CN109063758A - Clothes recognition methods and device based on picture - Google Patents
Clothes recognition methods and device based on picture Download PDFInfo
- Publication number
- CN109063758A CN109063758A CN201810802043.XA CN201810802043A CN109063758A CN 109063758 A CN109063758 A CN 109063758A CN 201810802043 A CN201810802043 A CN 201810802043A CN 109063758 A CN109063758 A CN 109063758A
- Authority
- CN
- China
- Prior art keywords
- information
- picture
- dress designing
- clothes
- pictorial information
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides based on picture clothes recognition methods and device, it is related to technical field of costume design, wherein, the clothes recognition methods based on picture includes: first, obtain the pictorial information of a dress designing, need exist for being illustrated is, an above-mentioned dress designing, which refers to, has at least contained the dress designing that design factor can be made or manufacture, secondly, in order to effectively examine or check the correlation degree of clothes current design and sales situation, pictorial information is identified by the vision situation of selling well model based on picture of training in advance, due to, in advance training the vision situation of selling well model based on picture be trained according to a variety of clothes instantly come, therefore, it can be good at measuring the sale trend of current dress designing, later, the sales forecast information of dress designing is obtained according to the result of identification, The sales situation that dress designing can be predicted by above-mentioned treatment process makes the clothes of design more by the favor of consumer.
Description
Technical field
The present invention relates to technical field of costume design, more particularly to clothes recognition methods and device based on picture.
Background technique
Clothes are the development with human society and constantly development and change.Phase in the time immemorial, the initial clothes of the mankind are
Made of leaf, animal skin etc., later, occur with bast-fibre and grass system etc. at clothing.And with the raising of productivity
With the development of science and technology, material becomes more and more abundant multiplicity, correspondingly, the type of the clothing of manufacture also gradually increases.In the modern times
In society, people can select the clothes for being suitble to oneself according to oneself hobby and specific requirements, in a certain sense for,
Clothes have been that everyone decorates oneself, protect oneself, can give the necessary supply of oneself and household, not just for wearing, even more one
Identity, a kind of life attitudes, one displaying charisma performance.
Therefore, during dress designing, it is necessary to comprehensively consider various factors just and can make the clothes designed by
The favor of consumer.But the various factors of dress designing is influenced, for example, society, science and technology, amusement etc. change in real time, why
Sample enables the clothes of design are liked it being a problem for clothing design by the majority of consumers, there is no at present effectively
Solution.
Summary of the invention
In view of this, clothes recognition methods and the device of the embodiment of the present invention being designed to provide based on picture, lead to
It crosses and presets the situation of selling well of the vision based on picture model and the pictorial information of dress designing is identified etc., effectively improve pair
The sales forecast of dress designing.
In a first aspect, the embodiment of the invention provides the clothes recognition methods based on picture, comprising:
Obtain the pictorial information of a dress designing；
The pictorial information is identified by the vision situation of selling well model based on picture of training in advance；
The sales forecast information of dress designing is obtained according to the result of identification.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein institute
The step of stating the pictorial information for obtaining a dress designing, comprising:
Search the corresponding pressing information of a dress designing；
The pressing information is shot, the pictorial information of dress designing is obtained.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein institute
The step of stating the pictorial information for obtaining a dress designing, comprising:
Search the design archive information an of dress designing；
The design archive information is shot, the pictorial information of dress designing is obtained.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein institute
State by the pictorial information by advance training the vision situation of selling well model based on picture identified the step of before, comprising:
Row shooting is put into more suits respectively, obtains multiple garment images；
Multiple described garment images are trained, clothes identification model is obtained；
The sales information of multiple garment images is extracted, and, the sales information is passed through into the clothes identification model
It is identified to obtain design feature information；
The sales information and the design feature information are trained, the vision situation of selling well mould based on picture is obtained
Type.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein institute
State the step of being identified the pictorial information by the vision situation of selling well model based on picture of training in advance, comprising:
The pictorial information is input in the vision situation of selling well model based on picture described in training in advance；
The vision situation of selling well model based on picture carries out various dimensions identification to the pictorial information according to training rules.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein institute
The step of stating the sales forecast information that dress designing is obtained according to the result of identification, comprising:
Sales forecast is carried out to the pictorial information by the vision situation of selling well model based on picture；
It is generated according to the result of sales forecast and recommends dress designing information.
