CN110264299A - Clothes recommended method, device and computer equipment based on recognition of face - Google Patents
Clothes recommended method, device and computer equipment based on recognition of face Download PDFInfo
- Publication number
- CN110264299A CN110264299A CN201910374822.9A CN201910374822A CN110264299A CN 110264299 A CN110264299 A CN 110264299A CN 201910374822 A CN201910374822 A CN 201910374822A CN 110264299 A CN110264299 A CN 110264299A
- Authority
- CN
- China
- Prior art keywords
- human body
- user
- information
- clothes
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Abstract
The embodiment of the present application provides a kind of clothes recommended method, device, computer equipment and computer readable storage medium based on recognition of face.The embodiment of the present application belongs to technical field of face recognition, when carrying out clothes recommendation, judges whether to detect human body by predetermined manner;If detecting human body, the facial image of the corresponding user of human body is obtained;The human body identity of user is obtained by recognition of face according to facial image;3-D scanning is carried out to obtain the body information of user to user;Based on human body identity and the matched big data analysis of the body information, according to first according to human body identity again according to body information sequence, from database obtain with human body identity and the matched clothing information of body information;The clothing information including garment image is shown to user to carry out clothes recommendation to user by display screen, is recommended based on the big data intelligent clothing of recognition of face and 3-D scanning, can be improved the accuracy of clothes recommendation, improve the efficiency of intelligent clothing recommendation.
Description
Technical field
This application involves clothes recommended technology field more particularly to a kind of clothes recommended methods based on recognition of face, dress
It sets, computer equipment and computer readable storage medium.
Background technique
It in traditional technology or is that user provides the stature data of oneself, it is corresponding according to stature data according to stature data
Size carry out clothes the stature data for choosing or be manual measurement user, then select stature data correspond to size into
Row clothes is chosen perhaps clothes and is recommended but in the process or user forgets oneself stature data or stature data
Variation or be inconvenient to measure stature data, can all reduce the efficiency that clothes is chosen and recommended.
Summary of the invention
The embodiment of the present application provide it is a kind of by the clothes recommended method of recognition of face, device, computer equipment and based on
Calculation machine readable storage medium storing program for executing, is able to solve and when choosing clothes in traditional technology clothes is recommended with inefficient problem.
In a first aspect, the embodiment of the present application provides a kind of clothes recommended method based on recognition of face, the method packet
It includes: judging whether to detect human body by predetermined manner;If detecting the human body, the people is obtained by image capture device
The facial image of the corresponding user of body;The human body identity of the user, institute are obtained by recognition of face according to the facial image
State the attributive character that human body identity refers to human body;3-D scanning is carried out to obtain the use to the user by three-dimensional scanning device
The body information at family;Based on the human body identity and the matched big data analysis of the body information, according to first according to described in
The human body identity sequence according to the body information again obtains and the human body identity and the body information from database
The clothing information matched;It will include that the clothing information of garment image is shown to the user with to the use by display screen
Family carries out clothes recommendation.
Second aspect, the embodiment of the present application also provides a kind of clothes recommendation apparatus based on recognition of face, comprising: judgement
Unit detects human body for judging whether by predetermined manner;First acquisition unit, if leading to for detecting the human body
Cross the facial image that image capture device obtains the corresponding user of the human body;Second acquisition unit, for according to the face
Image obtains the human body identity of the user by recognition of face, and the human body identity refers to the attributive character of human body;Scanning element,
For carrying out 3-D scanning to the user by three-dimensional scanning device to obtain the body information of the user;Third obtains single
Member, for based on the human body identity and the matched big data analysis of the body information, according to elder generation according to the human body body
Part sequence according to the body information again, obtains and the human body identity and the matched clothes of the body information from database
Fill information;Display unit, for by display screen by include garment image the clothing information be shown to the user with
Clothes recommendation is carried out to the user.
The third aspect, the embodiment of the present application also provides a kind of computer equipments comprising memory and processor, it is described
Computer program is stored on memory, the processor is realized described based on recognition of face when executing the computer program
Clothes recommended method.
Fourth aspect, it is described computer-readable to deposit the embodiment of the present application also provides a kind of computer readable storage medium
Storage media is stored with computer program, and the computer program executes the processor when being executed by processor described based on people
The clothes recommended method of face identification.
The embodiment of the present application provide it is a kind of by the clothes recommended method of recognition of face, device, computer equipment and based on
Calculation machine readable storage medium storing program for executing.When the embodiment of the present application recommends clothes, judge whether to detect human body by predetermined manner,
If detecting the human body, the facial image of the corresponding user of the human body is obtained by image capture device, according to the people
Face image obtains the accurate human body identity of the user by recognition of face, and the human body identity refers to the attributive character of human body, root
According to the human body, the accurate body information that 3-D scanning obtains the user is carried out to the user by three-dimensional scanning device,
In the accurate human body identity and on the basis of the body information of user, it is based on and the human body identity and the stature is believed
Matched big data analysis is ceased, according to elder generation according to the human body identity sequence according to the body information again, from database
Acquisition and the human body identity and the matched clothing information of the body information, by showing screen by the institute including garment image
It states clothing information and is shown to the user to carry out clothes recommendation to the user, realize based on recognition of face and 3-D scanning
Big data intelligent clothing is recommended, and can be improved the accuracy of clothes recommendation, to improve what intelligent clothing when choosing clothes was recommended
Efficiency.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present application, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of the clothes recommended method provided by the embodiments of the present application based on recognition of face;
Fig. 2 is the flow diagram of the clothes recommended method provided by the embodiments of the present application based on recognition of face;
Fig. 3 is another flow diagram of the clothes recommended method provided by the embodiments of the present application based on recognition of face;
Fig. 4 is a sub- flow diagram in the clothes recommended method provided by the embodiments of the present application based on recognition of face;
Fig. 5 is the schematic block diagram of the clothes recommendation apparatus provided by the embodiments of the present application based on recognition of face;
Fig. 6 is another schematic block diagram of the clothes recommendation apparatus provided by the embodiments of the present application based on recognition of face;
And
Fig. 7 is the schematic block diagram of computer equipment provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is the application scenarios of the clothes recommended method provided by the embodiments of the present application based on recognition of face
Schematic diagram.The application scenarios include:
(1) man face image acquiring equipment, including camera, the man face image acquiring equipment are connect with server.
(2) spatial digitizer, English are 3D scanner, and what it is due to spatial digitizer measurement is distance, in the knot measured
Fruit contains depth information, therefore spatial digitizer can be used for obtaining the body information of the user, spatial digitizer and service
Device connection.
(3) server, server are used to carry out the processing of the clothes recommending data based on recognition of face and 3-D scanning,
Server can be single server, server cluster or Cloud Server, and server can also include if server cluster
Primary server and from server.
(4) clothes recommend display equipment, include mainly display, and for interacting with user, for example display clothes push away
It is recommending as a result, and receive the operation of user to obtain the information data of user, clothes recommend display equipment to connect with server.
Please continue to refer to Fig. 1, as shown in Figure 1, in the embodiment of the present application, mainly being executed with server end and being known based on face
The technical solution of clothes recommended method of the application based on recognition of face is explained for the step of other clothes recommended method, is schemed
Each body of work process in 1 is as follows: server is by man face image acquiring equipment acquisition facial image or with infrared inspection
The predetermined manners such as survey judge whether to detect human body, if detecting the human body, control man face image acquiring equipment acquires face
Image, and the corresponding facial image of the human body of man face image acquiring equipment acquisition is obtained, passed through according to the facial image
Recognition of face obtains the human body identity of the user, and the human body identity refers to the attributive character of human body, according to the human body, passes through
Three-dimensional scanning device carries out 3-D scanning to the user to obtain the body information of the user, is based on and the human body identity
And the matched big data analysis of body information, according to elder generation according to the human body identity again according to the suitable of the body information
Sequence, acquisition and the human body identity and the matched clothing information of the body information from database pass through clothes and recommend to show
The clothing information including garment image is shown to the user to carry out clothes to the user by the display screen of equipment
Recommend.
It should be noted that the application scenarios of the above-mentioned clothes recommended method based on recognition of face are merely illustrative this Shen
Please technical solution, be not used to limit technical scheme, above-mentioned connection relationship can also have other forms.
Fig. 2 is the schematic flow chart of the clothes recommended method provided by the embodiments of the present application based on recognition of face.The base
It is applied in the clothes recommended method of recognition of face in Fig. 1 in server, to complete the clothes recommended method based on recognition of face
All or part of function.
Referring to Fig. 2, Fig. 2 is the process signal of the clothes recommended method provided by the embodiments of the present application based on recognition of face
Figure.As shown in Fig. 2, this approach includes the following steps S201-S206:
S201, judge whether to detect human body by predetermined manner.
Wherein, predetermined manner includes the modes such as recognition of face or infrared detection.
Recognition of face, also referred to as Identification of Images or face recognition are to carry out personal part based on facial feature information of people
Identification.Image or video flowing containing face, and automatic detection and tracking face in the picture are acquired with video camera or camera,
And then face recognition is carried out to the face detected.
Specifically, the user of purchase clothes is judged whether there is by recognition of face or infrared detection.To pass through face
For identification, if can detect that face judgement has the user of purchase clothes by recognition of face, if face judgement is not detected
There is no the users of purchase clothes.
When carrying out clothes recommendation, In vivo detection is carried out to judge whether to deposit by recognition of face or infrared detection first
In the user of purchase clothes, if identifying there is the user of purchase clothes in face judgement, start the step of carrying out clothes recommendation, if
The unidentified judgement of face out continues through recognition of face or infrared detection carries out In vivo detection there is no the user of purchase clothes
Until detecting living body to judge the user that there are purchase clothes.By taking recognition of face as an example, video camera or camera etc. can be used
Image capture device acquires image or video flowing, and automatic detection and tracking face in the picture, and then judges the image of acquisition
Or the user of purchase clothes is judged whether there is in video flowing with the presence or absence of face.And user is when needing to buy clothes, place
Include in the regional scope that image capture device can collect face, the image capture devices such as video camera or camera are collected
There are the image or video flowing of face, automatically detection and tracking face, and then face progress face's knowledge to detecting in the picture
Not, and by recognition of face the user of purchase clothes is judged whether there is.
If S202, detecting the human body, the face figure of the corresponding user of the human body is obtained by image capture device
Picture;
S203, the human body identity for obtaining the user by recognition of face according to the facial image, the human body identity
Refer to the attributive character of human body.
Wherein, human body identity refers to the attributive character of human body, and the attributive character of human body includes the gender of human body, and human body is
Male or women, human body belong to the attributive character such as which age bracket and shape of face.
Specifically, it when carrying out clothes recommendation, is deposited if carrying out In vivo detection judgement by recognition of face or infrared detection
In human body, human body identity is further determined to determine the suitable clothes classification of human body according to human body identity by recognition of face.
Wherein, the clothes classification, including men's clothing, women's dress, men's clothing and women's dress Rigen can be respectively divided into children's garment, blueness according to age bracket again
Classifications, the clothes classifications such as teenager's dress, person in middle and old age's dress the practical style for including can be divided according to clothes.When detecting human body,
Human body can be judged whether there is by recognition of face or infrared detection, if detecting human body, can by recognition of face with
Identifying human body identity, the human body identity refers to the gender for identifying human body, age information, such as male, women, children,
Juvenile, young, middle age or old age et al. body part.
In recognition of face, since male and female and human body are in the difference of the significant physiological characteristic of different age group,
The gender of human body and the probable ranges at age can be identified by recognition of face.Face can also be carried out by machine learning
Identification estimates which age bracket human body belongs to according to face, for example, the face age based on Boosting RBF neural
Estimation method first extracts face characteristic with non-negative matrix factorization method, then determines a facial image by RBF neural
And its estimation function between the age that is consistent.To improve the generalization ability of neural network and the accuracy of fault diagnosis, utilize
One sequence of function neural network based of Boosting method construct is combined into the estimation function of a reinforcement,
Finally carry out age estimation.Can also wrinkle texture and facial image skin analysis based on Hough transform age and gender
Recognition methods.The face age identification research in, face complexion can change with the age, cause the current looks of object with
There is difference between image in image library, so as to cause the decline of discrimination.It is influenced brought by this variation to reduce, it can
The effect that change of age is simulated using Age Variations facial image reconstructing method improves the discrimination of face, realizes face looks
Accurately identify and predict.The specific algorithm of face age estimation can be selected, herein not by many according to practical business
It repeats again.
S204,3-D scanning is carried out to the user to obtain the body information of the user by three-dimensional scanning device.
Wherein, 3-D scanning refers to and is scanned to object space shape and structure and color, to obtain body surface
Space coordinate, 3-D scanning technology are able to achieve non-cpntact measurement, and its measurement result can directly with various software interface.
Specifically, if identifying human body, three-dimensional is carried out to human body by three-dimensional scanning device according to the human body identity and is swept
Retouch to obtain the body information of human body, the body information include shoulder breadth, bust, waistline, seat enclose, hip circumference, knee circumference, upper body ruler
Very little, lower part of the body size and bottoms etc. determine the information of garment size, and sleeve length, the clothing of suitable human body are estimated according to the body information
The reasonable interval of the clothing informations such as long, preceding wave, back rise and foreign minister, to recommend the suitable size of clothes according to clothing information.
S205, based on the human body identity and the matched big data analysis of the body information, according to first according to described in
The human body identity sequence according to the body information again obtains and the human body identity and the body information from database
The clothing information matched;
It S206, will include that the clothing information of garment image is shown to the user with to the use by display screen
Family carries out clothes recommendation.
Specifically, it needs to match clothing information and the human body identity and the body information in advance, and general
It is stored with data.Under normal circumstances, clothes are to be corresponding with suitable crowd, for example, the age bracket that clothes adapt to, is baby
The age-colonies such as youngster, children and adolescents or person in middle and old age, the corresponding gender of clothes, such as Men's Wear or Women's Wear etc.,
It further include the size of clothes, the corresponding size of the people of different heights and weight is also different.Clothes corresponding age, gender
And size is the essential information of clothes, can by tabular form by the clothes number of clothes, the clothes corresponding age, gender and
Size is mapped, in the gender for obtaining user, after age et al. body informations such as body part and weight, height, according to human body
Identity and body information are obtained from database and are encoded with the human body identity and the matched clothing information of the body information,
The clothing information that clothes encode this corresponding clothes is retrieved again by clothes coding, and clothing information includes clothes number, clothes
Fill the information of the clothes such as pattern, clothes quality, garment dimension, clothing color and the corresponding picture of this clothes.
Further, if clothes fashion is relatively more, the clothing information of acquisition may include a plurality of clothes, comprising a plurality of
In the case where clothes, clothing information can be shown according to preset condition.For example, numbered according to clothes, by clothes according to
Number order is shown.Alternatively, being shown clothes according to season belonging to clothes, work as example, obtaining computer equipment
The preceding time judges current season according to the computer equipment current time, this season clothes, then root is preferentially shown according to season
This season clothes are shown according to sequence from the near to the distant according to the successive time sequencing that clothes in this season clothes list, due to what is just listed
Garment size is more complete, while being also the kinds of goods of preferential recommendation, to improve the recommendation efficiency of this season clothes.Further
Ground can also recommend the clothes of the corresponding lower first quarter in current season.Due to clothes listing it is advanced, recommend current season pair
The clothes for the lower first quarter answered.For example, current season is spring, the clothes of summer can be recommended, current season is summer, can be with
Recommend the clothes in autumn.It is shown it is, the Time To Market of clothes and season are combined.First according to season according still further to
Clothes are shown by the Time To Market of clothes, by showing the more clothes of category, improve the efficiency that clothes are recommended.
After the human body identity and the body information that obtain user, filtered out from database and human body identity and body information phase
Matched garment data, the garment data include identical or close as the human body identity and/or the body information difference
As garment data corresponding to human body identity and/or body information, based on the human body identity and body information with the user
The analysis of the big data to match, according to elder generation according to the human body identity sequence according to the body information again, from database
Acquisition and the human body identity and the matched clothing information of the body information, pass through and show screen in the garment data filtered out
The clothing information including garment image is shown to the user to carry out clothes recommendation to the user.Wherein, with institute
The data that the human body identity and the body information for stating user match, refer to including with the human body identity and/or institute
It states body information and distinguishes garment data corresponding to identical or approximate human body identity and/or body information, specifically include:
1) garment data corresponding to human body identity identical or approximate with the human body identity, including age and shape of face
Deng with the corresponding attributive character of identical or similar properties human body identity.For example, if the age of one user of identification is male
30 years old, garment data corresponding to the age in the preset range about thirty years old floated respectively, such as 25 years old year can be filtered out
Clothes, the clothes of 35 years old age bracket and the clothes of 40 years old age bracket of age section.The human body identity is identical or approximate human body
The corresponding human body identity of every money clothes, can be the pre- target user for first passing through and manually setting in garment data corresponding to identity
Human body identity, be also possible to accumulation sales data in save purchase clothes user human body identity, for example, design one
Money clothes, the original intention of design are the males for 30 years old, the field value of the human body identity of this clothes can be assigned a value of 30 years old and
For male, during actual selling operation, by the accumulation of sales data, judgement has 35 years old male user to have purchased this
Money clothes, in another sample data of this clothes, the field value of the human body identity of this clothes can be assigned a value of 35 years old
And be male, the corresponding human body identity of this clothes includes 30 years old and is male and 35 years old and is two kinds of situations of male.
2) garment data corresponding to identical or approximate body information is distinguished with the body information, include and height
The identical perhaps approximate garment data of data and garment data identical or approximate with weight data etc..Wherein, with height number
According to identical or approximate garment data, refer to and preset range that the height that identifies floats up and down respectively in height number
According to corresponding garment data, for example, considering that the range of height may include height if the height identified is 175 centimetres
Corresponding to height in 175 centimetres of preset ranges to float up and down respectively such as respectively 170 centimetres, 175 centimetres and 180 centimetres
Garment data;Garment data identical or approximate with weight data, refers to and the weight that identifies floats up and down respectively
Garment data corresponding to weight data in preset range, for example, considering weight model if the weight identified is 70 kilograms
Enclose may include weight is respectively body in 70 kilograms of preset ranges to float up and down respectively such as 68 kilograms, 70 kilograms and 72 kilograms
The corresponding garment data of weight.
The information such as existing clothes fashion and garment size are matched with human body identity and body information in advance, it is this
Matching, which can be, to be artificially arranged, and is also possible to be accumulated in garment marketing data, and by clothes fashion and garment size
And human body identity and the matched data storage of body information are into database.For example, if being obtained by recognition of face and 3-D scanning
The human body information and body information for getting user F are respectively young male, 175 centimetres of height and 68 kilograms of weight, inquiry
Gender is young male, and height is the corresponding garment data of height of 175 centimetres of preset ranges to float up and down respectively, and combines
Weight is the corresponding garment data of weight of 68 kilograms of preset ranges to float up and down respectively, is therefrom found matched with user F
Clothes, if the information of a clothes L are as follows: coding A1, young male, size L, the human body identity of this clothing matching are young male
Property, the body information includes 175 centimetres and 68 kilograms of weight of matching, by the information coding A1 of above-mentioned clothes L, size L and is somebody's turn to do
The clothing information of this clothes such as color, the picture of money clothes is by showing that screen is shown to user F to carry out clothes to user F
Recommend.
When the embodiment of the present application recommends clothes, judge whether to detect human body by predetermined manner, if detecting
The human body obtains the facial image of the corresponding user of the human body by image capture device, logical according to the facial image
The accurate human body identity that recognition of face obtains the user is crossed, the human body identity refers to the attributive character of human body, according to the people
Body carries out the accurate body information that 3-D scanning obtains the user to the user by three-dimensional scanning device, in user's standard
On the basis of the true human body identity and the body information, based on matched with the human body identity and the body information
Big data analysis obtains and institute according to elder generation according to the human body identity sequence according to the body information again from database
Human body identity and the matched clothing information of the body information are stated, is believed the clothes including garment image by display screen
Breath is shown to the user to carry out clothes recommendation to the user, realizes the big data intelligence based on recognition of face and 3-D scanning
Energy clothes are recommended, and can be improved the accuracy of clothes recommendation, to improve the efficiency that intelligent clothing is recommended when choosing clothes.
Into one, obtained and the human body identity and the matched clothing information of the body information from database described
The step of before further include:
It is matched described in determination according to the human body identity and the body information with the individual type data of storage
The individual type of user.
Described obtain from database is wrapped with the step of human body identity and the body information matched clothing information
It includes:
It is obtained and the matched clothing information of the individual type from database.
Wherein, individual type refers to crowd's type belonging to user's individual, for example, boy, girl, young male, male
Middle age, male is old, women is young, women is middle aged and the individual types such as female old aged people, height are fat or thin.
Specifically, due to individual type difference, there are different that is, different people to be suitble to different clothes for clothes
's.Clothes between different individual types are general or cannot obscure mutually, for example, boy be not suitable for male middle age or
The clothes in male's old age, girl are also not suitable for the clothes of women middle age or female old aged people.According to the human body identity and body of acquisition
The individual type that material information etc. determines is children or adult, and the human body upper body obtained for example, being male or women
And the fat or thin physical characteristic of height that corresponding size of the lower part of the body etc. determines classifies user from the big data of accumulation, and according to
User's classification, selectes corresponding clothes fashion and size, recommends suitable clothes to user.For example, if human body is young man,
175CM high, 70 kilograms of weight, then human body is classified as XXL size by the body information for needing to meet for XXL size according to jacket
In this kind, recommend the jacket of XXL size to user.If identification user belong to the fat figure of comparison, recommend loose clothes to
User, can more be suitble to the demand of wearing of user, if judging, user is excessively thin and weak, recommend the clothes of close-fitting money to user.
When the embodiment of the present application recommends clothes, judge whether to detect human body by predetermined manner, if detecting
The human body obtains the accurate human body identity of the user by recognition of face, and the human body identity refers to the attributive character of human body,
According to the human body, the accurate body information of the user is obtained by user described in 3-D scanning, it is accurately described in user
On the basis of human body identity and the body information, with the determination user is matched with the individual type data of storage
Body type to accurately determine the individual type of user, then obtains and the human body identity and the stature from database
The clothing information of information matches is realized by showing that screen is shown to user to carry out clothes recommendation and is based on recognition of face and three-dimensional
The big data intelligent clothing of scanning is recommended, and by determining individual type described in user, may be implemented accurately to recommend, Neng Gouti
The accuracy that high clothes are recommended, to improve the efficiency that intelligent clothing is recommended when choosing clothes.
In one embodiment, the human body identity for obtaining the user by recognition of face according to the facial image
The step of include:
Gender, age and the shape of face of the user are obtained by recognition of face according to the facial image.
Wherein, shape of face refers to the profile of face.The upper half of face is made of maxilla, cheekbone, temporal bone, frontal bone and parietal bone
Arc-shaped structure, lower half depend on mandibular form, these all be influence shape of face an important factor for.Jawbone has risen very heavy
The effect wanted determines the foundation structure of shape of face.
Specifically, since different shapes of face are suitble to different garment coordinations, such as long face, it is suitble to wear the clothes of Jewel neck,
It can wear high neckline, polo shirt or the jacket being branded as, but uncomfortable suitable V-arrangement neckline identical with shape of face and the low neck opened
Son;Square face is suitble to wear the clothes of V-arrangement or spoon shape neck, not wear the clothes of rectangular neckline, if clothes is led in top of arranging in pairs or groups again,
That is just equivalent to square face and be exaggerated, that is just at extreme too big, and plain, round face, wears V-arrangement neck or lapel clothing certainly
Clothes, the clothes of uncomfortable suitable Jewel neck, thick neck are suitble to wear spacious opening door collar, certainly also should not be too wide or too narrow, unsuitable
The clothes of close the door neck or narrow neckline is worn, short neck is suitble to wear the clothes of spacious neck, lapel or lowdosage, certainly namely
The clothes of uncomfortable suitable polo-neck mouth.Wherein, shape of face can be carried out automatically by the unsupervised learning mode in artificial intelligence
Identification.The people of different shapes of face and different stature has proper garment coordination, can be with by recognition of face and 3-D scanning
The identity for accurately identifying user is collected simultaneously the letter such as body information of user, such as height, measurements of the chest, waist and hips, shoulder breadth and shape of face
Breath, so that gender, age and the shape of face of the user are obtained to the clothes of the suitable user of user's recommendation according to recognition of face, thus
Improve the accuracy and efficiency that clothes are recommended.
Further, the step of human body identity for obtaining the user by recognition of face according to the facial image
It include: gender, age, shape of face and the face complexion for obtaining the user by recognition of face according to the facial image.
Wherein, the colour of skin is the essential characteristic of face, and the point of penetration as Face datection is most simple, intuitive.In cromogram
As in, the colour of skin typically relatively collection neutralizes stable region, while studies have shown that different race, age and gender
People on main distinction main brightness in the colour of skin, remove this factor of brightness, the colour of skin has in certain colour of skin space
There is certain cluster, by realizing detection and segmentation to the colour of skin.Everyone colour of skin has a keynote, some clothes face
Color and certain ten divisions of keynote serve as a contrast, and some but becomes intense darkness without light, to find out the clothing color of the suitable colour of skin, needs first to find out use
The colour of skin keynote at family, the different people of the colour of skin are suitable for the clothes of different colours.Such as:
(1) speciality of fair skin be cheek through the sun once shine be easy it is rubescent because most of color can enable it is white
Fair-skinned skin more beautiful is moving, can most protrude pure white skin especially in colour system with yellow class and blue series, and entirety is enabled to seem bright
Amorous photo people, the bright color such as example greenish orange red, lemon yellow of tone, apple green, purplish red, sky blue are most suitable for but, for fair skin
User, the clothes of yellow class and blue series can be recommended, it is particularly recommended that such as greenish orange red, lemon yellow, apple green, purplish red, sky blue
Etc. the clothes of bright color.
(2) the deeper people of skin color is suitble to some dark brown colour system clothes, you is enabled apparently more to have individual character.Blackish green, purplish red, coffee
Coffee color, golden yellow can all make you apparently naturally graceful, and opposite blue series are then incompatible with you, do not wear the upper of blue series preferably
Clothing.
(3) what skin was partially yellow preferably wears blue cast clothes, such as the colors such as wine is red, pale purple, purplish blue, and face can be enabled more pale,
But strong yellow class is not worn preferably such as brown, Exocarpium Citri Rubrum etc., is not worn, in order to avoid complexion is enabled to seem more dark yellow no brilliance.Health
Wheat, the collocation of this sharp contrast of black and white and they are unusual closes lining, the heavy real tone such as dark blue, charcoal ash and it is pink,
These dark red, emerald green bright colors can most protrude optimistic individual character.
In clothes recommendation, recommends different clothes for the different colours of skin, relatively good recommendation effect may be implemented, from
And improve the efficiency that clothes are recommended and chosen.For example, the human body of colour of skin depth is suitble to saturate clothes, the white or shallow people of the colour of skin
It is suitble to the clothes etc. of light tone, according to human body identity, body information and face complexion, recommends corresponding clothes, can more improve clothes
It fills the accuracy recommended and improves the efficiency that clothes are recommended.
In one embodiment, gender, the year for obtaining the user by recognition of face according to the facial image
When the step of age and shape of face, further includes:
The human face expression of the user is obtained according to the human face expression by recognition of face according to the facial image
Obtain the personality information of the user.
Specifically, the personality that user can also be judged by recognition of face, in conjunction with people personality psychology classify with
Recommend the clothes for being suitble to user's personality.For example, recognition of face detect face be in smile epidemic situation comparison it is permanent when, can be pre-
Genus Homo is surveyed in more optimistic personality, optimistic personality generally relatively flexibly, is ready to attempt novel thing, so that it may in this way
User recommend the brightly painted clothes of fashion fashion trend, if identified by way of recognition of face face be in it is conscientious
It says the state laughed at, can predict that Genus Homo in relatively more proper state, can predict that Genus Homo in than more conservative personality, guards personality
People it is generally more stubborn and select single, do not like the clothes attempted fresh affairs or excessively make widely known lofty tone, can be with
The clothes for recommending dark mainstream classic look to such user, can more meet the demand of client.
Referring to Fig. 3, Fig. 3 is another stream of the clothes recommended method provided by the embodiments of the present application based on recognition of face
Journey schematic diagram.As shown in figure 3, in this embodiment, it is described based on matched big with the human body identity and the body information
Data analysis, according to elder generation according to the human body identity sequence according to the body information again, obtained from database with it is described
Before the step of human body identity and the body information matched clothing information, further includes:
S305, the interactive information interacted with the user is received;
It is described based on the human body identity and the matched big data analysis of the body information, according to elder generation according to the people
Body part sequence according to the body information again, obtains from database and matches with the human body identity and the body information
Clothing information the step of include:
S306, based on the human body identity, the body information and the matched big data analysis of the interactive information, press
According to the sequence according to the human body identity, the body information and the interactive information, obtained and the human body from database
Identity, body information matching and the matched clothing information of the interactive information.
Specifically, the step S301-S304 and S307 in embodiment illustrated in fig. 3 can be respectively corresponded refering to real shown in Fig. 2
The step S201 to S204 and S206 in example is applied, by reference by step S201-S204 and S206 in embodiment illustrated in fig. 2
It is incorporated herein, details are not described herein.In order to more accurately accurately recommend clothes to user, in addition to tentatively according to user's
Human body identity and body information are recommended further pass through pre- with after human body identity and the matched clothes of body information to user
Rhetoric question topic and user interact, with user interaction during obtain interactive information, according to interactive information judge deeper into
User information, for example the color liked of user is light tone or dark color, and style is crew neck or stand-up collar, and style is generous succinct
Or the hobby of the equal users itself of modification of complicated is inclined to, and is known according to the industry of the customer interaction information combination apparel industry of acquisition
Know, by the way of deep learning, the hobby of user is judged, and on the basis of user identity and body information, is adjusted
The whole clothes to user are recommended, and to realize the accurate recommendation to user, improve the efficiency of clothes recommendation and user's choosing clothes.
It is interacted, user can be carried out by being pre-designed several simple questions by machinery equipment and user
Test receives the test selection of user to select to recommend associated garments according to the test of user, according to the test result of user, benefit
With the big data knowledge of the apparel industry of storage, the hobby of user is predicted, in conjunction with the hobby of user, from according to human body identity and body
Material information recommends to correspond in the option of clothes, further reduces recommended range, realizes and precisely recommends.
Further, described the step of receiving the interactive information interacted with the user includes: to receive user to same
The tendency level data of the marking data of class stature dressing, the selection for buying situation or preference of arranging in pairs or groups, recommended user's clothes.
Wherein, marking data refer to that user gives a mark to the current dressing for recommending clothes, and in the case of 100 points, user is to current
Dressing makes 90 scores, shows that user is satisfied with current dressing, if user makes 50 scores to current dressing, shows that user is dissatisfied current
Dress.
The selection of purchase situation refers to whether test client can buy the selection currently arranged in pairs or groups, and client selects purchase surface visitor
The satisfied current collocation in family, client's selection are not bought, and show the dissatisfied current collocation of client.
Be inclined to level data, refer to user to collocation preference satisfaction, can by way of several stars, for example,
Five stars are set, if user selects five stars, show that user extremely meets current collocation, if user selects a star,
Show that user is not very interesting to current collocation.
Specifically, the test of simple, intuitive can be taken to reinforce interacting with user by electronic equipment, by user and
The simple interaction of friendly interface obtains user to phases such as the marking situation of similar stature dressing, purchase situation or collocation preferences
Information, marking and recommendation based on a large number of users in big data are closed, then from according to human body identity and body information, recommends corresponding clothes
In the option of dress, recommended range is further reduced, realize and precisely recommend, simultaneously because the marking of a large number of users and pushing away in big data
It recommends, can be implemented as user and more comprehensive collocation recommendation is provided.By recognition of face and 3-D scanning, can accurately identify
The identity of user out is collected simultaneously body information of user, such as height, three-dimensional, shoulder breadth etc., on the one hand, pass through user couple
The different collocation of similar stature are given a mark, it can be determined that the clothes preference of user recommends similar clothes for user.Another party
Face, marking of the user that can collect similar size to different collocation are selected the more suitable collocation of such stature and are recommended
User.After going out specific user by recognition of face, marking situation, purchase situation, collocation preference of user etc. can also be recorded, with
The reference recommended as clothes.
