out the recommendation index that weight statistics obtains makeups scheme, according to the recommendation index
Assume makeups scheme to the user.
12. methods according to claim 11, it is characterised in that also include：Feature mark is carried out to sample facial image
With extract and set up faceform, with to face feature carry out classification generate feature classification model.
13. methods according to claim 12, it is characterised in that feature mark is carried out to sample facial image and extraction is built
Vertical faceform, is included with carrying out classification generation feature classification model to face feature：
Face characteristic according to extracting carries out face shape modeling and the modeling of face texture respectively obtains face shape model and people
Face texture model；
Faceform is set up according to the face shape model and face texture model, spy is generated to carry out classification to face feature
Levy classification model.
14. methods according to claim 11, it is characterised in that also include：Preference information according to user, user are located
The Weather information on ground, the birthday by information combination producing personalization auxiliary makeups label of any one or more of user；
Carried out in the data base that any one of claim 1-10 method is set up according to the personalized auxiliary makeups label
The coupling of makeups key word.
15. methods according to claim 10, it is characterised in that also include：To including the makeups key word for matching
Makeups scheme carries out one-level and secondary merger sequence respectively.
Storehouse device is built in a kind of 16. makeups storehouses, it is characterised in that include：
Unit set up by document, for extracting makeups key word from the makeups scheme of collection, according to the content of the makeups scheme
Structural generation makeups describe document；
Weight-assigning unit, for closing for describing the makeups that in the content structure of document, diverse location occurs in the makeups
Keyword gives different weights.
17. devices according to claim 16, it is characterised in that the document is set up unit and is further used for from collecting
Cosmetic knowledge in extract cosmetic knowledge key word, the makeups scheme includes the cosmetic knowledge；According to the cosmetic knowledge
Content structure generate cosmetic knowledge description document；
The weight-assigning unit is further used for being that diverse location goes out in the content structure of the cosmetic knowledge description document
The existing makeups key word gives different weights to be included：It is different in the content structure of the cosmetic knowledge description document
The cosmetic knowledge key word that position occurs gives different weights.
18. devices according to claim 16 or 17, it is characterised in that the document is set up unit and is further used for from adopting
Modeling scheme key word is extracted in the modeling scheme of collection, the makeups scheme includes the modeling scheme, according to the moulding side
The content structure of case generates modeling scheme and describes document；
The weight-assigning unit is further used for being that diverse location goes out in the content structure of the cosmetic knowledge description document
The existing makeups key word gives different weights to be included：It is to describe diverse location in document in the modeling scheme to occur
The modeling scheme key word gives different weights.
19. a kind of personalization makeups auxiliary device, it is characterised in that include：
Tag match unit, for entering to the facial image of user in real in the face feature classification model for pre-building
Row coupling obtains the personalized makeups label of user；
Keywords matching unit, for the institute for being set up in any one of claim 1-10 method according to the personalization makeups label
Stating carries out the coupling of makeups key word in data base；
Makeups recommendation unit, gives for describing document diverse location according to the makeups key word for matching in corresponding makeups
Different weights, to including that the makeups scheme of makeups key word for matching carries out weight statistics and obtain the recommendation of makeups scheme referring to
Number, assumes makeups scheme according to the recommendation index to the user.
20. devices according to claim 19, it is characterised in that also include：Assisted tag unit, for according to user's
Preference information, the on-site Weather information of user, the birthday by information combination producing personalization auxiliary of any one or more of user
Makeups label；
The Keywords matching unit is further used for according to the personalized auxiliary makeups label is in claim 1-10
The coupling of makeups key word is carried out in data base described in any one that method is set up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873350.8A CN106446207B (en) | 2016-09-30 | 2016-09-30 | Makeups library banking process, personalized makeups householder method and its device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610873350.8A CN106446207B (en) | 2016-09-30 | 2016-09-30 | Makeups library banking process, personalized makeups householder method and its device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106446207A true CN106446207A (en) | 2017-02-22 |
| CN106446207B CN106446207B (en) | 2019-11-12 |
Family
