CN104921410B - A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model - Google Patents
A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model Download PDFInfo
- Publication number
- CN104921410B CN104921410B CN201510405858.0A CN201510405858A CN104921410B CN 104921410 B CN104921410 B CN 104921410B CN 201510405858 A CN201510405858 A CN 201510405858A CN 104921410 B CN104921410 B CN 104921410B
- Authority
- CN
- China
- Prior art keywords
- foot
- shoe tree
- parameter
- model
- difference
- 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.)
- Active
Links
Abstract
The present invention relates to a kind of shoe tree parameter automatic prediction method based on dual model, it is characterised in that comprise the following steps:(S1) training of foot and last carving disaggregated model, foot and last carving difference model;(S2) dual model automatic Prediction shoe tree parameter is utilized.In addition, the invention further relates to a kind of shoe tree parameter automatic Prediction device based on dual model, including data acquisition module, for gathering foot parameter;Dual model training module, for training foot with shoe tree disaggregated model and foot and shoe tree difference model;Memory module, for preserving foot data, basic shoe tree parameter, foot and shoe tree disaggregated model, foot and shoe tree difference model;Automatic Prediction module, for automatic Prediction shoe tree parameter.For the strong problem of current shoe last designing inefficiency, subjectivity, the general character of client's wear shoes is excavated, the shoe tree parameter automatic prediction method and device based on dual model is designed, according to the foot parameter automatic Prediction of client and suitable shoe tree parameter can be designed.
Description
Technical field
The present invention relates to a kind of parameter automatic prediction method and prediction meanss, more particularly to a kind of shoe tree based on dual model
Parameter automatic prediction method and prediction meanss.
Background technology
With the progress of society, expanding economy, the raising of living standards of the people, style, comfort level of the people to shoes
And the requirement of shoe-making process is also being gradually stepped up, on market, common shoes are one-size-fits-all mostly, rule of thumb design, for most
For number consumer, there is the risk that does not fit, and customize the shoes that a pair of fits, not only time-consuming, cost is also prohibitively expensive, general
Logical consumer cannot often undertake.
Wherein, shoe tree is the benchmark for making shoes, and comfort level, style with shoes etc. have direct relation, and restriction disappears
The person of expense customizes the key node of suitable shoes.At present, shoe tree parameter is typically basic by experienced technology master worker correction foot type
Gain of parameter, and foot type data are made up of some the basic feature parameters for manually obtaining, correction of the shoe tree at these characteristic points,
Transition is determined that not only there is very strong subjectivity mostly by the experience of designer, and efficiency is low, holds at high price, therefore, tradition
Shoe last model method for designing be difficult to meet the requirement of quick design high-quality shoe tree, constrain the comfortable, shoes of high-quality low-cost
Design and making.
Content of the invention
In order to solve the deficiencies in the prior art, it is an object of the invention to provide one kind being capable of fast and accurately shoe tree parameter
Automatic prediction method and prediction meanss.
To achieve these goals, the invention provides a kind of shoe tree parameter automatic prediction method based on dual model, bag
Include following steps:
The training of step one, foot and last carving disaggregated model, foot and last carving difference model;
Step 2, using dual model automatic Prediction shoe tree parameter.
Preferably, step one further includes following steps:
Step S101, measures tester's foot parameter;
Step S102, allows tester to try the footwear that basic shoe tree makes on, mates most suitable footwear code;
Step S103, using different footwear codes as different classifications, foot parameter is classified using SVM training as feature
Device, obtains foot and last carving disaggregated model;
Step S104, is read in basic shoe tree parameter, is corresponded with foot parameter, do difference;
Step S105, counts the difference expectation of identical footwear code, obtains foot and last carving difference model.
Preferably, step 2 further includes following steps:
Step S201, measures the foot parameter of consumer;
Step S202, predicts shoe tree yardage using foot with last carving disaggregated model;
Step S203, in foot with last carving difference model, obtains the difference of the corresponding foot of shoe tree yardage and last carving;
Step S204, foot parameter obtain the parameter of final last carving plus corresponding difference.