Referring to Fig. 4, Fig. 4 is a subflow in the clothes recommended method provided by the embodiments of the present application based on recognition of face
Journey schematic diagram, as shown in figure 4, in this embodiment, the step of receiving the interactive information interacted with the user packet
It includes:
S401, show that the dressing of the human body identity and the body information and default clothes fashion is arranged in pairs or groups so that the use
It scores dressing collocation at family;
S402, the score data that user arranges in pairs or groups to the dressing is received;
S403, the collocation preference that the user is obtained according to the score data;
It is described based on the human body identity, the body information and the matched big data analysis of the interactive information, press
According to the sequence according to the human body identity, the body information and the interactive information, obtained and the human body from database
The step of identity, body information matching and the interactive information matched clothing information includes:
Based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to
According to the human body identity, the body information and it is described collocation preference sequence, from database obtain with the human body identity,
The body information and the matched clothing information of the collocation preference.
Specifically, after the human body identity and body information for obtaining user, can be believed according to the human body identity and stature
Breath is selected arranges in pairs or groups with the dressing of the human body identity and the matched default clothes fashion of body information, and dressing collocation is passed through
Display screen is presented to the user, so that user gives a mark to dressing collocation, the marking feelings arranged in pairs or groups according to user to the dressing
Condition obtains the collocation preference of user, and then realizes and matched according to the human body identity, the body information and the collocation preference
Recommend clothes for user, is obtained from database matched with the human body identity, the body information and the collocation preference
Clothing information is pushed away by showing that screen is shown to user to carry out clothes recommendation to be embodied as the collocation of user individual's creation
It recommends
Further, it is also based on a large amount of user's marking data and recommending data, on the basis of big data analysis,
More comprehensive collocation is provided for user to recommend.
Please continue to refer to Fig. 3, it is described by display screen by include garment image the clothing information be shown to it is described
After the step of user is to carry out clothes recommendation to the user, further includes:
S308, it obtains from database and is shown to the associated default dress ornament of the clothing information by the display screen
The user is to carry out clothes recommendation.
Specifically, since the effect of clothes focuses on collocation, according to the user's choice, recommend mutually to arrange in pairs or groups with user's selection pre-
If dress ornament.For example, user has chosen a jacket, then the information such as style, the quality of jacket can be chosen according to user, according to pre-
Other dress ornaments relatively good with this jacket collocation dressing effect being first arranged, other preset dress ornaments are obtained from database and are pushed away
It recommends and gives other dress ornaments of trousers, shoes and hats, the jewellery etc. of the collocation of this jacket of user's selection, to realize wider scope and higher
The clothes of efficiency are recommended.
Please continue to refer to Fig. 3, it is described by display screen by include garment image the clothing information be shown to it is described
After the step of user is to carry out clothes recommendation to the user, further includes:
S309, by the garment marketing data in machine learning analytical database with obtain clothes recommendation classification information.
Wherein, machine learning includes the modes such as supervised learning, unsupervised learning and semi-supervised learning.
Specifically, by the garment marketing data in machine learning analytical database to obtain the classification letter of clothes recommendation
Breath, to improve the accuracy that clothes are recommended as far as possible.For example, analyzing a group by the sales data in database
Certain corresponding clothes sales volume is bigger, that is, this clothes is in " quick-fried money ", then subsequent clothes recommendation process, if identification
This clothes preferentially can be recommended user by the user that the group includes out, to improve the accuracy and clothes of clothes recommendation
The efficiency of recommendation.It for another example, can also be by combining the artificial of the machine learning such as unsupervised learning during clothes are recommended
Aptitude manner realizes the accuracy that garment coordination is recommended, for example, if passing through machine according to the big data of garment coordination database
It is higher that study analysis goes out a certain colour of skin and certain colour systems welcome degree of arranging in pairs or groups, so that it may by the clothes of this colour of skin and this cie system of color representation cie
Dress is recommended to be used as subsequent reference, alternatively, if a clothes are with a pair of shoes and/or the collocation of other accessories more by the joyous of user
It meets, so that it may which the clothes and the shoes and/or other accessories are arranged in pairs or groups to realize combined recommendation.
It is big it is possible to further will build up in such a way that the supervised learning of artificial intelligence and unsupervised learning combine
Amount user data is analyzed and is sorted out automatically, may include following procedure:
Firstly, user is received according to the categorical data of the experience input usually accumulated, for example, will according to dress designing original intention
Clothes fashion and corresponding group are matched, for example young money, middle aged money, old money etc. are matched with corresponding group.
Secondly, realizing that the user data that will build up on is finely divided again by way of unsupervised learning.For example, by man
Clothes are divided into young, middle age and old age, then in each classification, are looked good with according to the shape of face of different people and stature different
Style is classified, and the classification of clothing color is carried out according to the colour of skin of user, further according to the body information that the height of user is fat or thin
Recommend different sizes, so that the unsupervised learning by artificial intelligence successively segments the corresponding relationship of user and clothes to realize
Accurate recommendation to user's clothes.
Third is realized the update of clothes classification according to the user data of accumulation, is regularly updated in preset period of time point
Class, for example, three days, five days or a week etc., flexibly as increase new on seasonal variations and style is realized to fangle
Accurate recommendation.
In the embodiment of the present application, since the people of different shapes of face and different statures has proper garment coordination, lead to
Recognition of face and 3-D scanning are crossed, can accurately identify the identity of user, is collected simultaneously the body information of user, such as
Height, three-dimensional, shoulder breadth etc., then by obtaining user to the different interactive information given a mark of arranging in pairs or groups of similar stature to judge to use
The clothes preference at family recommends similar clothes for user, can also be according to the user of the similar size of accumulation to different collocation
Marking, selects the more suitable collocation of such stature and recommends user, after going out specific user by recognition of face, can also tie
The reference that the marking situation, purchase situation, collocation preference etc. for sharing family are recommended as clothes.The embodiment of the present application can bring with
Lower benefit:
1) it, is based on recognition of face user and 3-D scanning user, can accurately identify the identity of user and is collected into
The body information of user recommends clothes and garment coordination for user individual's creation, can be improved clothes and recommends and choose
Efficiency, to save the resource that clothes are chosen;
2), based on a large amount of user marking data and recommending data, more comprehensive collocation is provided for user and is recommended, thus
Improve efficiency and accuracy that clothes are recommended.
It should be noted that the clothes recommended method described in above-mentioned each embodiment based on recognition of face, it can basis
It needs the technical characteristic for including in different embodiments re-starting combination, to obtain the embodiment after combination, but all at this
Apply within desired protection scope.
Referring to Fig. 5, Fig. 5 is the schematic frame of the clothes recommendation apparatus provided by the embodiments of the present application based on recognition of face
Figure.Corresponding to the above-mentioned clothes recommended method based on recognition of face, the embodiment of the present application also provides a kind of based on recognition of face
Clothes recommendation apparatus.As shown in figure 5, it includes above-mentioned based on face knowledge for executing for being somebody's turn to do the clothes recommendation apparatus based on recognition of face
The unit of other clothes recommended method, the device can be configured in the computer equipments such as server.Specifically, figure is please referred to
5, it should include judging unit 501, first acquisition unit 502, second acquisition unit based on the clothes recommendation apparatus 500 of recognition of face
503, scanning element 504, third acquiring unit 505 and display unit 506.
Wherein, judging unit 501 detect human body for judging whether by predetermined manner;
First acquisition unit 502, if it is corresponding to obtain the human body by image capture device for detecting the human body
User facial image;
Second acquisition unit 503, for obtaining the human body body of the user by recognition of face according to the facial image
Part, the human body identity refers to the attributive character of human body;
Scanning element 504, for carrying out 3-D scanning to the user by three-dimensional scanning device to obtain the user
Body information;
Third acquiring unit 505, for based on the human body identity and the matched big data analysis of the body information,
According to elder generation according to the human body identity sequence according to the body information again, obtained from database with the human body identity and
The matched clothing information of body information;
Display unit 506, for the clothing information including garment image to be shown to the use by display screen
Family is to carry out clothes recommendation to the user.
In one embodiment, the second acquisition unit 503, for being obtained according to the facial image by recognition of face
Take gender, age and the shape of face of the user.
In one embodiment, the second acquisition unit 503 is also used to pass through recognition of face according to the facial image
The human face expression of the user is obtained to judge the personality information of the user according to the human face expression.
Referring to Fig. 6, Fig. 6 shows for another of the clothes recommendation apparatus provided by the embodiments of the present application based on recognition of face
Meaning property block diagram.As shown in fig. 6, in this embodiment, the clothes recommendation apparatus 500 based on recognition of face further include:
Receiving unit 507, for receiving the interactive information interacted with the user;
The third acquiring unit 505, for being based on and the human body identity, the body information and the interactive information
Matched big data analysis, according to the sequence according to the human body identity, the body information and the interactive information, from data
It obtains and is matched with the human body identity, the body information and the matched clothing information of the interactive information in library.
Please continue to refer to Fig. 6, as shown in fig. 6, the receiving unit 507 includes:
Subelement 5071 is shown, for showing the dressing of the human body identity and the body information and default clothes fashion
It arranges in pairs or groups so that the user scores to dressing collocation;
Receiving subelement 5072, the score data arranged in pairs or groups for receiving user to the dressing;
Subelement 5073 is obtained, for obtaining the collocation preference of the user according to the score data;
The third acquiring unit 505, for being based on and the human body identity, the body information and the interactive information
Matched big data analysis, according to the sequence according to the human body identity, the body information and the collocation preference, from data
It is obtained and the human body identity, the body information and the matched clothing information of the collocation preference in library.
Please continue to refer to Fig. 6, as shown in fig. 6, the clothes recommendation apparatus 500 based on recognition of face further include:
4th acquiring unit 508 passes through institute with the associated default dress ornament of the clothing information for obtaining from database
It states display screen and is shown to the user to carry out clothes recommendation;
Analytical unit 509, for obtaining clothes recommendation by the garment marketing data in machine learning analytical database
Classification information.
It should be noted that it is apparent to those skilled in the art that, the above-mentioned clothes based on recognition of face
The specific implementation process of recommendation apparatus and each unit is filled, it can be with reference to the corresponding description in preceding method embodiment, in order to describe
It is convenienct and succinct, details are not described herein.
Meanwhile the division of each unit and connection type are only used for lifting in the above-mentioned clothes recommendation apparatus based on recognition of face
Example explanation, in other embodiments, can be divided into as required different units for the clothes recommendation apparatus based on recognition of face,
Each unit in clothes recommendation apparatus based on recognition of face can also be taken the different order of connection and mode, to complete above-mentioned base
In all or part of function of the clothes recommendation apparatus of recognition of face.
The above-mentioned clothes recommendation apparatus based on recognition of face can be implemented as a kind of form of computer program, the computer
Program can be run in computer equipment as shown in Figure 7.
Referring to Fig. 7, Fig. 7 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The computer
Equipment 700 can be desktop computer, and perhaps the computer equipments such as server are also possible to component or portion in other equipment
Part.
Refering to Fig. 7, which includes processor 702, memory and the net connected by system bus 701
Network interface 705, wherein memory may include non-volatile memory medium 703 and built-in storage 704.
The non-volatile memory medium 703 can storage program area 7031 and computer program 7032.The computer program
7032 are performed, and processor 702 may make to execute a kind of above-mentioned clothes recommended method based on recognition of face.
The processor 702 is for providing calculating and control ability, to support the operation of entire computer equipment 700.
The built-in storage 704 provides environment for the operation of the computer program 7032 in non-volatile memory medium 703, should
When computer program 7032 is executed by processor 702, processor 702 may make to execute a kind of above-mentioned clothes based on recognition of face
Recommended method.
The network interface 705 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Fig. 7
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 700 thereon, specific computer equipment 700 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.For example, in some embodiments, computer equipment can
Only to include memory and processor, in such embodiments, reality shown in the structure and function and Fig. 7 of memory and processor
It is consistent to apply example, details are not described herein.
Wherein, the processor 702 is for running computer program 7032 stored in memory, to realize following step
It is rapid: to judge whether to detect human body by predetermined manner;If detecting the human body, the people is obtained by image capture device
The facial image of the corresponding user of body;The human body identity of the user, institute are obtained by recognition of face according to the facial image
State the attributive character that human body identity refers to human body;3-D scanning is carried out to obtain the use to the user by three-dimensional scanning device
The body information at family;Based on the human body identity and the matched big data analysis of the body information, according to first according to described in
The human body identity sequence according to the body information again obtains and the human body identity and the body information from database
The clothing information matched;It will include that the clothing information of garment image is shown to the user with to the use by display screen
Family carries out clothes recommendation.
In one embodiment, the processor 702 realize it is described according to the facial image by recognition of face acquisition
When the step of the human body identity of the user, following steps are implemented:
Gender, age and the shape of face of the user are obtained by recognition of face according to the facial image.
In one embodiment, the processor 702 realize it is described according to the facial image by recognition of face acquisition
When the step of the gender of the user, age and shape of face, also perform the steps of
The human face expression of the user is obtained according to the human face expression by recognition of face according to the facial image
Judge the personality information of the user.
In one embodiment, the processor 702 is realizing described be based on and the human body identity and the body information
Matched big data analysis is obtained from database according to elder generation according to the human body identity sequence according to the body information again
Take with the step of the human body identity and the body information matched clothing information before, also perform the steps of
Receive the interactive information interacted with the user;
The processor 702 is realizing described be based on and the human body identity and the matched big data of the body information point
Analysis obtains and the human body body from database according to elder generation according to the human body identity sequence according to the body information again
When the step of part and the matched clothing information of the body information, following steps are implemented:
Based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to
According to the sequence of the human body identity, the body information and the interactive information, obtained from database with the human body identity,
The body information matching and the matched clothing information of the interactive information.
In one embodiment, the processor 702 is in the interactive information for realizing that the reception is interacted with the user
Step when, implement following steps:
Show that the dressing of the human body identity and the body information and default clothes fashion is arranged in pairs or groups so that the user couple
The dressing collocation is scored;
Receive the score data that user arranges in pairs or groups to the dressing;
The collocation preference of the user is obtained according to the score data;
The processor 702 is realizing described be based on and the human body identity, the body information and the interactive information
Matched big data analysis, according to the sequence according to the human body identity, the body information and the interactive information, from data
It obtains and is matched with the human body identity, the body information and when the step of the matched clothing information of the interactive information in library,
Implement following steps:
Based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to
According to the human body identity, the body information and it is described collocation preference sequence, from database obtain with the human body identity,
The body information and the matched clothing information of the collocation preference.
In one embodiment, the processor 702 will include described in garment image realizing described by display screen
Clothing information was shown to after the step of user is to carry out clothes recommendation to the user, was also performed the steps of
Acquisition is shown to the associated default dress ornament of the clothing information by the display screen described from database
User is to carry out clothes recommendation.
In one embodiment, the processor 702 will include described in garment image realizing described by display screen
Clothing information was shown to after the step of user is to carry out clothes recommendation to the user, was also performed the steps of
By the garment marketing data in machine learning analytical database to obtain the classification information of clothes recommendation.
It should be appreciated that in the embodiment of the present application, processor 702 can be central processing unit (Central
ProcessingUnit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that can be completed by computer program, which can be stored in a computer readable storage medium.The computer
Program is executed by least one processor in the computer system, to realize the process step of the embodiment of the above method.
Therefore, the application also provides a kind of computer readable storage medium.The computer readable storage medium can be non-
The computer readable storage medium of volatibility, the computer-readable recording medium storage have computer program, the computer program
Processor is set to execute following steps when being executed by processor:
A kind of computer program product, when run on a computer, so that computer executes in the above various embodiments
The step of described clothes recommended method based on recognition of face.
The computer readable storage medium can be the internal storage unit of aforementioned device, such as the hard disk or interior of equipment
It deposits.What the computer readable storage medium was also possible to be equipped on the External memory equipment of the equipment, such as the equipment
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the computer readable storage medium can also both include the inside of the equipment
Storage unit also includes External memory equipment.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The computer readable storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), the various computer readable storage mediums that can store program code such as magnetic or disk.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond scope of the present application.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
Step in the embodiment of the present application method can be sequentially adjusted, merged and deleted according to actual needs.This Shen
Please the unit in embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the application
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, the technical solution of the application is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that an electronic equipment (can be individual
Computer, terminal or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
The above, the only specific embodiment of the application, but the bright protection scope of the application is not limited thereto, and is appointed
What those familiar with the art within the technical scope of the present application, can readily occur in various equivalent modifications or
Replacement, these modifications or substitutions should all cover within the scope of protection of this application.Therefore, the protection scope Ying Yiquan of the application
Subject to the protection scope that benefit requires.
Claims (10)
1. a kind of clothes recommended method based on recognition of face, which is characterized in that the described method includes:
Judge whether to detect human body by predetermined manner;
If detecting the human body, the facial image of the corresponding user of the human body is obtained by image capture device;
The human body identity of the user is obtained by recognition of face according to the facial image, the human body identity refers to the category of human body
Property feature;
3-D scanning is carried out to obtain the body information of the user to the user by three-dimensional scanning device;
Based on the human body identity and the matched big data analysis of the body information, according to elder generation according to the human body identity again
According to the sequence of the body information, obtains from database and believe with the human body identity and the matched clothes of the body information
Breath;
The clothing information including garment image is shown to the user to take to the user by display screen
Dress is recommended.
2. the clothes recommended method based on recognition of face according to claim 1, which is characterized in that described according to the face
Image is obtained the step of human body identity of the user by recognition of face and includes:
Gender, age and the shape of face of the user are obtained by recognition of face according to the facial image.
3. the clothes recommended method based on recognition of face according to claim 2, which is characterized in that described according to the face
When image obtains the step of the gender of the user, age and shape of face by recognition of face, further includes:
The human face expression of the user is obtained to obtain according to the human face expression by recognition of face according to the facial image
The personality information of the user.
4. the clothes recommended method based on recognition of face according to claim 1, which is characterized in that described to be based on and the people
Body part and the matched big data analysis of the body information, according to elder generation according to the human body identity again according to the body information
Sequence, from obtained in database with the step of the human body identity and the body information matched clothing information before, also
Include:
Receive the interactive information interacted with the user;
It is described based on the human body identity and the matched big data analysis of the body information, according to elder generation according to the human body body
Part sequence according to the body information again, obtains and the human body identity and the matched clothes of the body information from database
Fill information the step of include:
Based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to institute
The sequence for stating human body identity, the body information and the interactive information obtains and the human body identity, described from database
Body information matching and the matched clothing information of the interactive information.
5. the clothes recommended method based on recognition of face according to claim 4, which is characterized in that the reception and the use
The step of interactive information that family interacts includes:
Show that the dressing of the human body identity and the body information and default clothes fashion is arranged in pairs or groups so that the user is to described
Dressing collocation is scored;
Receive the score data that user arranges in pairs or groups to the dressing;
The collocation preference of the user is obtained according to the score data;
It is described based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to
According to the sequence of the human body identity, the body information and the interactive information, obtained from database with the human body identity,
The step of body information matching and the interactive information matched clothing information includes:
Based on the human body identity, the body information and the matched big data analysis of the interactive information, according to according to institute
The sequence for stating human body identity, the body information and the collocation preference, obtains and the human body identity, described from database
Body information and the matched clothing information of the collocation preference.
6. the clothes recommended method based on recognition of face according to claim 1, which is characterized in that described by showing screen
After the clothing information for including the steps that garment image is shown to the user to carry out clothes recommendation to the user,
Further include:
It is obtained from database and the user is shown to by the display screen with the clothing information associated default dress ornament
To carry out clothes recommendation.
7. the clothes recommended method described in -6 any one based on recognition of face according to claim 1, which is characterized in that described to pass through
The clothing information including garment image is shown to the user to carry out clothes recommendation to the user by display screen
After step, further includes:
By the garment marketing data in machine learning analytical database to obtain the classification information of clothes recommendation.
8. a kind of clothes recommendation apparatus based on recognition of face characterized by comprising
Judging unit detects human body for judging whether by predetermined manner;
First acquisition unit, if obtaining the corresponding user of the human body by image capture device for detecting the human body
Facial image;
Second acquisition unit, it is described for obtaining the human body identity of the user by recognition of face according to the facial image
Human body identity refers to the attributive character of human body;
Scanning element, for carrying out 3-D scanning to the user by three-dimensional scanning device to obtain the stature of the user and believe
Breath;
Third acquiring unit, for based on the human body identity and the matched big data analysis of the body information, according to elder generation
According to the human body identity sequence according to the body information again, obtained and the human body identity and the body from database
The clothing information of material information matches;
Display unit, for will include that the clothing information of garment image is shown to the user with to institute by display screen
It states user and carries out clothes recommendation.
9. a kind of computer equipment, which is characterized in that the computer equipment includes memory and is connected with the memory
Processor;The memory is for storing computer program;The processor is based on running and storing in the memory
Calculation machine program, the step of to execute clothes recommended method as described in claim any one of 1-7 based on recognition of face.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program are based on the processor execution as described in any one of claim 1-7
The step of clothes recommended method of recognition of face.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910374822.9A CN110264299A (en) | 2019-05-07 | 2019-05-07 | Clothes recommended method, device and computer equipment based on recognition of face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910374822.9A CN110264299A (en) | 2019-05-07 | 2019-05-07 | Clothes recommended method, device and computer equipment based on recognition of face |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110264299A true CN110264299A (en) | 2019-09-20 |
Family
ID=67914227