The 5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein the method also includes:
When the pictorial information has multiple, multiple pictorial informations are carried out respectively by the vision situation of selling well model
Sales forecast；
Multiple recommendation dress designing information are generated according to the result of sales forecast；
Multiple recommendation dress designing information are ranked up according to the sequence of recommendation grade from high to low.
Second aspect, the embodiment of the invention provides the clothes identification devices based on picture, comprising:
Picture obtains module, for obtaining the pictorial information of a dress designing；
Identification module, for knowing the pictorial information by the vision situation of selling well model based on picture of training in advance
Not；
Sales forecast module obtains the sales forecast information of dress designing for the result according to identification.
The third aspect, the embodiment of the present invention also provide a kind of terminal, including memory and processor, and memory is for depositing
Storage supports processor to execute the program for the clothes recognition methods based on picture that above-mentioned aspect provides, and processor is configurable for
Execute the program stored in memory.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, computer readable storage medium
On be stored with computer program, when computer program is run by processor execute any of the above-described method the step of.
Clothes recognition methods and device provided in an embodiment of the present invention based on picture, wherein should the clothes based on picture
Recognition methods includes: the pictorial information firstly, one dress designing of acquisition, needs to be illustrated herein, an above-mentioned clothes
Installing meter, which refers to, has at least contained the dress designing that design factor can be made or manufacture,
It is secondary, in order to examine or check the correlation degree of clothes current design and sales situation, by pictorial information by training in advance based on figure
The vision situation of selling well model of piece identified, since the vision situation of selling well model based on picture of training is more according to instantly in advance
Kind of clothes and its sales situation, which are trained, to be obtained, therefore, should vision situation of selling well model based on picture can be good at weighing
The sales trend of current dress designing is measured, later, after above-mentioned pictorial information to be inputted to the vision situation of selling well model based on picture, energy
It is enough that the sales forecast information of dress designing is obtained according to the result of identification, by above-mentioned treatment process, that is, obtain dress designing
It is effectively combined with the vision situation of selling well model based on picture after pictorial information, it can be pre- according to current trend fashion etc.
The sales situation of dress designing is measured, so that being conducive to designer designs the clothes being more received by the market.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 shows the first pass figure of the clothes recognition methods based on picture provided by the embodiment of the present invention；
Fig. 2 shows the second flow charts of the clothes recognition methods provided by the embodiment of the present invention based on picture；
Fig. 3 shows the structure connection figure of the clothes identification device based on picture provided by the embodiment of the present invention.
Icon: 1- picture obtains module；2- identification module；3- sales forecast module.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Currently, science and technology have made huge strides, fashion is constantly developed, and during dress designing, how to be designed
Meeting the clothes of consumers' aesthetic and obtaining good sales volume is a problem for clothing design.Especially by shadow
The various factors of dress designing is rung, for example, the factors such as society, science and technology, amusement all change in real time, how to ensure and designs
Clothes have good sales situation, there is no effective solution method at present.
Based on this, the embodiment of the invention provides based on picture clothes recognition methods and device, below by embodiment
It is described.
Embodiment 1
Referring to Fig. 1 and Fig. 2, the present embodiment propose the clothes recognition methods based on picture specifically includes the following steps:
Step S101: the pictorial information of a dress designing is obtained.
In the present embodiment, an above-mentioned dress designing refers to that at least having contained design factor can make or
A dress designing through making usually first designs the relevant information of clothes in the design process of clothes,
This, the relevant information of clothes, which can obtain concentrating by pictorial information, to be showed, and later, makes clothes according to above-mentioned pictorial information.
Therefore, above-mentioned pictorial information and a dress designing are one-to-one, also, usually by above-mentioned pictorial information and a clothes
Design, which is united, to be stored, to facilitate designer and producer etc. to check.And the size, style, face of clothes itself
Color etc. can not be directly comprehensively compared, and therefore, in the clothes recognition methods based on model, need first to extract a clothes
Pictorial information in design.
Step S102: pictorial information is identified by the vision situation of selling well model based on picture of training in advance.
In the present embodiment, since the vision situation of selling well model based on picture of training in advance is comprehensive current multiple types
Clothes and train come characteristic model.Therefore, in implementation process, above-mentioned pictorial information is input to this based on picture
Vision situation of selling well model identified in can fast and accurately identify a dress designing corresponding with pictorial information fashion,
The characteristic feature of classification and color etc., the result that can be fast and accurately identified.