Present invention also offers a kind of shoe tree parameter automatic Prediction device based on dual model, including data acquisition module,
For gathering foot parameter;Dual model training module, for training foot with shoe tree disaggregated model and foot and shoe tree difference model;Deposit
Storage module, for preserving foot data, basic shoe tree parameter, foot and shoe tree disaggregated model, foot and shoe tree difference model;Automatically pre-
Module is surveyed, for automatic Prediction shoe tree parameter.
For the strong problem of current shoe last designing inefficiency, subjectivity, the general character of client's wear shoes is excavated, is designed and is based on
The shoe tree parameter automatic prediction method of dual model and device, according to the foot parameter automatic Prediction of client and can design conjunction
Suitable shoe tree parameter.
Description of the drawings
Fig. 1 is the flow chart of first preferred embodiment of the invention;
Fig. 2 is the flow chart of second preferred embodiment of the invention;
Fig. 3 is the structural representation of prediction meanss provided by the present invention.
Specific embodiment
As shown in figure 1, the invention provides a kind of shoe tree parameter automatic prediction method based on dual model, walks including following
Suddenly:
The training of step one, foot and last carving disaggregated model, foot and last carving difference model;
Step 2, using dual model automatic Prediction shoe tree parameter.
Advantageously, the step one further includes following steps:
S101, measures tester's foot parameter;
S102, allows tester to try the footwear that basic shoe tree makes on, mates most suitable footwear code;
S103, using different footwear codes as different classifications, foot parameter is trained grader using SVM, is obtained as feature
To foot and last carving disaggregated model;
S104, is read in basic shoe tree parameter, is corresponded with foot parameter, do difference;
S105, counts the difference expectation of identical footwear code, obtains foot and last carving difference model.
As shown in Fig. 2 the step one can further include following steps:
S111, measures tester's foot parameter;
S112, allows tester to try the footwear that basic shoe tree makes on, mates most suitable footwear code;
S113, is read in basic shoe tree parameter, is corresponded with foot parameter, do difference
S114, counts the difference expectation of identical footwear code, obtains foot and last carving difference model;
S115, using different footwear codes as different classifications, foot parameter is trained grader using SVM, is obtained as feature
To foot and last carving disaggregated model.
In above-mentioned S101 steps, during measurement tester's foot parameter, foot length, rear height followed by back gauge, foot plantar is specifically included
Enclose G2, foot plantar enclose G3, foot pocket with enclosing that G4, foot are wide, the palm is wide, inner wide, the little toe evagination dot profile of thumb evagination dot profile 5 outer wide, the
Outer wide, the heel heart profile overall with of the outer wide, waist curve of wide in one plantar toe profile, the 5th plantar toe profile, thumb heights, foot type G2 be high,
Foot type G3 is high, foot type G4 is high, foot projection floor space, G2 areas, G3 areas, G4 areas, the front middle section areas of G4, foot front body
Long-pending, whole foot volume.
In above-mentioned S102 steps, that is, allow tester to try the footwear that basic shoe tree makes on, mate 0 yard of most suitable footwear, here
Need to allow multiple testers to try the footwear that basic shoe tree makes on, but when matching most suitable footwear code, record, and with this
The foot parameter of tester is associated, and obtains disaggregated model.
In above-mentioned S103 and S115 steps, when foot is obtained with shoe tree disaggregated model, need to train grader using SVM.
SVM English full name be support vector machine, Chinese entitled support vector machine, popular for, it is a kind of two class
Disaggregated model, its basic model be defined as on feature space between 5 every maximum linear classifier, its learning strategy is interval
Maximize, can finally be converted into the solution of a convex quadratic programming problem.
In above-mentioned S105 and S114 steps, when obtaining foot with last carving difference model, need the formula for utilizing as follows:
Wherein i represents different footwear codes, and Ni is the corresponding learning sample numbers of footwear code i, and C is foot parameter and shoe tree parameter difference.
Two models, i.e. disaggregated model and difference model can be obtained by step one.
Step 2 may further include following steps:
S201, measures the foot parameter of consumer;
S202, predicts shoe tree yardage using foot with last carving disaggregated model;
S203, in foot with last carving difference model, obtains the difference of the corresponding foot of shoe tree yardage and last carving;
S204, foot parameter obtain the parameter of final last carving plus corresponding difference.
In above-mentioned steps S201, first measurement will customize the foot parameter of certain concrete consumer of footwear, specifically include foot
Long, rear height followed by back gauge, foot plantar enclose G2, foot plantar enclose G3, foot pocket with enclosing that G4, foot width, the palm be wide, wide in thumb evagination dot profile,
In outer wide, the first plantar toe profile of little toe evagination dot profile, outer wide, the heel heart profile of the outer wide, waist curve of wide, the 5th plantar toe profile is complete
Before width, thumb heights, foot type G2 height, foot type G3 height, foot type G4 height, foot projection floor space, G2 areas, G3 areas, G4 areas, G4
Middle section area, foot front volume, whole foot volume.
The foot parameter of consumer is applied to foot and shoe tree yardage is predicted with shoe tree disaggregated model, if the shoe tree of prediction
Yardage is excessive with usual yardage gap, then artificial correction.
Using foot and footwear difference model, the difference of the corresponding foot of consumer's shoe tree yardage and shoe tree is obtained.
Again by consumer foot parameter plus after corresponding difference must final shoe tree parameter.For example, by consumer's foot
After long numerical value is plus the difference corresponding with foot appearance obtained from difference model, it is possible to draw the length value of shoe tree.
Advantageously, in step 2, by the parameter read-in data base of the final shoe tree for obtaining, for carrying out increment to model
Study.
As shown in figure 3, present invention also offers a kind of shoe tree parameter automatic Prediction device based on dual model, including number
According to acquisition module, for gathering foot parameter;Dual model training module, for training foot with shoe tree disaggregated model and foot and shoe tree
Difference model;Memory module, for preserving foot data, basic shoe tree parameter, foot and shoe tree disaggregated model, foot and shoe tree difference
Model;Automatic Prediction module, for automatic Prediction shoe tree parameter.
Data acquisition module, for gathering foot parameter, concrete collection includes that foot length, rear height followed by back gauge, foot plantar are enclosed
G2, foot plantar enclose G3, foot pocket with enclosing that G4, foot are wide, the palm is wide, outer wide, the first plantar of wide in thumb evagination dot profile, little toe evagination dot profile
Outer wide, the heel heart profile overall with of the outer wide, waist curve of wide in toe profile, the 5th plantar toe profile, thumb heights, foot type G2 are high, foot type
G3 is high, foot type G4 is high, foot projection floor space, G2 areas, G3 areas, G4 areas, the front middle section areas of G4, foot front volume, whole
Foot volume is in interior parameter information.
Preferably, the dual model training module includes foot with shoe tree disaggregated model training unit and foot and shoe tree difference mould
Type training unit.Wherein, foot trains grader with shoe tree disaggregated model training unit using SVM.The training of shoe tree difference model is single
Using equation below during unit's work:
Wherein i represents different footwear codes, and Ni is the corresponding learning sample numbers of footwear code i, and C is foot parameter and shoe tree parameter difference.
Advantageously, the automatic Prediction module includes shoe tree yardage predicting unit, should for the foot parameter by consumer
Shoe tree yardage is predicted for foot with shoe tree disaggregated model, if the shoe tree yardage of prediction is excessive with usual yardage gap,
Artificial correction.
Preferably, the automatic Prediction module includes foot and shoe tree difference acquiring unit, for obtaining consumer's shoe tree
The corresponding foot of yardage and the difference of shoe tree.
For the strong problem of current shoe last designing inefficiency, subjectivity, the general character of client's wear shoes is excavated, is designed and is based on
The shoe tree parameter automatic prediction method of dual model and device, according to the foot parameter automatic Prediction of client and can design properly
Shoe tree parameter.
The preferred specific embodiment of the present invention described in detail above.It should be appreciated that one of ordinary skill in the art
Just many modifications and variations can be made according to the design concept of the present invention without the need for creative work.Therefore, all the art
Middle technical staff design concept under this invention passes through logical analysis, reasoning, or a limited experiment on the basis of existing technology
Available technical scheme, all should be within the scope of the present invention and/or in the protection domain that is defined in the patent claims.
Claims (8)
1. a kind of shoe tree parameter automatic prediction method based on dual model, it is characterised in that comprise the following steps:
The training of step one, foot and last carving disaggregated model, foot and last carving difference model;
Step 2, using dual model automatic Prediction shoe tree parameter;
Wherein,
The step one further includes following steps,
(S101) tester's foot parameter is measured;
(S102) allow tester to try the footwear that basic shoe tree makes on, mate most suitable footwear code;
(S103) using different footwear codes as different classifications, foot parameter is trained grader using SVM, is obtained as feature
Foot and last carving disaggregated model;
(S104) basic shoe tree parameter is read in, is corresponded with foot parameter, is done difference;
(S105) the difference expectation of identical footwear code is counted, foot and last carving difference model is obtained;
Or,
The step one further includes following steps:
(S111) tester's foot parameter is measured;
(S112) allow tester to try the footwear that basic shoe tree makes on, mate most suitable footwear code;
(S113) basic shoe tree parameter is read in, is corresponded with foot parameter, is done difference;
(S114) the difference expectation of identical footwear code is counted, foot and last carving difference model is obtained;
(S115) using different footwear codes as different classifications, foot parameter is trained grader using SVM, is obtained as feature
Foot and last carving disaggregated model.
2. a kind of shoe tree parameter automatic prediction method based on dual model according to claim 1, it is characterised in that described
Step 2 further includes following steps:
(S201) the foot parameter of consumer is measured;
(S202) shoe tree yardage is predicted using foot with last carving disaggregated model;
(S203) difference of the corresponding foot of shoe tree yardage and last carving, in foot with last carving difference model, is obtained;
(S204) foot parameter obtains the parameter of final last carving plus corresponding difference.
3. a kind of shoe tree parameter automatic prediction method based on dual model according to claim 2, it is characterised in that described
Step 2 also comprises the steps:
(S205) if the shoe tree yardage of prediction is excessive with usual yardage gap, artificial correction.
4. a kind of shoe tree parameter automatic prediction method based on dual model according to claim 3, it is characterised in that described
Step 2 also comprises the steps:
(S206) by the parameter read-in data base of the final shoe tree for obtaining, for carrying out incremental learning to model.
5. a kind of shoe tree parameter automatic Prediction device based on dual model, it is characterised in that:Including data acquisition module, for adopting
Collection foot parameter;Dual model training module, for training foot with shoe tree disaggregated model and foot and shoe tree difference model;Storage mould
Block, for preserving foot data, basic shoe tree parameter, foot and shoe tree disaggregated model, foot and shoe tree difference model;Automatic Prediction mould
Block, for automatic Prediction shoe tree parameter.
6. a kind of shoe tree parameter automatic Prediction device based on dual model according to claim 5, it is characterised in that:Described
Dual model training module includes foot with shoe tree disaggregated model training unit and foot and shoe tree difference model training unit.
7. a kind of shoe tree parameter automatic Prediction device based on dual model according to claim 6, it is characterised in that:Described
Automatic Prediction module includes shoe tree yardage predicting unit.
