CN103886117B - A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software - Google Patents
A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software Download PDFInfo
- Publication number
- CN103886117B CN103886117B CN201210559590.2A CN201210559590A CN103886117B CN 103886117 B CN103886117 B CN 103886117B CN 201210559590 A CN201210559590 A CN 201210559590A CN 103886117 B CN103886117 B CN 103886117B
- Authority
- CN
- China
- Prior art keywords
- angle
- parameter
- central point
- sides
- buttocks
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007935 neutral effect Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000013507 mapping Methods 0.000 claims abstract description 6
- 210000001624 hip Anatomy 0.000 claims description 46
- 210000001217 buttock Anatomy 0.000 claims description 43
- 210000000038 chest Anatomy 0.000 claims description 39
- 230000008859 change Effects 0.000 claims description 26
- 210000000481 breast Anatomy 0.000 claims description 22
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 230000036541 health Effects 0.000 claims description 14
- 210000001015 abdomen Anatomy 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 5
- 210000003127 knee Anatomy 0.000 claims description 5
- 210000003141 lower extremity Anatomy 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses and a kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software.Described method includes following four steps: 1, select 11 affects the bigger build modeling parameters output parameter as BP neutral net to body surface;2,36 physical characteristic parameters input parameter as BP neutral net is analyzed;3, under Matlab environment, build the initial model of BP network, by network training, obtain optimum network structure, set up physical characteristic parameter and shape adjustment nonlinearity in parameters mapping relations;4, the coded system of human parameters modeling interface document in analyzing three-dimensional fitting software, generates customization virtual human body based on client's build and body dimension.The present invention can not only meet the virtual fitting personalization for jacket fit assessment, the Human Modeling demand of customization, and can realize, from characteristics of human body's parameter efficiently producing to personalized human body, being widely used in custom made clothing platform.
Description
Technical field
The present invention relates to a kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software, belong to clothing industry digitized
Technical field.
Background technology
Along with society and economic development, people start to pursue personalized dress designing, it is desirable to be able to dress meets certainly
Own physical characteristic and aesthetic customized clothing.Because everyone build, figure are different with the colour of skin, aesthetic standards are also
Difference, so, in current customized clothing design and manufacturing process, needing is fitted by me could observe clothes and wear
Effect.In order to solve the trouble must brought by my fitting, there is relevant virtual three-dimensional fitting soft
Part is developed, and this three-dimensional virtual fitting is for ready-made clothes fitness information analysis and the important means of evaluation, and three-dimensional virtual fitting is imitated
The quality of fruit, the Design and Machining and the specification that directly influence clothing determine link.And wherein, according to build and the size of client
Set up the basis that individualized virtual anthropometric dummy is three-dimensional fitting.In existing three-dimensional fitting software, virtual human body personalization is joined
Number modeling is to be realized, then by the subjective judgement of the build to human body, to buman body type by girth size and length dimension
Being finely adjusted, the virtual human body so generated is relatively big with the difference of actual build, affects the final utilization effect of three-dimensional fitting.
Summary of the invention
It is an object of the invention to provide and a kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software, by people's body examination
Amount learns the research of the mapping relations of the physical characteristic parameter that buman body type characteristic parameter is applied to three-dimensional fitting software, to improve
The precision of virtual human body so that the virtual human body of generation conforms better to the requirement that in personalized customization, customization zoarium is evaluated,
And by the programmed method analysis of docking port file, to realize from characteristics of human body's parameter efficiently producing to personalized human body, from
And effectively solve the above-mentioned problems in the prior art.
For achieving the above object, the technical solution used in the present invention is as follows:
A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software, comprise the steps:
The first step, the impact of the Human Modeling parameters on human pattern of body form change confirmed in three-dimensional fitting software, select 11 to body
Table affects the bigger build modeling parameters output parameter as BP neutral net;Described 11 are bigger on body surface impact
Build modeling parameters is: shoulder parameter, chest locations parameter, breast peak distance parameter, abdomen parameter, health width parameter, buttocks
Width parameter, upper half height parameter, affect bodyside surface curve change pose parameter, affect waist to knee shaft angle change
Change lower part of the body pose parameter, bottom position parameter and affect upper half health shaft angle change upper body pose parameter;
The output parameter that second step, basis are selected, analyzes 36 physical characteristic parameters that output parameter may produce impact,
Input parameter as BP neutral net;36 described physical characteristic parameters are: front fillet, rear fillet, average shoulder angle,
Side neck point to the distance of breast point, the distance/front length of side neck point to breast point, BP dot spacing, BP dot spacing/chest measurement, abdomen coign,
Attacking Midfielder's central point is to the angle of chest both sides, the angle of side waist central point to chest both sides, Attacking Midfielder's central point to chest both sides
Angle/the angle of side waist central point to chest both sides, the vertical angle of Attacking Midfielder to breast, the angle of Attacking Midfielder's central point to buttocks both sides,
Side waist central point is to the angle of buttocks both sides, the folder of the angle/side waist central point to buttocks both sides of Attacking Midfielder's central point to buttocks both sides
Angle, the angle/angle of Attacking Midfielder's central point chest both sides of Attacking Midfielder's central point to buttocks both sides, side waist central point are to buttocks both sides
In the angle/angle of side waist central point to chest both sides, the vertical angle of low back to buttocks, back of the body length, the back of the body length/height, side knee
Heart point to the vertical angle of waist central point, the angle of side waist central point to buttocks central point, lower body shaft angle, upper half health shaft angle,
Hit exactly before upper body angle, low back to collare angle, highly, enclose under neck circumference, shoulder breadth, chest measurement, breast, waistline, lower hip circumference, upper buttocks
Enclose, outer lower limb length and interior length;
3rd step, under Matlab environment, build the initial model of BP network, by network training, analyze minimax method,
Normalized square mean method and without processing after data are standardized processing by three kinds of methods respectively the shadow to neural network forecast ability
Ring, analyze that the different network numbers of plies arranges the impact on neural network forecast ability, to analyze different training function setup pre-to network
The impact of survey ability, analyze different node transfer function and the impact on neural network forecast ability is set, analyzes different hidden layer joints
Count and arrange the impact on neural network forecast ability, analysis heterogeneous networks inputs and output parameter arranges the shadow to neural network forecast ability
Ring, obtain optimum network structure: the neutral net number of plies uses 4 layers, and the training function setup of network is { trainlm}, network
Node transfer function be set to logsig, purelin, logsig}, and set up physical characteristic parameter with in three-dimensional fitting software
Shape adjustment nonlinearity in parameters mapping relations;
In 4th step, analyzing three-dimensional fitting software, the coded system of the interface document of human parameters modeling, sets up third party software
Platform, built-in neural network structure, inputted, through neutral net by the physical characteristic data file that 3-D scanning is obtained
Parameters Transformation, automatically generate and be applied to anthropometric dummy interface document in three-dimensional fitting software, then the interface document of generation is led
Enter in three-dimensional fitting software, the three-dimensional virtual human body accordingly with customization physical characteristic can be generated.
Preferably, the 3rd step selects minimax method to process data.
Preferably, described three-dimensional fitting software has build input parameter, shape adjustment parameter and human parameters modeling
Interface document.
As further preferred scheme, described three-dimensional fitting software is the V-stitcher software of Gerber company of the U.S..
Compared with prior art, the present invention has following significance progress and a beneficial effect:
On the basis of the present invention is based on anthropometry, uses BP neutral net, set up three-dimensional virtual human body girth size, height
Degree size, length dimension, angle-data and build input nonlinearity in parameters mapping relations in three-dimensional fitting software, use people
Body characteristics Parameters Transformation has obtained can apply to the shape adjustment parameter of three-dimensional fitting software and has reached to improve virtual human body modeling essence
The method of degree.The virtual fitting personalization for jacket fit assessment, the Human Modeling demand of customization can not only be met,
And technical support can be provided for the customization of clothing industry, can realize from characteristics of human body's parameter to the height of personalized human body
Effect generates, and can be widely used in custom made clothing platform.
Detailed description of the invention
Below in conjunction with embodiment, the present invention is described in further details:
Three-dimensional fitting software described in the present embodiment is the V-stitcher software of Gerber company of the U.S., described Matlab
For Matlab7.1 version.
The a kind of of present invention offer improves the method for virtual human body modeling accuracy in three-dimensional fitting software, comprises the steps:
The first step, the impact of the Human Modeling parameters on human pattern of body form change confirmed in three-dimensional fitting software, select 11 to body
Table affects the bigger build modeling parameters output parameter as BP neutral net;Described 11 are bigger on body surface impact
Build modeling parameters is: shoulder parameter, chest locations parameter, breast peak distance parameter, abdomen parameter, health width parameter, buttocks
Width parameter, upper half height parameter, pose parameter, lower part of the body pose parameter, bottom position parameter and upper body pose parameter;
The output parameter that second step, basis are selected, analyzes 36 physical characteristic parameters that output parameter may produce impact,
Input parameter as BP neutral net;36 described physical characteristic parameters are preferably: front fillet, rear fillet, average
Fillet, the distance of side neck point to breast point, the distance/front length of side neck point to breast point, BP dot spacing, BP dot spacing/chest measurement, abdomen
Coign, Attacking Midfielder's central point are to the angle of chest both sides, the angle of side waist central point to chest both sides, Attacking Midfielder's central point to chest
The angle of the both sides/angle of side waist central point to chest both sides, the vertical angle of Attacking Midfielder to breast, Attacking Midfielder's central point are to buttocks both sides
Angle, the angle of side waist central point to buttocks both sides, Attacking Midfielder's central point to buttocks both sides angle/side waist central point to buttocks
The angle of both sides, Attacking Midfielder's central point are to the angle/angle of Attacking Midfielder's central point chest both sides of buttocks both sides, side waist central point to buttocks
The angle of both sides, the portion/angle of side waist central point to chest both sides, the vertical angle of low back to buttocks, the back of the body are long, the back of the body length/height, side
Face knee center point is to the vertical angle of waist central point, the angle of side waist central point to buttocks central point, lower body shaft angle, upper half
Hit exactly before health shaft angle, upper body angle, low back to collare angle, highly, enclose under neck circumference, shoulder breadth, chest measurement, breast, waistline, under
Hip circumference, upper hip circumference, outer lower limb length and interior length;
3rd step, under Matlab environment, build the initial model of BP network, by network training, analyze minimax method,
Normalized square mean method and without processing after data are standardized processing by three kinds of methods respectively the shadow to neural network forecast ability
Ring, analyze that the different network numbers of plies arranges the impact on neural network forecast ability, to analyze different training function setup pre-to network
The impact of survey ability, analyze different node transfer function and the impact on neural network forecast ability is set, analyzes different hidden layer joints
Count and arrange the impact on neural network forecast ability, analysis heterogeneous networks inputs and output parameter arranges the shadow to neural network forecast ability
Ring, obtain optimum network structure: the neutral net number of plies uses 4 layers, and the training function setup of network is { trainlm}, network
Node transfer function be set to logsig, purelin, logsig}, and set up physical characteristic parameter with in three-dimensional fitting software
Shape adjustment nonlinearity in parameters mapping relations;
The coded system of human parameters modeling interface document in 4th step, analyzing three-dimensional fitting software, obtained by the 3rd step
Conversion parameter and corresponding anthropometric data, generate customization virtual human body based on client's build and body dimension.
Data are processed by the preferably at most minimum method of the 3rd step.