Step S103: the sales forecast information of dress designing is obtained according to the result of identification.
After the result for obtaining above-mentioned identification, the sales forecast letter of dress designing corresponding to the clothes can be obtained
Breath has obtained fashion, classification and color of one dress designing of characterization etc. by the vision situation of selling well model based on picture
The sales volume situation of characteristic feature.It needs to be illustrated, which has specifically included the ruler of a dress designing
The specific influence on garment marketing such as very little, style, color proportion, the result of the identification based on above-mentioned pictorial information can be taken
Install the sales forecast information of meter.
A kind of generating process of pictorial information, the step of the pictorial information of above-mentioned one dress designing of acquisition are specifically told about below
Suddenly, comprising:
(1) the corresponding pressing information of a dress designing is searched.
Due to needing first to design a set of pressing, and obtain after constantly correct to pressing before making clothes
The sizing file of one dress designing, i.e. referred to as pressing information.In process later, specifically made according to pressing information
Make clothes.In the present embodiment, the form of the corresponding pressing information of a dress designing of acquisition is paper-based form.
(2) pressing information is shot, obtains the pictorial information of dress designing.
Since dress designing is mostly the frame information described in drawing or drafting instrument, rather than garment body.Cause
This measures dress designing in order to unified, the pressing information for one-to-one part dress designing of uniting is clapped in the present embodiment
It takes the photograph, to obtain the pictorial information of dress designing.
The generating process of another pictorial information is specifically told about below, the pictorial information of above-mentioned one dress designing of acquisition
Step, comprising:
(1) the design archive information of a dress designing is searched.
Since the dress designing of complete set is as made of multiple details synthesis.When need to a dress designing into
When row synthesis examination, the design archive information an of dress designing can be searched, directly so as to conveniently obtain one
The global feature of dress designing.
Search the design archive information of a dress designing to consider to dress designing.In general, composition design shelves
The archives element information of case information has multiple, also, is different between each archives element information, in terms of different
To be considered to dress designing.It is different from multiple and different element informations is obtained by picture, archives element information be mostly with
The form of text and symbol indicates.Above-mentioned pictorial information is usually electronic parameter form.
(2) design archive information is shot, obtains the pictorial information of dress designing.
Since the design archive information inconvenience indicated in the form of text and symbol is compared one by one.Thus, having
In body implementation process, design archive information is shot, the pictorial information of dress designing is obtained, later, with pictorial information
Form carries out subsequent processing.
Here the generating process of the vision situation of selling well model based on picture under introducing first, it is above-mentioned to pass through pictorial information in advance
Before the step of trained vision situation of selling well model based on picture is identified, comprising:
Step S001: putting into row shooting to more suits respectively, obtain multiple garment images,
It needs to be illustrated, above-mentioned more set clothes are to investigate fashion, characteristic of division in advance by big data
With color characteristic.In the present embodiment, row shooting is put into more suits, and obtaining multiple garment images can be more comprehensive
Come to its influence to sales situation of the comprehensive considerations such as fashion, characteristic of division and color characteristic.Here, the tricks of clothes is also
Need to consider many and diverse factor that subsequent training calculates, when it is implemented, the tricks of clothes according to circumstances can flexibly be set.
Step S002: being trained multiple garment images, obtains clothes identification model.
Firstly, the fashion factor to multiple garment images is trained, fashion tag recognition model is obtained.In implementation process
In, first the fashion factor of multiple garment images is trained, that is, after the fashion factor calculating for integrating every garment image, is obtained
The fashion tag recognition model of the fashion degree of some fashion factor can be examined or check.
Secondly, the classification factor to multiple garment images is trained, Classification and Identification model is obtained.In implementation process,
The classification factor of multiple garment images is trained, that is, after the classification factor calculating for integrating every garment image, obtaining can
Examine or check the Classification and Identification model of the classification satisfaction of some classification factor.It needs to be illustrated, the type of classification can be
Classify according to the style of clothes, material or translucency.
Secondly, the color factors to multiple garment images are trained, color identification model is obtained.In implementation process,
The color factors of multiple garment images are trained, that is, after the color factors calculating for integrating every garment image, obtaining can
Examine or check the color identification model of the color satisfaction of some color factors.It needs to be illustrated, the type of color can be
Classify according to default rule.
Later, the view based on picture is generated in conjunction with fashion tag recognition model, Classification and Identification model and color identification model
Feel situation of selling well model, the sales volume situation that the dress designing considered is treated by the classification of multi-angle carries out Comprehensive Assessment, that is, passes through
Vision situation of selling well model obtains the model that sales forecast can be carried out for other dress designing to the training of multiple garment images.
Step S003: extracting the sales information of multiple garment images, also, by sales information by clothes identification model into
Row identification obtains design feature information.
When it is implemented, first obtaining the sales information generated corresponding to multiple garment images, and the sales information is defeated
Enter into clothes identification model obtained in above-mentioned steps S002 and identified, in this way the identification Jing Guo clothes identification model, energy
Design feature information is accessed, here, design feature information can characterize dress designing from fashion, classification and color etc.
Sale tendency.
Step S004: sales information and design feature information are trained, and obtain the vision situation of selling well model based on picture.
When it is implemented, the sales information of said extracted and design feature information unification are trained, it is special to obtain design
Levy the vision situation of selling well model based on picture of informational influence sales information.
Above-mentioned the step of being identified pictorial information by the vision situation of selling well model based on picture of training in advance, packet
It includes:
(1) pictorial information is input in the vision situation of selling well model based on picture of training in advance.
When it is implemented, being input to preparatory instruction as input parameter after getting the pictorial information of dress designing
It is considered in the experienced clothes identification model based on picture, i.e., predicts that current clothes are set by the comparison of priori value
The sales situation of meter.
(2) the vision situation of selling well model based on picture carries out various dimensions identification to pictorial information according to training rules.
It needs exist for being illustrated, the process considered is the clothes identification model based on picture according to training rules
Above-mentioned pictorial information is identified, needs to be illustrated, above-mentioned training rules be respectively according to fashion factor, classification because
Element and color factors carry out various dimensions identification to the data information of input, to be measured to pictorial information comprehensively.
The above-mentioned result according to identification obtains the step of sales forecast information of dress designing, comprising:
(1) sales forecast is carried out to pictorial information by the vision situation of selling well model based on picture.
The image information of dress designing is obtained by way of shooting picture, meanwhile, it is in great demand by the vision based on picture
Model identifies above-mentioned various dimensions, gets the sales forecast of dress designing, is specifically refined as current fashion, classification and color
Deng the integrated forecasting etc. for dress designing sales situation.
(2) it is generated according to the result of sales forecast and recommends dress designing information.
In order to effectively feed back market situation, it can be generated according to the result of sales forecast in the present embodiment and recommend dress designing
Information can make improvements that is, when some dress designing does not meet the sales trend recommended in vision situation of selling well model；When
When some dress designing extremely meets the sales trend recommended in vision situation of selling well model, corresponding recommendation dress designing letter is generated
Breath.
In addition, the above-mentioned clothes recognition methods based on picture further include:
(1) when pictorial information has it is multiple when, that is, have the pictorial information of multiple dress designing need to carry out sales forecast or
The when pictorial information of multiple angles of one dress designing needs to carry out sales forecast, by vision situation of selling well model respectively to multiple
Pictorial information carries out sales forecast.
It needs exist for being illustrated, the purpose for carrying out sales forecast is market in order to further consider dress designing
Situation.Form shooting picture, which obtains, has sold the pictorial informations of clothes come by way of carrying out sales forecast, more intuitive quasi-
Really.
(2) also, in order to effectively feed back market situation, multiple recommendation dress designing are generated according to the result of sales forecast
Information can comprehensively and effectively measure happiness of the consumer to various dress designing by multiple generations for recommending dress designing information
Love degree, effectively to be corrected to the pictorial information of dress designing.
(3) multiple recommendation dress designing information are ranked up according to the sequence of recommendation grade from high to low.
For the feedback for considering market definitely, by multiple recommendation dress designing information according to recommendation grade by
High to Low sequence is ranked up, to conveniently check.It needs exist for being illustrated, certain recommendation dress designing therein
Information can also be shown using mark is highlighted, and kept the result obtained more significant, checked convenient for designer.
In conclusion the clothes recognition methods provided in this embodiment based on picture includes: to set firstly, obtaining a clothes
The pictorial information of meter, secondly, passing through pictorial information pre- to examine or check the correlation degree of clothes current design and sales situation
First training the vision situation of selling well model based on picture identified, by advance training the vision situation of selling well model based on picture come
To instantly a variety of clothes and its sales situation be trained, i.e., the purchase intention of consumer is examined or check by priori accumulation,
Later, after above-mentioned pictorial information to be inputted to the vision situation of selling well model based on picture, clothes can be obtained according to the result of identification
The sales forecast information of design, by above-mentioned treatment process, i.e., after the pictorial information of acquisition dress designing by its be based on picture
Vision situation of selling well model effectively combined, current clothes can be measured well by the vision situation of selling well model based on picture
The sales trend of design, and effective sales forecast is carried out to current dress designing, it is designed more to be conducive to designer
Add by the favorite clothes of consumer.
Embodiment 2
Referring to Fig. 3, present embodiments providing the clothes identification device based on picture includes:
Picture obtains module 1, for obtaining the pictorial information of a dress designing；
Identification module 2, for identifying pictorial information by the vision situation of selling well model based on picture of training in advance；
Sales forecast module 3 obtains the sales forecast information of dress designing for the result according to identification.
Clothes identification device provided in an embodiment of the present invention based on picture, with provided by the above embodiment based on picture
Clothes recognition methods technical characteristic having the same reaches identical technical effect so also can solve identical technical problem.
The embodiment of the invention also provides a kind of terminal, including memory and processor, memory is supported for storing
Processor executes the program of above-described embodiment method, and processor is configurable for executing the program stored in memory.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program, when computer program is run by processor the step of the method for execution any of the above-described.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
The technical effect of clothes recognition methods and device provided by the embodiment of the present invention based on picture, realization principle and generation and
Preceding method embodiment is identical, and to briefly describe, Installation practice part does not refer to place, can refer in preceding method embodiment
Corresponding contents.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent portion can also be integrated to form with two or more modules
Point.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution 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 a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence, indication or suggestion relative importance can not be interpreted as.Moreover, term " packet
Include ", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion so that including the mistake of a series of elements
Journey, method, article or equipment not only include those elements, but also including other elements that are not explicitly listed, either
It further include for elements inherent to such a process, method, article, or device.In the absence of more restrictions, by sentence
The element that "including a ..." limits, it is not excluded that also deposit in the process, method, article or apparatus that includes the element
In other identical element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. the clothes recognition methods based on picture characterized by comprising
Obtain the pictorial information of a dress designing；
The pictorial information is identified by the vision situation of selling well model based on picture of training in advance；
The sales forecast information of dress designing is obtained according to the result of identification.
2. the clothes recognition methods according to claim 1 based on picture, which is characterized in that one clothes of the acquisition are set
The step of pictorial information of meter, comprising:
Search the corresponding pressing information of a dress designing；
The pressing information is shot, the pictorial information of dress designing is obtained.
3. the clothes recognition methods according to claim 1 based on picture, which is characterized in that one clothes of the acquisition are set
The step of pictorial information of meter, comprising:
Search the design archive information an of dress designing；
The design archive information is shot, the pictorial information of dress designing is obtained.
4. the clothes recognition methods according to claim 1 based on picture, which is characterized in that described by the pictorial information
Before the step of being identified by the vision situation of selling well model based on picture of training in advance, comprising:
Row shooting is put into more suits respectively, obtains multiple garment images；
Multiple described garment images are trained, clothes identification model is obtained；
The sales information of multiple garment images is extracted, and, the sales information is carried out by the clothes identification model
Identification obtains design feature information；
The sales information and the design feature information are trained, the vision situation of selling well model based on picture is obtained.
5. the clothes recognition methods according to claim 1 based on picture, which is characterized in that described by the pictorial information
The step of being identified by the vision situation of selling well model based on picture of training in advance, comprising:
The pictorial information is input in the vision situation of selling well model based on picture described in training in advance；
The vision situation of selling well model based on picture carries out various dimensions identification to the pictorial information according to training rules.
6. the clothes recognition methods according to claim 1 based on picture, which is characterized in that the result according to identification
The step of obtaining the sales forecast information of dress designing, comprising:
Sales forecast is carried out to the pictorial information by the vision situation of selling well model based on picture；
It is generated according to the result of sales forecast and recommends dress designing information.
7. the clothes recognition methods according to claim 6 based on picture, which is characterized in that the method also includes:
When the pictorial information has multiple, multiple pictorial informations are sold respectively by the vision situation of selling well model
Prediction；
Multiple recommendation dress designing information are generated according to the result of sales forecast；
Multiple recommendation dress designing information are ranked up according to the sequence of recommendation grade from high to low.
8. the clothes identification device based on picture characterized by comprising
Picture obtains module, for obtaining the pictorial information of a dress designing；
Identification module, for identifying the pictorial information by the vision situation of selling well model based on picture of training in advance；
Sales forecast module obtains the sales forecast information of dress designing for the result according to identification.
9. a kind of terminal, which is characterized in that including memory and processor, the memory supports processor to hold for storing
The program of any one of row claim 1 to 7 the method, the processor is configured to being stored in the memory for executing
Program.
10. a kind of computer readable storage medium, it is stored with computer program on computer readable storage medium, feature exists
In when computer program is run by processor the step of any one of execution the claims 1 to 7 the method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810802043.XA CN109063758A (en) | 2018-07-19 | 2018-07-19 | Clothes recognition methods and device based on picture |
| CN201910604280.XA CN110147854A (en) | 2018-07-19 | 2019-07-05 | Clothes recognition methods, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810802043.XA CN109063758A (en) | 2018-07-19 | 2018-07-19 | Clothes recognition methods and device based on picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063758A true CN109063758A (en) | 2018-12-21 |
Family
ID=64817772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810802043.XA Pending CN109063758A (en) | 2018-07-19 | 2018-07-19 | Clothes recognition methods and device based on picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063758A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657680A (en) * | 2018-12-27 | 2019-04-19 | 深圳码隆科技有限公司 | Image of clothing image pickup method, device and computer equipment |
| CN112950245A (en) * | 2019-12-10 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and medium for analyzing clothes trend |
| CN114863405A (en) * | 2022-04-06 | 2022-08-05 | 北京爱奇艺科技有限公司 | Clothing identification method, device, terminal and storage medium |
-
2018
- 2018-07-19 CN CN201810802043.XA patent/CN109063758A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109657680A (en) * | 2018-12-27 | 2019-04-19 | 深圳码隆科技有限公司 | Image of clothing image pickup method, device and computer equipment |
| CN112950245A (en) * | 2019-12-10 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and medium for analyzing clothes trend |
| CN114863405A (en) * | 2022-04-06 | 2022-08-05 | 北京爱奇艺科技有限公司 | Clothing identification method, device, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10963744B2 (en) | Cognitive automated and interactive personalized fashion designing using cognitive fashion scores and cognitive analysis of fashion trends and data | |
| CN105117463B (en) | Information processing method and information processing unit | |
| CN109829108B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| US20170262959A1 (en) | Browsing interface for item counterparts having different scales and lengths | |
| CN109034973B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation system and computer-readable storage medium | |
| US9183510B1 (en) | Method and system for personalized recommendation of lifestyle items | |
| KR20210098884A (en) | A method of providing a fashion item recommendation service using a body shape and purchase history | |
| CN109063755A (en) | Clothes recognition methods and device | |
| US10769524B1 (en) | Non-binary gender filter | |
| CN106055710A (en) | Video-based commodity recommendation method and device | |
| CN107632984A (en) | A kind of cluster data table shows methods, devices and systems | |
| Laenen et al. | Web search of fashion items with multimodal querying | |
| WO2018035164A1 (en) | Description information generation and presentation systems, methods, and devices | |
| CN109063758A (en) | Clothes recognition methods and device based on picture | |
| CN110427548B (en) | Information pushing method, information pushing device and computer readable storage medium | |
| Xia et al. | A method to create body sizing systems | |
| KR102295459B1 (en) | A method of providing a fashion item recommendation service to a user using a date | |
| CN110097400A (en) | Information recommendation method, apparatus and system, storage medium, intelligent interaction device | |
| CN109961329A (en) | Articles handling method and device, storage medium and electronic equipment | |
| KR20140037384A (en) | Apparatus and method for prediction of merchandise demand using social network service data | |
| US11972466B2 (en) | Computer storage media, method, and system for exploring and recommending matching products across categories | |
| Stan et al. | An intelligent personalized fashion recommendation system | |
| US20150365390A1 (en) | Method of creating preference image identification code, method of diagnosing preference image identification code, and method of providing information using preference image identification code | |
| CN110968670B (en) | Method, device, equipment and storage medium for acquiring attributes of popular commodities | |
| CN109034255A (en) | The prediction technique and device of clothes sales volume |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181221 |