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910374822.9A Pending CN110264299A (en) | 2019-05-07 | 2019-05-07 | Clothes recommended method, device and computer equipment based on recognition of face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110264299A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110852264A (en) * | 2019-11-11 | 2020-02-28 | 南京奥拓软件技术有限公司 | Method and device for service directional recommendation based on face recognition |
CN110909610A (en) * | 2019-10-26 | 2020-03-24 | 湖北讯獒信息工程有限公司 | Accurate age identification method based on artificial intelligence |
CN110929583A (en) * | 2019-10-26 | 2020-03-27 | 湖北讯獒信息工程有限公司 | High-detection-precision face recognition method |
CN111124118A (en) * | 2019-12-19 | 2020-05-08 | 利诚服装集团股份有限公司 | Three-dimensional human body measurement interaction method, device and system and readable storage medium |
CN111242725A (en) * | 2020-01-06 | 2020-06-05 | 利诚服装集团股份有限公司 | Clothing recommendation method and device based on human body size acquisition and ordering method |
CN111274476A (en) * | 2020-01-16 | 2020-06-12 | 长春每房科技有限公司 | Room source matching method, device and equipment based on face recognition and storage medium |
CN111311355A (en) * | 2020-01-20 | 2020-06-19 | 深圳市博乐信息技术有限公司 | Method and module for pushing by applying identity recognition and AR pushing system |
CN111508079A (en) * | 2020-04-22 | 2020-08-07 | 深圳追一科技有限公司 | Virtual clothing fitting method and device, terminal equipment and storage medium |
CN111612584A (en) * | 2020-05-22 | 2020-09-01 | 杭州智珺智能科技有限公司 | AI intelligent clothing recommendation method based on wearing and putting-on theory |
CN111935229A (en) * | 2020-07-10 | 2020-11-13 | 北京云迹科技有限公司 | Intelligent container pushing method and device and electronic equipment |
CN112446767A (en) * | 2020-12-14 | 2021-03-05 | 武汉纺织大学 | Clothing recommendation system |
CN112990056A (en) * | 2021-03-29 | 2021-06-18 | 北京市商汤科技开发有限公司 | Age identification method and device, electronic equipment and storage medium |
CN113205380A (en) * | 2021-04-23 | 2021-08-03 | 广州未来一手网络科技有限公司 | Clothing interactive customization sale method, device, equipment and storage medium |
CN113204663A (en) * | 2021-04-23 | 2021-08-03 | 广州未来一手网络科技有限公司 | Information processing method and device for clothing matching |
CN113393304A (en) * | 2021-06-30 | 2021-09-14 | 青岛海尔工业智能研究院有限公司 | Garment customization method and device |
CN113459975A (en) * | 2021-07-31 | 2021-10-01 | 重庆长安新能源汽车科技有限公司 | Intelligent cabin system |
CN115131825A (en) * | 2022-07-14 | 2022-09-30 | 北京百度网讯科技有限公司 | Human body attribute identification method and device, electronic equipment and storage medium |
CN117033688A (en) * | 2023-08-11 | 2023-11-10 | 翡梧(上海)创意设计有限公司 | Character image scene generation system based on AI interaction |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140124087A (en) * | 2013-04-16 | 2014-10-24 | 허명구 | System and method for recommending hair based on face and style recognition |
CN105868259A (en) * | 2015-12-29 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | Video recommendation method and device based on face identification |
KR20180008246A (en) * | 2016-07-14 | 2018-01-24 | 카페24 주식회사 | Method, Apparatus and System for Evaluating Dress Code, and Method and System for Recommending Dress Code |
CN108009268A (en) * | 2017-12-15 | 2018-05-08 | 惠州市敦雅科技有限公司 | A kind of individual, which wears, takes intelligent recommendation method |
CN109117779A (en) * | 2018-08-06 | 2019-01-01 | 百度在线网络技术(北京)有限公司 | One kind, which is worn, takes recommended method, device and electronic equipment |
-
2019
- 2019-05-07 CN CN201910374822.9A patent/CN110264299A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140124087A (en) * | 2013-04-16 | 2014-10-24 | 허명구 | System and method for recommending hair based on face and style recognition |
CN105868259A (en) * | 2015-12-29 | 2016-08-17 | 乐视致新电子科技(天津)有限公司 | Video recommendation method and device based on face identification |
WO2017113740A1 (en) * | 2015-12-29 | 2017-07-06 | 乐视控股(北京)有限公司 | Face recognition based video recommendation method and device |
KR20180008246A (en) * | 2016-07-14 | 2018-01-24 | 카페24 주식회사 | Method, Apparatus and System for Evaluating Dress Code, and Method and System for Recommending Dress Code |
CN108009268A (en) * | 2017-12-15 | 2018-05-08 | 惠州市敦雅科技有限公司 | A kind of individual, which wears, takes intelligent recommendation method |
CN109117779A (en) * | 2018-08-06 | 2019-01-01 | 百度在线网络技术(北京)有限公司 | One kind, which is worn, takes recommended method, device and electronic equipment |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110909610A (en) * | 2019-10-26 | 2020-03-24 | 湖北讯獒信息工程有限公司 | Accurate age identification method based on artificial intelligence |
CN110929583A (en) * | 2019-10-26 | 2020-03-27 | 湖北讯獒信息工程有限公司 | High-detection-precision face recognition method |
CN110852264A (en) * | 2019-11-11 | 2020-02-28 | 南京奥拓软件技术有限公司 | Method and device for service directional recommendation based on face recognition |
CN111124118A (en) * | 2019-12-19 | 2020-05-08 | 利诚服装集团股份有限公司 | Three-dimensional human body measurement interaction method, device and system and readable storage medium |
CN111242725A (en) * | 2020-01-06 | 2020-06-05 | 利诚服装集团股份有限公司 | Clothing recommendation method and device based on human body size acquisition and ordering method |
CN111274476A (en) * | 2020-01-16 | 2020-06-12 | 长春每房科技有限公司 | Room source matching method, device and equipment based on face recognition and storage medium |
CN111311355A (en) * | 2020-01-20 | 2020-06-19 | 深圳市博乐信息技术有限公司 | Method and module for pushing by applying identity recognition and AR pushing system |
CN111508079B (en) * | 2020-04-22 | 2024-01-23 | 深圳追一科技有限公司 | Virtual clothes try-on method and device, terminal equipment and storage medium |
CN111508079A (en) * | 2020-04-22 | 2020-08-07 | 深圳追一科技有限公司 | Virtual clothing fitting method and device, terminal equipment and storage medium |
CN111612584A (en) * | 2020-05-22 | 2020-09-01 | 杭州智珺智能科技有限公司 | AI intelligent clothing recommendation method based on wearing and putting-on theory |
CN111935229A (en) * | 2020-07-10 | 2020-11-13 | 北京云迹科技有限公司 | Intelligent container pushing method and device and electronic equipment |
CN112446767A (en) * | 2020-12-14 | 2021-03-05 | 武汉纺织大学 | Clothing recommendation system |
CN112990056A (en) * | 2021-03-29 | 2021-06-18 | 北京市商汤科技开发有限公司 | Age identification method and device, electronic equipment and storage medium |
CN113205380A (en) * | 2021-04-23 | 2021-08-03 | 广州未来一手网络科技有限公司 | Clothing interactive customization sale method, device, equipment and storage medium |
CN113204663A (en) * | 2021-04-23 | 2021-08-03 | 广州未来一手网络科技有限公司 | Information processing method and device for clothing matching |
CN113393304A (en) * | 2021-06-30 | 2021-09-14 | 青岛海尔工业智能研究院有限公司 | Garment customization method and device |
CN113459975A (en) * | 2021-07-31 | 2021-10-01 | 重庆长安新能源汽车科技有限公司 | Intelligent cabin system |
CN113459975B (en) * | 2021-07-31 | 2022-10-04 | 重庆长安新能源汽车科技有限公司 | Intelligent cabin system |
CN115131825A (en) * | 2022-07-14 | 2022-09-30 | 北京百度网讯科技有限公司 | Human body attribute identification method and device, electronic equipment and storage medium |
CN117033688A (en) * | 2023-08-11 | 2023-11-10 | 翡梧(上海)创意设计有限公司 | Character image scene generation system based on AI interaction |
CN117033688B (en) * | 2023-08-11 | 2024-03-12 | 翡梧(上海)创意设计有限公司 | Character image scene generation system based on AI interaction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110264299A (en) | Clothes recommended method, device and computer equipment based on recognition of face | |
US11250047B2 (en) | Retrieval support system, retrieval support method and retrieval support program | |
CN106779977B (en) | Clothing matching method and system based on intelligent mobile terminal | |
US10157416B2 (en) | Computer implemented methods and systems for generating virtual body models for garment fit visualisation | |
CN108256975A (en) | Wearing for 3-D effect is provided for virtual fitting person take system and method based on artificial intelligence | |
CN109840825A (en) | The recommender system of physical features based on user | |
CN106709781A (en) | Personal image design and collocation purchasing device and method | |
CN106651433A (en) | Interactive intelligent fitting mirror system and fitting method | |
US20160026926A1 (en) | Clothing matching system and method | |
CN106776865A (en) | A kind of garment coordination method and system based on user's dynamic need | |
CN106354768B (en) | Color-based user and commodity matching method and commodity matching recommendation method | |
CN108538375A (en) | Shaping and beauty mechanism operation system based on artificial intelligence and small routine | |
CN107729380A (en) | Clothing matching method, terminal, terminal | |
CN106951448A (en) | A kind of personalization, which is worn, takes recommendation method and system | |
CN108876930A (en) | A kind of personal image management application method and system | |
CN108876430A (en) | A kind of advertisement sending method based on crowd characteristic, electronic equipment and storage medium | |
US11544768B2 (en) | System and method for fashion recommendations | |
CN110310164A (en) | Image processing system, method, platform, machine readable media and equipment | |
CN106651501A (en) | Clothing matching method and system based on human body feature information | |
CN110490711A (en) | A kind of personalized visualization design platform | |
CN206400626U (en) | Interactive intelligent fitting mirror system | |
CN112651809A (en) | Intelligent commodity recommendation method based on cloud computing and big data synergistic effect for vertical electronic commerce platform | |
CN104268773A (en) | Background household product decision-making assisting method and system based on consumption feature information | |
US11526925B2 (en) | System and method for fashion recommendations | |
US11430043B2 (en) | System and method for fashion recommendations |
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 |