ID=58172717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610873350.8A Active CN106446207B (en) | 2016-09-30 | 2016-09-30 | Makeups library banking process, personalized makeups householder method and its device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446207B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121957A (en) * | 2017-12-19 | 2018-06-05 | 北京麒麟合盛网络技术有限公司 | The method for pushing and device of U.S. face material |
| CN108596094A (en) * | 2018-04-24 | 2018-09-28 | 杭州数为科技有限公司 | Personage's style detecting system, method, terminal and medium |
| WO2019223398A1 (en) * | 2018-05-22 | 2019-11-28 | 京东方科技集团股份有限公司 | Makeup plan recommendation method and apparatus, cloud device, and electronic device |
| CN112819718A (en) * | 2021-02-01 | 2021-05-18 | 深圳市商汤科技有限公司 | Image processing method and device, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599886A (en) * | 2008-06-05 | 2009-12-09 | 华为技术有限公司 | Querying method in the distributed structured network, system and equipment |
| CN102693288A (en) * | 2012-04-27 | 2012-09-26 | 上海申视汽车新技术有限公司 | Automatic recommendation method for makeup scheme |
| CN104750801A (en) * | 2015-03-24 | 2015-07-01 | 华迪计算机集团有限公司 | Generation method and system of structured document |
| CN105138648A (en) * | 2015-08-26 | 2015-12-09 | 宇龙计算机通信科技(深圳)有限公司 | Information recommendation method and user terminal |
-
2016
- 2016-09-30 CN CN201610873350.8A patent/CN106446207B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599886A (en) * | 2008-06-05 | 2009-12-09 | 华为技术有限公司 | Querying method in the distributed structured network, system and equipment |
| CN102693288A (en) * | 2012-04-27 | 2012-09-26 | 上海申视汽车新技术有限公司 | Automatic recommendation method for makeup scheme |
| CN104750801A (en) * | 2015-03-24 | 2015-07-01 | 华迪计算机集团有限公司 | Generation method and system of structured document |
| CN105138648A (en) * | 2015-08-26 | 2015-12-09 | 宇龙计算机通信科技(深圳)有限公司 | Information recommendation method and user terminal |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121957A (en) * | 2017-12-19 | 2018-06-05 | 北京麒麟合盛网络技术有限公司 | The method for pushing and device of U.S. face material |
| CN108121957B (en) * | 2017-12-19 | 2021-09-03 | 麒麟合盛网络技术股份有限公司 | Method and device for pushing beauty material |
| CN108596094A (en) * | 2018-04-24 | 2018-09-28 | 杭州数为科技有限公司 | Personage's style detecting system, method, terminal and medium |
| CN108596094B (en) * | 2018-04-24 | 2021-02-05 | 杭州数为科技有限公司 | Character style detection system, method, terminal and medium |
| WO2019223398A1 (en) * | 2018-05-22 | 2019-11-28 | 京东方科技集团股份有限公司 | Makeup plan recommendation method and apparatus, cloud device, and electronic device |
| US11449918B2 (en) | 2018-05-22 | 2022-09-20 | Beijing Boe Technology Development Co., Ltd. | Makeup scheme recommendation method and device, cloud device, and electronic device |
| CN112819718A (en) * | 2021-02-01 | 2021-05-18 | 深圳市商汤科技有限公司 | Image processing method and device, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106446207B (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101324961B (en) | Human face portion three-dimensional picture pasting method in computer virtual world | |
| CN108510437A (en) | A kind of virtual image generation method, device, equipment and readable storage medium storing program for executing | |
| CN104217454B (en) | A kind of human face animation generation method of video drive | |
| CN100468463C (en) | Method,apparatua and computer program for processing image | |
| CN105513125B (en) | Composograph generating means and method, the recording medium for executing this method | |
| CN109359538A (en) | Training method, gesture identification method, device and the equipment of convolutional neural networks | |
| CN109840825A (en) | The recommender system of physical features based on user | |
| CN109815826A (en) | The generation method and device of face character model | |
| CN107784630B (en) | Method, device and terminal for turning attributes of face image | |
| CN106446207B (en) | Makeups library banking process, personalized makeups householder method and its device | |
| CN110111236A (en) | The method for generating image based on the multiple target sketch that gradual confrontation generates network | |
| US20220292773A1 (en) | Methods and systems for personalized 3d head model deformation | |
| CN107169455A (en) | Face character recognition methods based on depth local feature | |
| CN102567716B (en) | Face synthetic system and implementation method | |
| CN104205168A (en) | Makeup application assistance device, makeup application assistance method, and makeup application assistance program | |
| CN109310196A (en) | Makeup auxiliary device and cosmetic auxiliary method | |
| CN108197574A (en) | The recognition methods of personage's style, terminal and computer readable storage medium | |
| US20220292772A1 (en) | Methods and systems for constructing facial position map | |
| CN110796593A (en) | Image processing method, device, medium and electronic equipment based on artificial intelligence | |
| CN106021550A (en) | Hair style designing method and system | |
| CN108564012A (en) | A kind of pedestrian's analytic method based on characteristics of human body's distribution | |
| WO2022197429A1 (en) | Methods and systems for extracting color from facial image | |
| CN113569732A (en) | Face attribute recognition method and system based on parallel sharing multitask network | |
| CN106326980A (en) | Robot and method for simulating human facial movements by robot | |
| CN104933742A (en) | Automatic cartoon image generation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |