CN106503345B - A kind of indigo printing fabric Ridge tracing method - Google Patents
A kind of indigo printing fabric Ridge tracing method Download PDFInfo
- Publication number
- CN106503345B CN106503345B CN201610931819.9A CN201610931819A CN106503345B CN 106503345 B CN106503345 B CN 106503345B CN 201610931819 A CN201610931819 A CN 201610931819A CN 106503345 B CN106503345 B CN 106503345B
- Authority
- CN
- China
- Prior art keywords
- grain pattern
- model
- skeleton
- pattern element
- printing fabric
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/12—Cloth
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/16—Cloth
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention discloses a kind of indigo printing fabric Ridge tracing methods.The present invention carries out element modeling, Model Matching and grain pattern to blue plating sample using digital graphic images technology and reconstructs, and realizes Traditional Dermatoglyphic Pattern innovative design on the basis of grain pattern parametrization.Main technical content of the present invention includes: to establish grain pattern element model using tensile splines curve;The grain pattern element in image is extracted using contour following algorithm, and carries out Model Matching using Hu square;To the parametrization grain pattern obtained after Model Matching, model parameter is mapped to target interval using mapping function, realizes the grain pattern innovative design of constant bone;Grain pattern skeleton is extracted by similar figures series, skeleton is carried out using parameter mapping method and builds again, grain pattern element is placed on new skeleton, realize the grain pattern innovative design of variation bone.Method provided by the invention, the bottleneck that can be used for solving indigo printing fabric grain pattern innovative design, open up new approach for the succession and development of this non-material cultural heritage of indigo printing fabric.
Description
Technical field
The invention belongs to Textile Pattern Design fields, and in particular to a kind of indigo printing fabric grain pattern innovative design method.
Background technique
Indigo printing fabric is the traditional textile of great civil characteristic, is identified as national non-material cultural heritage.It is blue at present
Calico Ridge tracing relies primarily on a small number of traditional-handwork artists, and design output capacity is limited, grain pattern innovation is difficult, becomes system
The about bottleneck of China's indigo printing fabric succession and development.Although can be provided by some Modern Graphic Design softwares for Ridge tracing
It is convenient, but this kind of software can not provide the key problem in mentality of designing and method, solution Ridge tracing as tool.Needle
Innovative design to traditional indigo printing fabric grain pattern, still lacks effective method at present.
Summary of the invention
This problem is innovated to solve indigo printing fabric grain pattern, the present invention provides a kind of indigo printing fabric grain pattern innovative design side
The transformation and innovation in grain pattern element level not only may be implemented based on existing traditional indigo printing fabric grain pattern in method, this method,
The innovation in grain pattern skeleton level can also be realized, so that improved grain pattern has a possibility that abundant.
The present invention is achieved through the following technical solutions: existing indigo printing fabric grain pattern being analyzed and is abstracted first, is built
Found a grain pattern element model;Then traditional indigo printing fabric grain pattern is matched using the model, realizes the modelling of grain pattern;
Finally by the Mapping and Converting to model parameter, the reconstruct and innovation of grain pattern are realized.
Main technical content of the invention includes:
(1) grain pattern element models
Grain pattern element model is established using the closed tensile splines curve by four nodes.Include in four nodes
Two moving points and two fixing points.Fixed point is located in reference axis, and moving point can then deviate reference axis in a certain range.Gu
Fixed point embodies the conformality of model, and moving point then embodies the diversity of mould shapes.Tradition is showed by model parameter control
The various grain pattern elements of indigo printing fabric.
(2) Model Matching
On the basis of image preprocessing, the grain pattern element in image is extracted using contour following algorithm.Utilize Hu square
Affine-invariant features are chosen and the immediate model instance of grain pattern element (mould shapes determined by a group model parameter value).It is right
The model instance of selection carries out affine transformation (translation, scaling, rotation), be allowed to grain pattern element maximal degree of coincidence, to substitute line
Original element in sample, to complete Model Matching.
(3) grain pattern reconstructs
To the parametrization grain pattern obtained after Model Matching, the mapping function selected using user, by one or more parameters
It is mapped to target interval, obtains the Ridge tracing of constant bone.Alternatively, being obtained by the way that grain pattern element is clustered and classified
Similar figures series in grain pattern, determines the skeleton point in grain pattern by similar figures series, connects all skeleton points and generates grain pattern bone
Frame;Grain pattern skeleton is regarded as single grain pattern element, matches grain pattern skeleton, then the mapping letter selected by user using element model
Number carries out skeletons and builds again, sampling site and needs to configure grain pattern element according to user again on new skeleton, obtains variation bone
Ridge tracing.
The present invention sufficiently can excavate and be transformed existing indigo printing fabric grain pattern, make improved grain pattern that new style face be presented
Looks realize the innovative design of traditional indigo printing fabric grain pattern, open up new approach for the succession and development of China's indigo printing fabric.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is grain pattern element model schematic diagram;
Fig. 2 (a) be model instance express various indigo printing fabric grain pattern elements section Example (on);
Fig. 2 (b) be model instance express various indigo printing fabric grain pattern elements section Example (under);
Fig. 3 is Model Matching process schematic;
Fig. 4 is one embodiment of constant skeleton grain pattern reconstruct;
Fig. 5 is the one embodiment for changing the reconstruct of skeleton grain pattern.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings of the specification.
In Fig. 1, two active nodes are P1, P2, and two stationary nodes are P3, P4, and O point is origin or reference point.Gu
Determine node P3, P4 to be located in x-axis and y-axis, intercept is respectively -1 and 1.Active node P1, P2 then can in a certain range partially
From reference axis, specific location is determined by radius of action (r1, r2) and deflecting angle (d1, d2).Sequentially using tensile splines curve
It connects P1, P2, P3, P4 and constitutes close-shaped, the universal model as grain pattern element.The model has r1, r2, d1, d2, t total
Five configuration parameters, wherein t is the coefficient of tension of spline curve.The value range of model parameter: -5≤r1≤5;-45°≤d1
≤45°;-5≤r2≤5;-45°≤d2≤45°;0≤t≤3.
In Fig. 2, some model instances are listed for expressing various typical indigo printing fabric grain pattern elements.To five moulds
Shape parameter distinguishes uniform sampling 20 values in its value interval, specifically: t takes 0.15k, and r1, r2 take -5+0.5k, d1, d2
- 45+4.5k is taken, wherein k=0,1,2 ..., 19.Each parameter has 20 values, combine 205Group parameter value.By one group of parameter
The determining mould shapes of value are a model instance, share 205A model instance, these mould examples constitute a model instance
Library.Its Hu square, position of centre of gravity and area are calculated to each model instance and are stored in model instance library, for making when Model Matching
With.
In Fig. 3, original image after gray processing, first passes through median filtering removal noise, reuses OTSU algorithm
Threshold segmentation is carried out, target and background are isolated.On this basis, each grain pattern member in image is extracted using contour following algorithm
Plain (red marks in figure).Hu square, position of centre of gravity and area are calculated to the grain pattern element of extraction, grain pattern element is calculated and model is real
The similarity distance (Euclidean distance of two Hu squares) of each model instance, chooses immediate model instance therewith in example library.It is right
The model instance of selection carries out affine transformation, first by its barycenter displacement to the center of gravity of grain pattern element, so that the two barycentric coodinates
Unanimously;Then both calculate the difference of area, if more than zero (model instance area is greater than element area) then by mould shapes gradually
It reduces, otherwise gradually amplifies, until the two area equation, zoom ratio at this time remembers s;Finally by model instance on 0~360 °
Rotation, the registration of computation model example and grain pattern element in each angle keep the angle, θ of maximal degree of coincidence in mind.In this way, line
Sample element is parameterized model instance substitution.The all elements in grain pattern are substituted with model instance according to the above method, just
Complete Model Matching.Wherein s, θ are the affine parameter of model instance, together with five model parameters r1, r2, d1, d2, t, they
It can be used when grain pattern reconstructs.
In Fig. 4, one or more model parameters are mapped to by target interval by the mapping function that user selects, are carried out
The grain pattern of constant skeleton reconstructs.If the parameter value of mapping front and back is respectively Z and Z ', the mapping function for reconstruct is Z '=f
(Z).Participate in mapping can be model parameter, be also possible to affine parameter.Some examples of mapping function are given in figure.
In Fig. 5, by rebuilding the skeleton of grain pattern, and grain pattern element is reconfigured on new skeleton, be changed bone
The grain pattern of frame reconstructs.Specifically: comprehensive Hu square and area are as index, by the way that grain pattern element is clustered and classified, by shape
Shape is similar and area similar in element be classified as a kind of (i.e. a similar figures series).For there are the feelings of multiple similar figures series
Condition is reconstructed in which series by user's selection.Then, to the similar figures series of selection, by the ginseng of wherein each grain pattern element
Examination point (the O point of i.e. each grain pattern element) is used as skeleton point, and connection skeleton point obtains grain pattern skeleton, then grain pattern skeleton is considered as list
A grain pattern element matches grain pattern skeleton using element model, passes through parameter mapping reconstruction skeleton.Finally, provided according to user
Element number, the equidistant sampling site on new skeleton place grain pattern element using element model on each point, complete variation bone
The grain pattern of frame reconstructs.The example of variation skeleton grain pattern reconstruct is given in figure.
Claims (5)
1. a kind of design method of indigo printing fabric grain pattern, it is characterised in that include the following steps
1) grain pattern element models
The universal model of grain pattern element, four nodes are established using the closed tensile splines curve by four nodes
In include two moving points and two fixing points, wherein fixed point is located in plane coordinates axle, passes through the model of model built ginseng
Number changes to show the various grain pattern elements of indigo printing fabric;
2) Model Matching
Original image after gray processing, first passes through median filtering removal noise, reuses OTSU algorithm and carry out Threshold segmentation,
Isolate target and background;The grain pattern element in image is extracted using contour following algorithm, Hu is calculated to the grain pattern element of extraction
Square, position of centre of gravity and area calculate the similarity distance of each model instance in grain pattern element and model instance library, choose therewith most
Close model instance carries out affine transformation to the model instance of selection, be allowed to grain pattern element maximal degree of coincidence, to substitute line
Original element in sample, to complete Model Matching;
3) grain pattern reconstructs
To the parametrization grain pattern obtained after Model Matching, one or more model parameters are reflected using the mapping function that user selects
It is mapped to target interval, obtains the Ridge tracing of constant bone;Alternatively, obtaining line by the way that grain pattern element is clustered and classified
Similar figures series in sample, determines the skeleton point in grain pattern by similar figures series, connects all skeleton points and generates grain pattern skeleton,
Grain pattern skeleton is matched using element model, the model parameter variation selected by user carries out skeleton and builds again, on new skeleton
Again it sampling site and needs to place grain pattern element according to user, obtains the Ridge tracing of variation bone.
2. indigo printing fabric Ridge tracing method according to claim 1, it is characterised in that stationary nodes P3, P4 point
Wei Yu not be in x-axis and y-axis, intercept is respectively -1 and 1, and the model parameter includes r1, r2, d1, d2, t, and wherein r1, r2 points
Not Wei moving point P1, P2 radius of action, d1, d2 are respectively the deflecting angle of moving point P1, P2, and t is the tension system of spline curve
Number.
3. indigo printing fabric Ridge tracing method according to claim 2, it is characterised in that the value model of the model parameter
It encloses: -5≤r1≤5;-45°≤d1≤45°;-5≤r2≤5;-45°≤d2≤45°;0≤t≤3.
4. indigo printing fabric Ridge tracing method according to claim 3, it is characterised in that the step 2) specific method
Are as follows: original image after gray processing, first passes through median filtering removal noise, reuses OTSU algorithm and carry out Threshold segmentation,
Isolate target and background;
On the basis of the above, each grain pattern element in image is extracted using contour following algorithm, the grain pattern element of extraction is calculated
Hu square, position of centre of gravity and area calculate the similarity distance of each model instance in grain pattern element and model instance library, i.e. two Hu
The Euclidean distance of square chooses immediate model instance therewith;Affine transformation is carried out to the model instance of selection, first by its center of gravity
The center of gravity of grain pattern element is moved to, so that the two barycentric coodinates are consistent;Then the difference of the two area is calculated, if more than zero, i.e.,
Model instance area is greater than element area, then gradually reduces mould shapes, otherwise gradually amplify, until the two area equation,
Zoom ratio at this time remembers s;Finally by model instance in 0~360 ° of upper rotation, computation model example and grain pattern in each angle
The registration of element keeps the angle, θ of maximal degree of coincidence in mind;
In this way, grain pattern element is parameterized model instance substitution.
5. indigo printing fabric Ridge tracing method according to claim 4, it is characterised in that the structure in the model instance library
Construction method is: to five model parameters r1, r2, d1, d2, t, uniform sampling 20 values are distinguished in its value interval, specifically:
T takes 0.15k, and r1, r2 take -5+0.5k, and d1, d2 take -45+4.5k, wherein k=0, and 1,2 ..., 19, each parameter has 20 values,
Combine 205Group parameter value is a model instance by the mould shapes that one group of parameter value determines, shares 205A model instance,
These model instances constitute a model instance library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610931819.9A CN106503345B (en) | 2016-10-25 | 2016-10-25 | A kind of indigo printing fabric Ridge tracing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610931819.9A CN106503345B (en) | 2016-10-25 | 2016-10-25 | A kind of indigo printing fabric Ridge tracing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106503345A CN106503345A (en) | 2017-03-15 |
CN106503345B true CN106503345B (en) | 2019-02-19 |
Family
ID=58319633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610931819.9A Expired - Fee Related CN106503345B (en) | 2016-10-25 | 2016-10-25 | A kind of indigo printing fabric Ridge tracing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106503345B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647456A (en) * | 2018-05-16 | 2018-10-12 | 贵州大学 | A kind of quantification design method of automobile style iteration |
CN109360266A (en) * | 2018-09-20 | 2019-02-19 | 深圳市创梦天地科技有限公司 | A kind of road modeling method, relevant apparatus and equipment |
CN111862330A (en) * | 2020-07-16 | 2020-10-30 | 完美世界(北京)软件科技发展有限公司 | Model acquisition method and apparatus, storage medium, and electronic apparatus |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010019573A (en) * | 2008-07-08 | 2010-01-28 | Nec Electronics Corp | Navigation system, navigation control device, and destination retrieval method |
CN103870645A (en) * | 2014-03-12 | 2014-06-18 | 天津大学 | Wax printing stamping pattern emulation method with ice vein effects |
CN103871084A (en) * | 2014-04-04 | 2014-06-18 | 南通农业职业技术学院 | Method for recognizing patterns of blueprint cloth |
CN104778458A (en) * | 2015-04-17 | 2015-07-15 | 浙江理工大学 | Textile pattern retrieval method based on textural features |
CN105787163A (en) * | 2015-12-31 | 2016-07-20 | 福州琪利软件有限公司 | Generating system and generating method of textile pattern file |
-
2016
- 2016-10-25 CN CN201610931819.9A patent/CN106503345B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010019573A (en) * | 2008-07-08 | 2010-01-28 | Nec Electronics Corp | Navigation system, navigation control device, and destination retrieval method |
CN103870645A (en) * | 2014-03-12 | 2014-06-18 | 天津大学 | Wax printing stamping pattern emulation method with ice vein effects |
CN103871084A (en) * | 2014-04-04 | 2014-06-18 | 南通农业职业技术学院 | Method for recognizing patterns of blueprint cloth |
CN104778458A (en) * | 2015-04-17 | 2015-07-15 | 浙江理工大学 | Textile pattern retrieval method based on textural features |
CN105787163A (en) * | 2015-12-31 | 2016-07-20 | 福州琪利软件有限公司 | Generating system and generating method of textile pattern file |
Non-Patent Citations (3)
Title |
---|
基于局部特征的服饰图案检索研究;徐平华 等;《北京服装学院学报》;20131031;第33卷(第4期);43-49 |
空间均匀有理张力样条参数曲线;孟雅琴 等;《计算机学报》;20031231;第26卷(第12期);1776-1780 |
织物图案连续性识别;陶晨 等;《纺织学报》;20160831;第37卷(第8期);37-40 |
Also Published As
Publication number | Publication date |
---|---|
CN106503345A (en) | 2017-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069746B (en) | Video real-time face replacement method and its system based on local affine invariant and color transfer technology | |
CN106327532B (en) | A kind of three-dimensional registration method of single image | |
Huang et al. | L1-medial skeleton of point cloud. | |
CN100543775C (en) | The method of following the tracks of based on the 3 d human motion of many orders camera | |
Livny et al. | Automatic reconstruction of tree skeletal structures from point clouds | |
CN108510577B (en) | Realistic motion migration and generation method and system based on existing motion data | |
CN105741355B (en) | A kind of block dividing method of triangle grid model | |
CN108399649A (en) | A kind of single picture three-dimensional facial reconstruction method based on cascade Recurrent networks | |
CN109166100A (en) | Multi-task learning method for cell count based on convolutional neural networks | |
CN106503345B (en) | A kind of indigo printing fabric Ridge tracing method | |
CN103310481B (en) | A kind of point cloud compressing method based on fuzzy entropy iteration | |
CN101783016B (en) | Crown appearance extract method based on shape analysis | |
CN107194937A (en) | Tongue image partition method under a kind of open environment | |
CN105138975B (en) | A kind of area of skin color of human body dividing method based on degree of depth conviction network | |
CN103871100A (en) | Method for rebuilding tree model based on point cloud and data driving | |
CN109766873A (en) | A kind of pedestrian mixing deformable convolution recognition methods again | |
Liu et al. | Image edge recognition of virtual reality scene based on multi-operator dynamic weight detection | |
CN111028335A (en) | Point cloud data block surface patch reconstruction method based on deep learning | |
CN110047079A (en) | A kind of optimum segmentation scale selection method based on objects similarity | |
CN105957154B (en) | A kind of the threedimensional model edit methods and system of data-driven | |
CN110757806A (en) | 3D printing-oriented double-type-shape close-laying method and system | |
CN114758070A (en) | Single-image three-dimensional human body fine reconstruction method based on cross-domain multitask | |
CN103300922A (en) | Generation of visual command data | |
Fengyi et al. | 3D Garment Design Model Based on Convolution Neural Network and Virtual Reality | |
CN108229502A (en) | A kind of three dimensional point cloud middle period chip base point extracting method of crown canopy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190219 Termination date: 20191025 |
|
CF01 | Termination of patent right due to non-payment of annual fee |