Described three-dimensional fitting software has build input parameter, shape adjustment parameter and human parameters modeling interface document, preferably
V-stitcher software for Gerber company of the U.S..
Embodiment
Control the virtual human body single shape adjustment Parameters variation in three-dimensional fitting software, when observing this Parameters variation, visual human
The Changing Pattern of body build.Observe result display three-dimensional fitting software in shape adjustment parameter for virtual human body shoulder,
These 7 human bodies of chest, abdominal part, buttocks, human body side curve, breast waist, buttocks waist carry out build regulation.And
To on body surface affect bigger shape adjustment parameter have 11, these parameters are: shoulder parameter, chest locations parameter, breast peak away from
From parameter, abdomen parameter, health width parameter, buttocks width parameter, upper half height parameter, pose parameter, lower part of the body posture ginseng
Number, bottom position parameter and upper body pose parameter.The main impact of the pattern of body form change of virtual human body is by above-mentioned parameter: shoulder ginseng
Number affects the change at virtual human body shoulder slope angle of inclination, and chest locations parameter affects the change of virtual human body breastheight, breast peak distance
Parameter affects the change of virtual human body BP dot spacing, and abdomen parameter affects virtual human body abdomen and dashes forward the change of degree, health width parameter
Affecting the change of the radius vector ratio of chest, waist, buttocks, buttocks width parameter affects the change of the radius vector ratio of buttocks, above the waist
Long parameter affects the change at vertical direction of the cervical vertebra point position, and pose parameter affects the side curve change of health, lower part of the body posture
Affect the waist change to the shaft angle of knee, the change of half health shaft angle, upper body posture under the influence of Bottom Position parameter
Parameter affects the change of upper half health shaft angle.
With reference to " an apparel modeling theory piece " body surface angular surveying position, human body side, human body thickness measure position, GBT
16160-2008 " clothing somatometric position and method " and the impact of shape adjustment parameters on human pattern of body form change,
To 36 characteristics of human body's parameters: front fillet, rear fillet, average shoulder angle, the distance of side neck point to breast point, side neck point are to breast point
Distance/front length, BP dot spacing, BP dot spacing/chest measurement, abdomen coign, the angle of Attacking Midfielder's central point to chest both sides, side waist
Central point to the angle of chest both sides, the angle of the angle/side waist central point to chest both sides of Attacking Midfielder's central point to chest both sides,
Attacking Midfielder is to the vertical angle of breast, the angle of Attacking Midfielder's central point to buttocks both sides, the angle of side waist central point to buttocks both sides, front
Waist central point is to the angle/angle of side waist central point to buttocks both sides of buttocks both sides, the angle of Attacking Midfielder's central point to buttocks both sides
The angle of/Attacking Midfielder central point chest both sides, the folder of angle/side waist central point to chest both sides of side waist central point to buttocks both sides
Angle, the vertical angle of low back to buttocks, back of the body length, the back of the body length/height, the vertical angle of side knee center point to waist central point, side
Face waist central point to hit exactly before the angle of buttocks central point, lower body shaft angle, upper half health shaft angle, upper body angle, low back to collare angle,
Highly, enclose under neck circumference, shoulder breadth, chest measurement, breast, waistline, lower hip circumference, upper hip circumference, outer lower limb length, interior length.
In Matlab7.1, build the initial model of BP network, by network training, minimax method, side will be used respectively
Differ from method for normalizing and without processing the data after three kinds of methods process, be trained in a network, after being respectively trained 10 times,
Add up mean square error, the maximum error of prediction and average AME that they train for 10 times.Result shows, uses normalizing
The data that change method is treated time more used in BP modeling training than former data is few, and in method for normalizing, makes
The data processed by minimax method carry out BP training, time used than the data using variance method for normalizing to process
Few, precision is high.Therefore select minimax method that data are carried out pre-treatment.
By the neutral net of the heterogeneous networks number of plies, different training functions, different node transfer function is combined network
Structure is configured.By above network structure, the input parameter processed by minimax method is trained.It is respectively trained
After 10 times, add up mean square error, the maximum error of prediction and average AME that they train for 10 times.Result shows,
The neutral net number of plies uses 4 layers, and the training function setup of network is that { trainlm}, the node transfer function of network is set to
{ when logsig, purelin, logsig}, the maximum error of neural network forecast and mean error are minimum, and the mean square error of network training is can
In the range of acceptance, obtain optimal network structure.
Using 11 idiotype parameters as individually output, build 11 neutral nets respectively, use MIV (Mean Impact Value)
36 input parameters of network are screened, analyzes and determine in 36 idiotype characteristic parameters respectively to 11 idiotypes adjustment ginsengs
The input parameter of the predictive value impact maximum of number, sets up 4 layers of neutral net of 11 multiple input single output.
In analyzing three-dimensional fitting software, the coded system of the interface document of human parameters modeling, sets up third party software platform, interior
Putting neural network structure, inputted by the physical characteristic data file obtained by 3-D scanning, the parameter through neutral net turns
Change, automatically generate and be applied to anthropometric dummy interface document in three-dimensional fitting software.The interface document that will generate, imports three-dimensional examination
In clothing software, the three-dimensional virtual human body accordingly with customization physical characteristic can be generated.
The most visible: on the basis of the present invention is based on anthropometry, use BP neutral net, set up three-dimensional virtual human
Body girth size, height dimension, length dimension, angle-data reflect with build input nonlinearity in parameters in three-dimensional fitting software
Penetrating relation, the shape adjustment parameter using characteristics of human body's Parameters Transformation to obtain can apply to three-dimensional fitting software reaches to improve
The method of virtual human body modeling accuracy.The virtual fitting for jacket fit assessment can not only be met personalized, customization
Human Modeling demand, and can for clothing industry customization provide technical support, can realize from characteristics of human body's parameter to
Efficiently producing of personalized human body, can be widely used in custom made clothing platform.
Finally be necessary it is pointed out here that, described above is served only for being described in further detail technical scheme,
It is not intended that limiting the scope of the invention, those skilled in the art make according to the foregoing of the present invention one
A little nonessential improvement and adjustment belong to protection scope of the present invention.
Claims (3)
1. one kind is improved the method for virtual human body modeling accuracy in three-dimensional fitting software, it is characterised in that comprise the steps:
The first step, the impact of the Human Modeling parameters on human pattern of body form change confirmed in three-dimensional fitting software, select 11 to body
Table affects the bigger build modeling parameters output parameter as BP neutral net;Described 11 are bigger on body surface impact
Build modeling parameters is: shoulder parameter, chest locations parameter, breast peak distance parameter, abdomen parameter, health width parameter, buttocks
Width parameter, upper half height parameter, affect bodyside surface curve change pose parameter, affect waist to knee shaft angle change
Change lower part of the body pose parameter, bottom position parameter and affect upper half health shaft angle change upper body pose parameter;
The output parameter that second step, basis are selected, analyzes 36 physical characteristic parameters that output parameter may produce impact,
Input parameter as BP neutral net;36 described physical characteristic parameters are: front fillet, rear fillet, average shoulder angle,
Side neck point to the distance of breast point, the distance/front length of side neck point to breast point, BP dot spacing, BP dot spacing/chest measurement, abdomen coign,
Attacking Midfielder's central point is to the angle of chest both sides, the angle of side waist central point to chest both sides, Attacking Midfielder's central point to chest both sides
Angle/the angle of side waist central point to chest both sides, the vertical angle of Attacking Midfielder to breast, the angle of Attacking Midfielder's central point to buttocks both sides,
Side waist central point is to the angle of buttocks both sides, the folder of the angle/side waist central point to buttocks both sides of Attacking Midfielder's central point to buttocks both sides
Angle, the angle/angle of Attacking Midfielder's central point chest both sides of Attacking Midfielder's central point to buttocks both sides, side waist central point are to buttocks both sides
In the angle/angle of side waist central point to chest both sides, the vertical angle of low back to buttocks, back of the body length, the back of the body length/height, side knee
Heart point to the vertical angle of waist central point, the angle of side waist central point to buttocks central point, lower body shaft angle, upper half health shaft angle,
Hit exactly before upper body angle, low back to collare angle, highly, enclose under neck circumference, shoulder breadth, chest measurement, breast, waistline, lower hip circumference, upper buttocks
Enclose, outer lower limb length and interior length;
3rd step, under Matlab environment, build the initial model of BP network, by network training, analyze minimax method,
Normalized square mean method and without processing after data are standardized processing by three kinds of methods respectively the shadow to neural network forecast ability
Ring, analyze that the different network numbers of plies arranges the impact on neural network forecast ability, to analyze different training function setup pre-to network
The impact of survey ability, analyze different node transfer function and the impact on neural network forecast ability is set, analyzes different hidden layer joints
Count and arrange the impact on neural network forecast ability, analysis heterogeneous networks inputs and output parameter arranges the shadow to neural network forecast ability
Ring, obtain optimum network structure: the neutral net number of plies uses 4 layers, and the training function setup of network is { trainlm}, network
Node transfer function be set to logsig, purelin, logsig}, and set up physical characteristic parameter with in three-dimensional fitting software
Shape adjustment nonlinearity in parameters mapping relations;
In 4th step, analyzing three-dimensional fitting software, the coded system of the interface document of human parameters modeling, sets up third party software
Platform, built-in neural network structure, inputted, through neutral net by the physical characteristic data file that 3-D scanning is obtained
Parameters Transformation, automatically generate and be applied to anthropometric dummy interface document in three-dimensional fitting software, then the interface document of generation is led
Enter in three-dimensional fitting software, the three-dimensional virtual human body accordingly with customization physical characteristic can be generated.
The method of virtual human body modeling accuracy in raising three-dimensional fitting software the most according to claim 1, it is characterised in that:
3rd step selects minimax method to process data.
The method of virtual human body modeling accuracy in raising three-dimensional fitting software the most according to claim 1, it is characterised in that:
Described three-dimensional fitting software has build input parameter, shape adjustment parameter and human parameters modeling interface document.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210559590.2A CN103886117B (en) | 2012-12-20 | 2012-12-20 | A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210559590.2A CN103886117B (en) | 2012-12-20 | 2012-12-20 | A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103886117A CN103886117A (en) | 2014-06-25 |
CN103886117B true CN103886117B (en) | 2016-08-24 |
Family
ID=50955009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210559590.2A Expired - Fee Related CN103886117B (en) | 2012-12-20 | 2012-12-20 | A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103886117B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104881892B (en) * | 2015-06-04 | 2017-10-27 | 厦门唯尔酷信息技术有限公司 | Model deformation method and its system |
CN107154071A (en) * | 2016-03-02 | 2017-09-12 | 南京航空航天大学 | The method that Case-based Reasoning generates individual face body Model according to anthropological measuring size data |
CN108197654A (en) * | 2018-01-03 | 2018-06-22 | 杭州贝嘟科技有限公司 | Stature data predication method, device, storage medium and equipment based on SVM algorithm |