8. a kind of shoe tree parameter automatic Prediction device based on dual model according to claim 7, it is characterised in that:Described
Automatic Prediction module includes foot and shoe tree difference acquiring unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510405858.0A CN104921410B (en) | 2015-07-10 | 2015-07-10 | A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510405858.0A CN104921410B (en) | 2015-07-10 | 2015-07-10 | A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104921410A CN104921410A (en) | 2015-09-23 |
CN104921410B true CN104921410B (en) | 2017-03-15 |
Family
ID=54109115
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510405858.0A Active CN104921410B (en) | 2015-07-10 | 2015-07-10 | A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104921410B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106937774B (en) * | 2017-03-30 | 2022-05-20 | 李文谦 | Shoe tree size prediction method and device based on deep learning |
CN108960262B (en) * | 2017-05-19 | 2024-02-09 | 意礴数字科技(深圳)有限公司 | Method, device and system for predicting shoe codes and computer readable storage medium |
CN107259711A (en) * | 2017-07-25 | 2017-10-20 | 余友和 | A kind of shoes match somebody with somebody code system |
CN107609933B (en) * | 2017-08-24 | 2020-06-23 | 深圳市云智数据服务有限公司 | Footage customization method and system based on store transaction records |
CN108765059B (en) * | 2018-04-28 | 2021-09-28 | 北京知足科技有限公司 | Shoe pushing method and device |
CN109086294A (en) * | 2018-06-13 | 2018-12-25 | 东莞时谛智能科技有限公司 | A kind of shoe tree database sharing and management method and system |
CN109064260B (en) * | 2018-07-11 | 2022-03-01 | 北京知足科技有限公司 | Shoe type data acquisition method and device |
CN109003167B (en) * | 2018-08-01 | 2020-12-29 | 深圳市云智数据服务有限公司 | Data processing method and device for shoe and boot customization |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4817222A (en) * | 1987-10-15 | 1989-04-04 | Shafir Aaron | Method and apparatus for making shoe lasts and/or shoe components |
CN101088728A (en) * | 2007-07-19 | 2007-12-19 | 清华大学 | Digitalized sneakers tree customizing production apparatus and process |
CN101658347B (en) * | 2009-09-24 | 2011-11-30 | 浙江大学 | Method for obtaining dynamic shape of foot model |
CN102214250B (en) * | 2010-04-12 | 2013-06-05 | 温州大学 | Method for generating statistics deformation model from shoe tree sample set |
CN102783767B (en) * | 2011-05-18 | 2014-12-17 | 香港纺织及成衣研发中心有限公司 | System for designing customized shoe tree and evaluating comfort thereof |
CN204838260U (en) * | 2015-07-10 | 2015-12-09 | 李文谦 | Automatic prediction unit of shoe tree parameter based on bimodulus type |
-
2015
- 2015-07-10 CN CN201510405858.0A patent/CN104921410B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104921410A (en) | 2015-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104921410B (en) | A kind of shoe tree parameter automatic prediction method and prediction meanss based on dual model | |
EP3649883B1 (en) | A method for manufacturing an outsole and a method for generating a visual ousole pattern | |
CN105243547A (en) | Footwear customization service platform and customization method thereof | |
CN109567812B (en) | Gait analysis system based on intelligent insole | |
Eerikäinen | Predicting the height–diameter pattern of planted Pinus kesiya stands in Zambia and Zimbabwe | |
JP7431354B2 (en) | System and method for controlling shoe parts manufacturing machine | |
RU2008126210A (en) | METHOD FOR DETECTING NERVOUS DEGENERATIVE DISEASE, DETECTION PROGRAM AND DETECTOR | |
CN102184539A (en) | Image-processing-technology-based plane footprint detection and analysis system and method thereof | |
CN110370647B (en) | 3D printing insole and manufacturing method thereof | |
CN106447453A (en) | Customization method of digital shoe product | |
CN204838260U (en) | Automatic prediction unit of shoe tree parameter based on bimodulus type | |
CN114041659B (en) | Shoe and boot customization method based on fitting standardization | |
CN107609933A (en) | A kind of foot-measuring method for customizing based on shops's conclusion of the business record, system | |
CN111354463B (en) | Human health measurement method, device, computer equipment and storage medium | |
CN108288304A (en) | The production method of insole and midsole, system and terminal device | |
CN109003167B (en) | Data processing method and device for shoe and boot customization | |
KR20180110842A (en) | Customized semi-permanent make-up recommendation system based on virtual experience and its service method | |
Andersson et al. | Users beware: Variable effects of parenthood on happiness within and across international datasets | |
Mäkinen et al. | Comparison of treewise and standwise forest simulators by means of quantile regression | |
CN105913424A (en) | Tooth-based age estimation method and device | |
CN103955715B (en) | Automatic person identification method based on barefoot or stockinged footprint image | |
CN109583277B (en) | Gender determination method of barefoot footprint based on CNN | |
CN106682624A (en) | Built-up area extraction method and apparatus based on time sequence remote sensing information | |
CN102063533A (en) | Method for designing shoe tree according to pelma image analysis data | |
CN109543747A (en) | A kind of data characteristics selection method and device based on stratified random forest |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |