CN107292685A - A kind of method of automatic recommendation size and the fitting cabinet system using this method - Google Patents
A kind of method of automatic recommendation size and the fitting cabinet system using this method Download PDFInfo
- Publication number
- CN107292685A CN107292685A CN201610192990.2A CN201610192990A CN107292685A CN 107292685 A CN107292685 A CN 107292685A CN 201610192990 A CN201610192990 A CN 201610192990A CN 107292685 A CN107292685 A CN 107292685A
- Authority
- CN
- China
- Prior art keywords
- data
- measured
- client
- model
- size
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of method of automatic recommendation size and using the fitting cabinet system of this method, method includes：S1, human body 3D data scannings are carried out using 3D sensors, 3D data are spliced and set up the 3D data model to be measured of human body；S2, using marked measurement position 3D Data Reference Models to 3D data model to be measured carry out non-rigid registration, and then calculate obtain the 3D data model to be measured position to be measured sized data；S3, the sized data obtained in step S3 is input in the neural network model established based on sample data, and then obtains clothing size；S4, the clothing size obtained according to step S3 control corresponding wardrobe door to open so that client tries clothing on.The present invention can assist client to complete to try process on to clothes, realize automation and accurately measure and improve automation marketing system, greatly reduce human cost.
Description
Technical field
The present invention relates to clothes service field, more particularly to a kind of method of automatic recommendation size and use should
The fitting cabinet system of method.
Background technology
Present people's living standard more and more higher, the requirement to clothes is not only attractive in appearance but also comfortable and fit.
The either net purchase of current trend or clothes customization is required for comparing accurately sizing information.So needs pair
Human body is measured, using obtain most suitable personal clothing size as clothing customization size data is provided.Simultaneously
Dress designing needs substantial amounts of somatic data model as foundation.
Traditional data acquisition mode is that human body is measured with tape measure by tailor.But measuring size can be because each
The various customs of tailor are different with method to produce different results, and accurate data degree has uncertain factor.
Simultaneously because human cost also significantly rises.Therefore the sector automation is accurately measured and perfect automatic
Changing marketing system turns into the urgent demand of manufacturer.
The content of the invention
The technical problem to be solved in the present invention is that the drawbacks described above for prior art is automatic there is provided one kind
Recommend the method and the fitting cabinet system using this method of size.
The technical solution adopted for the present invention to solve the technical problems is：Construct a kind of side of automatic recommendation size
Method, including：
S1, human body 3D data scannings are carried out using 3D sensors, 3D data are spliced and set up the 3D of human body
Data model to be measured；
S2, using marked measurement position 3D Data Reference Models to 3D data model to be measured carry out it is non-
Rigid Registration, and then calculate the sized data for the position to be measured for obtaining the 3D data model to be measured；
S3, the sized data obtained in step S3 is input to the neutral net established based on sample data
In model, and then obtain clothing size；
S4, the clothing size obtained according to step S3 control corresponding wardrobe door to open so that client tries clothing on
Thing.
In the method for automatic recommendation size of the present invention, the step S2 includes：
S21, determine a typical body model, and marked after measurement position and to join as the 3D data
Examine model；
S22, by the 3D Data Reference Models non-rigid registration to the 3D data model to be measured, after registration
3D data model to be measured on obtain mark position；
S23, the mark position of acquisition correspondence is labeled on 3D data model to be measured；
S24, the sized data for calculating position to be measured.
In the method for automatic recommendation size of the present invention, the data inputted in the step S3 are also wrapped
Also include before including height and weight data, the step S3：The body of human body is obtained by instrument for measuring height
High and weight data.
In the method for automatic recommendation size of the present invention, the neural network model is 3 layers of nerve net
Network, including input layer, hidden layer and output layer, sized data and the height and weight data are as defeated
Enter layer, output layer uses softmax graders, what it was exported be the probability of different clothing sizes and each
The probability sum of clothing size is 1.
In the method for automatic recommendation size of the present invention, also include after the step S4：
S5, the clothing size adjust instruction of reception user's input are adjusted to obtained clothing size, and profit
The clothing size obtained with final adjustment is modified to the neural network model.