JP6921768B2 (en) * | 2018-02-21 | 2021-08-18 | 株式会社東芝 | Virtual fitting system, virtual fitting method, virtual fitting program, and information processing device |
CN108876881A (en) * | 2018-06-04 | 2018-11-23 | 浙江大学 | Figure self-adaptation three-dimensional virtual human model construction method and animation system based on Kinect |
CN113474824A (en) * | 2019-02-25 | 2021-10-01 | 松下知识产权经营株式会社 | Evaluation system, spatial design support system, evaluation method, and program |
CN110135078B (en) * | 2019-05-17 | 2023-03-14 | 浙江凌迪数字科技有限公司 | Human body parameter automatic generation method based on machine learning |
CN110705023A (en) * | 2019-08-30 | 2020-01-17 | 杭州海飘科技有限公司 | Somatosensory support technical method based on neural network algorithm |
CN112200717B (en) * | 2020-10-26 | 2021-07-27 | 广州紫为云科技有限公司 | Complex garment virtual fitting method and device based on neural network and storage medium |
CN117541685A (en) * | 2023-11-08 | 2024-02-09 | 另一个我(北京)虚拟科技开发有限公司 | Virtual mapping human body model construction method and system for personalized service requirements and personalized service platform |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101013481A (en) * | 2007-02-09 | 2007-08-08 | 浙江理工大学 | Female body classification and identification method |
-
2012
- 2012-12-20 CN CN201210559590.2A patent/CN103886117B/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101013481A (en) * | 2007-02-09 | 2007-08-08 | 浙江理工大学 | Female body classification and identification method |
Non-Patent Citations (3)
Title |
---|
基于BP神经网络的服装号型推荐方法研究;郑爱花;《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》;20110615;第2011年卷(第06期);第B024-230页的摘要、第1.2.2节、第4.2节、第4.3节、第4.5节和图4.2、表4.2 * |
基于用户照片和神经网络的三维个性化人体建模方法研究;邓卫燕;《中国博士学位论文全文数据库 信息科技辑》;20090415;第2009年卷(第04期);第I138-34页 * |
基于神经网络的三维人体建模方法;邓卫燕等;《上海交通大学学报》;20081031;第42卷(第10期);第1631-1634、1639页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103886117A (en) | 2014-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103886117B (en) | A kind of improve the method for virtual human body modeling accuracy in three-dimensional fitting software | |
CN103886115B (en) | The foundation of a kind of three-dimensional virtual human platform based on different building shape and call method thereof | |
CN108256975A (en) | Wearing for 3-D effect is provided for virtual fitting person take system and method based on artificial intelligence | |
CN106066898A (en) | Three-dimensional full-fashioned knitted sweater and method and system for generating three-dimensional knitting pattern thereof | |
JP6836038B2 (en) | Human body model providing system, human body model transformation method, and computer program | |
CN107705365A (en) | Editable three-dimensional (3 D) manikin creation method, device, electronic equipment and computer program product | |
CN103535963B (en) | Sportswear dynamic foundation pattern and foundation pattern building method | |
JPH10130929A (en) | Device for producing corrected underwear and its production | |
CN103413350A (en) | Three-dimensional cup model obtaining method based on three-dimensional chest shapes | |
McKinney et al. | Building patternmaking theory: a case study of published patternmaking practices for pants | |
CN107480315A (en) | Parameterize the method and system of model design | |
Hong et al. | Collaborative 3D-to-2D tight-fitting garment pattern design process for scoliotic people | |
CN109064386A (en) | A kind of method for building up of 3 D stereo garment form | |
CN108175140A (en) | A kind of processing method of Western-style clothes back | |
Petrak et al. | Research of 3D body models computer adjustment based on anthropometric data determined by laser 3D scanner | |
Cha | The uplifting effect of a prototype brassiere | |
CN105876958A (en) | Pattern making method for asymmetric corselet | |
KR102263987B1 (en) | Apparatus and methods for providing shape of user-customized bedding | |
Slavinska et al. | Development of an adaptive method for regulating corset comfort based on the parameters of design zones identification | |
Sun et al. | Image perception of female breast beauty and its relation to 3D anthropometric measurements | |
CN109741149B (en) | Clothing size generation method and system | |
CN104881892B (en) | Model deformation method and its system | |
WO2020232917A1 (en) | Automatic human body parameter generation method based on machine learning | |
Sun et al. | The stable status evaluation for female breast implant surgery by calculating related physics parameters | |
Wang | A study of ease distribution in relation to jacket pattern alteration |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160824 |