In the method for automatic recommendation size of the present invention, include after the step S4：
S6, the 3D data model to be measured and clothing size for recording client, and by itself and time point one at that time
Rise to deliver in Cloud Server and preserve.
In the method for automatic recommendation size of the present invention, following step is also included before the step S1
Suddenly：
S01, the authentication information for obtaining client's input, if the authentication information is not present, obtain the note of client
Volume information and the log-on message that the client is preserved in Cloud Server, enter back into step S04；If the certification is believed
Breath has been present, then is directly entered step S02；
S02, by Cloud Server inquire about whether the client performed 3D data scannings and tried clothing on, if
Step S03 is then performed, step S04 is otherwise performed；
S03, Cloud Server return to the time point that client last time is tried on, if what last time was tried on
Time point points out client without logging data within effective time, then, jumps to step S01；If last
The time point once tried on not within effective time, then into step S04；
S04, transmission short message verification code are to client, and client triggers starting step by inputting the short message verification code
S1。
In the method for automatic recommendation size of the present invention, the authentication information is cell-phone number or two dimension
Code.
The invention also discloses one kind fitting cabinet system, including the cabinet with multiple wardrobe doors, 3D sensing
Device and control module, the control module are used to control the 3D sensors and cabinet according to described method
Work.
In fitting cabinet system of the present invention, the cloud that system also includes being connected with each fitting cabinet system takes
Business device, the relevant information for managing, collecting and distributing each fitting cabinet system.
Implement the present invention automatic recommendation size method and using this method fitting cabinet system, with
Lower beneficial effect：The present invention measures indirect survey by 3D Data Reference Models to 3D data model to be measured
The sized data of human body position to be measured is calculated, these data, which are put into neural network model, to be calculated
Fit clothing size, the cabinet door equipped with corresponding size clothing is opened according to corresponding size, assists client to complete
Process is tried on to clothes, automation is realized and accurately measures and improve automation marketing system, drop significantly
Low human cost；
Further, the clothing size obtained during trying on using final adjustment is to the neural network model
It is modified, improves data model；Client-related information can also be collected, carrying out data by cloud service is total to
Enjoy；The operation of playing property of portions of client is also prevented from, using short message verification code plus the side of effective time has been scanned
Formula is verified, only just can be scanned and try on operation by the client of checking.
Brief description of the drawings
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing：
Fig. 1 is the flow chart of the method for the automatic recommendation size of the present invention；
Fig. 2 is the process schematic of the exemplary steps S2 by taking bust, waistline as an example；
Fig. 3 is the schematic diagram of the neural network model in step S3.
Embodiment
In order to which technical characteristic, purpose and effect to the present invention are more clearly understood from, accompanying drawing is now compareed detailed
Describe bright embodiment of the invention in detail.
As shown in figure 1, being the flow chart of the method for the automatic recommendation size of the present invention；
The method of the present invention is mainly included the following steps that：
S1, human body 3D data scannings are carried out using 3D sensors, 3D data are spliced and set up the 3D of human body
Data model to be measured；
S2, using marked measurement position 3D Data Reference Models to 3D data model to be measured carry out it is non-
Rigid Registration, and then calculate the sized data for the position to be measured for obtaining the 3D data model to be measured；
S3, the sized data obtained in step S3 is input to the neutral net established based on sample data
In model, and then obtain clothing size；
S4, the clothing size obtained according to step S3 control corresponding wardrobe door to open so that client tries clothing on
Thing.
With reference to Fig. 2, wherein, the step S2 includes：
S21, determine a typical body model, and marked after measurement position and to join as the 3D data
Examine model；
Wherein, typical body model can, with the average human model in training set, be gone out with red line mark
Position to be measured.It is that top right plot in 3D Data Reference Models, Fig. 2 is represented such as the picture left above in Fig. 2
Be 3D data model to be measured.
S22, by the 3D Data Reference Models non-rigid registration to the 3D data model to be measured, after registration
3D data model to be measured on obtain mark position, as shown in the lower-left figure in Fig. 2.
Wherein, method for registering includes non-rigid ICP, SIFT Flow etc..
S23, the mark position of acquisition correspondence is labeled on 3D data model to be measured, the bottom right in such as Fig. 2
Shown in figure.
S24, the sized data for calculating position to be measured.
It is to illustrate by taking bust, waistline as an example, other human body positions to be measured can similarly be obtained in Fig. 2.
Wherein, the data inputted in the step S3 also include height and weight data, the step S3
Also include before：The height and weight data of human body are obtained by instrument for measuring height.
With reference to Fig. 3, neural network model involved in step S3 is described below.
Above-mentioned neutral net can classify after the training of substantial amounts of data to new input,
The size of up/down dress is obtained according to information such as height, body weight.Due to man, woman, upper dress, lower dress
It is corresponding to input and export otherwise varied, therefore the present invention needs four neural network models of framework：On man
Dress, dress under man, on woman fill neural network model under dress, woman.
It is specific to implement as follows exemplified by being filled on man on the training of neural network model：
1) neural network model, is built, as shown in Figure 3.
Wherein L1 is first layer, i.e. input layer, and comprising these input information of x1...xn, n represents step
The quantity of the position to be measured obtained in S2, n=7 in the present invention, represent height, collar, shoulder breadth, bust,
Waistline, upper height, the length information of brachium ,+1 is node offset；L2 is hidden layer, t=5；Finally
L3 is output layer, is a softmax grader, output be different clothing sizes probability, its
With for 1, K=10 here (this is determined by the scope of size).
2) mass data collection (data for pass of pretending on man) is collected, is mainly included：Height, collar, shoulder
Width, bust, waistline, upper height, brachium and jacket size.Data are designated as { (x(1),y(1)),...,(x(M),y(M)),
Wherein input feature vector x(m)∈Rn+1(we agree as follows to symbol：Characteristic vector x dimension is n,
Wherein x0=1 correspondence intercept, m ∈ { 1,2 ..., M })；y(m)∈ { 1,2 ..., K }, as tag along sort.
3) for y(i)=k, correspondence output P (y=k | x)=1, P (y ≠ k | x)=0.
4) selection of activation primitive:Neutral net mainly has at present：Sigmoid, tanh, bipolar S-shaped letter
Number etc., the present invention uses sigmoid functions:Softmax layers
5) Establishment of Neural Model uses BP algorithm.
Notation declarations：1. l=1,2,3 represents the number of plies of network.2. W, b is network parameter.③
z(l)=W(l-1)x+b(l-1)Represent l layers of input (note here l ≠ 1).④a(l)=f (z(l)) represent l layers
Activation value (wherein, the 3rd layer of f be hθ(x))。
The first step:Determine loss function (represent the 3rd layer of jth unit weighted input and, including bias unit).
Second step:Initialize W, b
3rd step：L is calculated according to feedforward neural network2,L3Activation value.
4th step：BP algorithm asks W, b
To output layer (the 3rd layer)
(2)
For l=2,1 each layer is calculated as：δ(l)=((W(l))Tδ(l+1))·f'(z(l)) (3)
Calculate the local derviation numerical value finally needed：
Then W, b are updated
6) neural network model is trained
Initial training：Data set is divided into train_sample and test_sample collection, in 5)
Model is trained to train_sample, obtains whole network parameter W and b.Then, use
Test_sample carries out size classification and Detection, can be by adjusting neuron number if accuracy rate is not high
Obtain size to obtain satisfied W, b with increase train_sample.Whole training process can use N-fold
Cross validation (N-fold Cross-validation) determines the model and parameter of neutral net.
Certainly, fitting cabinet can also carry out user's training after introducing to the market, be specially：Fit each time, be
System can all require that user provides satisfied sizing information.Obtained new data set is added to by we
In train_sample, re -training model can obtain model parameter W, the b of renewal, so that finally
Obtain more accurately size classifying quality.Therefore, also include after the step S4：
S5, the clothing size adjust instruction of reception user's input are adjusted to obtained clothing size, and profit
The clothing size obtained with final adjustment is modified to the neural network model.
It is further preferred that data sharing is realized present invention also adds Cloud Server, in the step S4
Include afterwards：
S6, the 3D data model to be measured and clothing size for recording client, and by itself and time point one at that time
Rise to deliver in Cloud Server and preserve.
It is further comprising the steps of before the step S1：
S01, the authentication information for obtaining client's input, if the authentication information is not present, obtain the note of client
Volume information and the log-on message that the client is preserved in Cloud Server, enter back into step S04；If the certification is believed
Breath has been present, then is directly entered step S02；
Wherein, the authentication information is cell-phone number or Quick Response Code.Certain number also can store many simultaneously
Acquiescence presses one man operation in people's metrical information, the settable limitation below step of system.
S02, by Cloud Server inquire about whether the client performed 3D data scannings and tried clothing on, if
Step S03 is then performed, step S04 is otherwise performed；
S03, Cloud Server return to the time point that client last time is tried on, if what last time was tried on
Time point points out client without logging data within effective time, then, jumps to step S01；If last
The time point once tried on not within effective time, then into step S04；
S04, transmission short message verification code are to client, and client triggers starting step by inputting the short message verification code
S1。
Verified using short message verification code plus scanned by the way of effective time, only pass through client's ability of checking
It is scanned and tries on operation.
Accordingly, the invention also discloses one kind fitting cabinet system, including the cabinet with multiple wardrobe doors,
3D sensors and control module, the control module are used for described method and control the 3D sensors and cabinet
The work of body.Load trying on a dress or trousers for different clothing sizes in the sub- cabinet of each wardrobe door.Will not
The Data Enter control module of different sizes with cabinet correspondence.
In summary, the method for the automatic recommendation size of the present invention and the fitting cabinet system using this method are implemented
System, has the advantages that：The present invention is carried out by 3D Data Reference Models to 3D data model to be measured
Measurement indirect measuring goes out the sized data of human body position to be measured, and these data are put into neural network model
Fit clothing size can be calculated, the cabinet door equipped with corresponding size clothing, association are opened according to corresponding size
Help client to complete to try process on to clothes, realize automation and accurately measure and improve automation sale body
System, greatly reduces human cost；Further, the clothing obtained during trying on using final adjustment
Size is modified to the neural network model, improves data model；Client-related information can also be collected,
Data sharing is carried out by cloud service；The operation of playing property of portions of client is also prevented from, using short message verification code
Plus scanned the mode of effective time and verify, only it just can be scanned and try on behaviour by the client of checking
Make.
Embodiments of the invention are described above in conjunction with accompanying drawing, but the invention is not limited in above-mentioned
Embodiment, above-mentioned embodiment be only it is schematical, rather than restricted, this
The those of ordinary skill in field is not departing from present inventive concept and claim is protected under the enlightenment of the present invention
Under the ambit of shield, many forms can be also made, these are belonged within the protection of the present invention.
Claims (10)
1. a kind of method of automatic recommendation size, it is characterised in that including：
S1, human body 3D data scannings are carried out using 3D sensors, 3D data are spliced and set up the 3D of human body
Data model to be measured；
S2, using marked measurement position 3D Data Reference Models to 3D data model to be measured carry out it is non-
Rigid Registration, and then calculate the sized data for the position to be measured for obtaining the 3D data model to be measured；
S3, the sized data obtained in step S3 is input to the neutral net established based on sample data
In model, and then obtain clothing size；
S4, the clothing size obtained according to step S3 control corresponding wardrobe door to open so that client tries clothing on
Thing.
2. the method for automatic recommendation size according to claim 1, it is characterised in that the step
S2 includes：
S21, determine a typical body model, and marked after measurement position and to join as the 3D data
Examine model；
S22, by the 3D Data Reference Models non-rigid registration to the 3D data model to be measured, after registration
3D data model to be measured on obtain mark position；
S23, the mark position of acquisition correspondence is labeled on 3D data model to be measured；
S24, the sized data for calculating position to be measured.
3. the method for automatic recommendation size according to claim 1, it is characterised in that the step
The data inputted in S3 also include also including before height and weight data, the step S3：Pass through height
Measuring instrument obtains the height and weight data of human body.
4. the method for automatic recommendation size according to claim 3, it is characterised in that the nerve
Network model is 3 layers of neutral net, including input layer, hidden layer and output layer, sized data and described
Height and weight data are as input layer, and output layer uses softmax graders, and what it was exported is different
The probability sum of the probability of clothing size and each clothing size is 1.
5. the method for automatic recommendation size according to claim 1, it is characterised in that the step
Also include after S4：
S5, the clothing size adjust instruction of reception user's input are adjusted to obtained clothing size, and profit
The clothing size obtained with final adjustment is modified to the neural network model.
6. the method for automatic recommendation size according to claim 1, it is characterised in that the step
Include after S4：
S6, the 3D data model to be measured and clothing size for recording client, and by itself and time point one at that time
Rise to deliver in Cloud Server and preserve.
7. the method for automatic recommendation size according to claim 6, it is characterised in that the step
It is further comprising the steps of before S1：
S01, the authentication information for obtaining client's input, if the authentication information is not present, obtain the note of client
Volume information and the log-on message that the client is preserved in Cloud Server, enter back into step S04；If the certification is believed
Breath has been present, then is directly entered step S02；
S02, by Cloud Server inquire about whether the client performed 3D data scannings and tried clothing on, if
Step S03 is then performed, step S04 is otherwise performed；
S03, Cloud Server return to the time point that client last time is tried on, if what last time was tried on
Time point points out client without logging data within effective time, then, jumps to step S01；If last
The time point once tried on not within effective time, then into step S04；
S04, transmission short message verification code are to client, and client triggers starting step by inputting the short message verification code
S1。
8. the method for automatic recommendation size according to claim 7, it is characterised in that the certification
Information is cell-phone number or Quick Response Code.
9. one kind fitting cabinet system, it is characterised in that sensed including the cabinet with multiple wardrobe doors, 3D
Device and control module, the method that the control module is used for according to any one of 1-8 control the 3D to pass
The work of sensor and cabinet.
10. fitting cabinet system according to claim 9, it is characterised in that system also includes and each
The Cloud Server that cabinet system of fitting is connected, the relevant information for managing, collecting and distributing each fitting cabinet system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610192990.2A CN107292685A (en) | 2016-03-30 | 2016-03-30 | A kind of method of automatic recommendation size and the fitting cabinet system using this method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610192990.2A CN107292685A (en) | 2016-03-30 | 2016-03-30 | A kind of method of automatic recommendation size and the fitting cabinet system using this method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107292685A true CN107292685A (en) | 2017-10-24 |
Family
ID=60086791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610192990.2A Pending CN107292685A (en) | 2016-03-30 | 2016-03-30 | A kind of method of automatic recommendation size and the fitting cabinet system using this method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107292685A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985657A (en) * | 2018-08-06 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Evaluation method, device and the server of personage's clothing collocation |
| CN110021061A (en) * | 2018-01-08 | 2019-07-16 | 广东欧珀移动通信有限公司 | Collocation model building method, dress ornament recommended method, device, medium and terminal |
| CN111175973A (en) * | 2019-12-31 | 2020-05-19 | Oppo广东移动通信有限公司 | Head band adjusting method and adjusting device, computer storage medium and head-mounted equipment |
| CN113418170A (en) * | 2021-06-23 | 2021-09-21 | 徐桂云 | Electric energy storage street lamp equipment for wind power generation |
| CN113742323A (en) * | 2021-07-22 | 2021-12-03 | 定智衣(上海)服装科技有限公司 | Scheme for efficiently correcting individual characteristic dimension of human body |
| CN114851565A (en) * | 2022-04-12 | 2022-08-05 | 深圳市广德教育科技股份有限公司 | Method for manufacturing fitting model by using 3D printing technology |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070225859A1 (en) * | 2004-05-13 | 2007-09-27 | Koninklijke Philips Electronics, N.V. | Wardrobe Management System |
| CN104080401A (en) * | 2011-11-17 | 2014-10-01 | 泰克梅德3D公司 | Method and system for forming a virtual model of a human subject |
| CN104463622A (en) * | 2014-11-28 | 2015-03-25 | 常州市武进区半导体照明应用技术研究院 | Fitting system and application method thereof |
-
2016
- 2016-03-30 CN CN201610192990.2A patent/CN107292685A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070225859A1 (en) * | 2004-05-13 | 2007-09-27 | Koninklijke Philips Electronics, N.V. | Wardrobe Management System |
| CN104080401A (en) * | 2011-11-17 | 2014-10-01 | 泰克梅德3D公司 | Method and system for forming a virtual model of a human subject |
| CN104463622A (en) * | 2014-11-28 | 2015-03-25 | 常州市武进区半导体照明应用技术研究院 | Fitting system and application method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 李越: "《中国优秀硕士学位论文全文数据库》", 《中国优秀硕士学位论文全文数据库》 * |
| 郑爱花: "基于BP神经网络的服装号型推荐方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021061A (en) * | 2018-01-08 | 2019-07-16 | 广东欧珀移动通信有限公司 | Collocation model building method, dress ornament recommended method, device, medium and terminal |
| CN108985657A (en) * | 2018-08-06 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Evaluation method, device and the server of personage's clothing collocation |
| CN111175973A (en) * | 2019-12-31 | 2020-05-19 | Oppo广东移动通信有限公司 | Head band adjusting method and adjusting device, computer storage medium and head-mounted equipment |
| CN113418170A (en) * | 2021-06-23 | 2021-09-21 | 徐桂云 | Electric energy storage street lamp equipment for wind power generation |
| CN113742323A (en) * | 2021-07-22 | 2021-12-03 | 定智衣(上海)服装科技有限公司 | Scheme for efficiently correcting individual characteristic dimension of human body |
| CN113742323B (en) * | 2021-07-22 | 2023-11-17 | 定智衣(上海)服装科技有限公司 | Method for correcting individual characteristic size of human body |
| CN114851565A (en) * | 2022-04-12 | 2022-08-05 | 深圳市广德教育科技股份有限公司 | Method for manufacturing fitting model by using 3D printing technology |
| CN114851565B (en) * | 2022-04-12 | 2024-03-29 | 深圳市广德教育科技股份有限公司 | Method for manufacturing fitting model by using 3D printing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107292685A (en) | A kind of method of automatic recommendation size and the fitting cabinet system using this method | |
| Gill | A review of research and innovation in garment sizing, prototyping and fitting | |
| CN104978762B (en) | Clothes threedimensional model generation method and system | |
| CN103886026B (en) | Clothing matching method based on personal feature | |
| CN106897568A (en) | The treating method and apparatus of case history structuring | |
| CN102939614A (en) | Method for remotely determining clothes dimensions | |
| CN107180375A (en) | A kind of garment size commending system based on multilayer neural network | |
| CN109558902A (en) | A kind of fast target detection method | |
| CN108229268A (en) | Expression Recognition and convolutional neural networks model training method, device and electronic equipment | |
| CN103472197B (en) | Cross-perception information interaction sensing fusion method in intelligent bionic evaluation for food | |
| CN108334849A (en) | A kind of recognition methods again of the pedestrian based on Riemann manifold | |
| CN110472611A (en) | Method, apparatus, electronic equipment and the readable storage medium storing program for executing of character attribute identification | |
| CN107330750A (en) | A kind of recommended products figure method and device, electronic equipment | |
| CN105303418A (en) | Site selection method and device | |
| CN110321774B (en) | Crop disaster situation evaluation method, device, equipment and computer readable storage medium | |
| CN110222925A (en) | Performance quantization wire examination method, device and computer readable storage medium | |
| CN107808116A (en) | A kind of wheat spider detection method based on the fusion study of depth multilayer feature | |
| CN106228133A (en) | User authentication method and device | |
| CN110491490A (en) | A kind of doctor's appraisal procedure and device | |
| KR102026625B1 (en) | Personalized clothing recommendation method for clothing store | |
| CN109859101A (en) | The recognition methods of corps canopy thermal infrared images and system | |
| CN110415133A (en) | A kind of wisdom agricultural doctor management system and method | |
| CN109871869A (en) | A kind of Lung neoplasm classification method and its device | |
| WO2008072923A1 (en) | Goods mediating system and method based on coordinating | |
| CN110209860A (en) | A kind of interpretable garment coordination method and device based on clothes attribute of template-directed |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |