CN106127781A - The measuring method of a kind of yarn dyed fabric density and device - Google Patents
The measuring method of a kind of yarn dyed fabric density and device Download PDFInfo
- Publication number
- CN106127781A CN106127781A CN201610504660.2A CN201610504660A CN106127781A CN 106127781 A CN106127781 A CN 106127781A CN 201610504660 A CN201610504660 A CN 201610504660A CN 106127781 A CN106127781 A CN 106127781A
- Authority
- CN
- China
- Prior art keywords
- image
- dyed fabric
- yarn dyed
- yarn
- subimage
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004927 fusion Effects 0.000 claims abstract description 42
- 230000009466 transformation Effects 0.000 claims abstract description 33
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 11
- 230000008878 coupling Effects 0.000 claims abstract description 4
- 238000010168 coupling process Methods 0.000 claims abstract description 4
- 238000005859 coupling reaction Methods 0.000 claims abstract description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 101000643424 Homo sapiens Protein phosphatase Slingshot homolog 1 Proteins 0.000 claims description 6
- 101000643431 Homo sapiens Protein phosphatase Slingshot homolog 2 Proteins 0.000 claims description 6
- 239000004753 textile Substances 0.000 claims description 5
- 238000002156 mixing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 229910052704 radon Inorganic materials 0.000 claims description 3
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 3
- 101100110333 Arabidopsis thaliana ATL31 gene Proteins 0.000 claims description 2
- 102100023431 E3 ubiquitin-protein ligase TRIM21 Human genes 0.000 claims description 2
- 101000685877 Homo sapiens E3 ubiquitin-protein ligase TRIM21 Proteins 0.000 claims description 2
- 101000685886 Homo sapiens RNA-binding protein RO60 Proteins 0.000 claims description 2
- 101100045541 Homo sapiens TBCD gene Proteins 0.000 claims description 2
- 102100023433 RNA-binding protein RO60 Human genes 0.000 claims description 2
- 101150093640 SSD1 gene Proteins 0.000 claims description 2
- 101100111629 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR2 gene Proteins 0.000 claims description 2
- 241001011888 Sulfolobus spindle-shaped virus 1 Species 0.000 claims description 2
- 241001011846 Sulfolobus spindle-shaped virus 2 Species 0.000 claims description 2
- 102100030290 Tubulin-specific chaperone D Human genes 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000000205 computational method Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims description 2
- 238000001179 sorption measurement Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000000605 extraction Methods 0.000 abstract 1
- 238000005259 measurement Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 239000002759 woven fabric Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T3/147—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Abstract
The invention provides measuring method and the device of a kind of yarn dyed fabric density.Front-back two-sided image capturing system gathers the front-back two-sided image of yarn dyed fabric;Utilize affine transformation to realize the one_to_one corresponding of front-back two-sided image pixel-class, complete the para-position coupling of front-back two-sided image;By Image Fusion based on double-deck wavelet transformation, the gray-scale map of front-back two-sided image is merged;The spectrogram of fusion image is obtained by fast Fourier transform technology;Complete yarn dyed fabric density finally by the characteristic frequency point of correspondence yarn cycle information in extraction spectrogram automatically to measure.
Description
Technical field
The present invention relates to Automatic Measurement Technique field, particularly to a kind of side measuring yarn dyed fabric density based on spectrum analysis
Method and device.
Background technology
Yarn dyed fabric density is the critical specifications parameter of woven fabric, and fabric and the outward appearance of clothing and physical property are played decision
Property effect, the measurement of yarn dyed fabric density is the most also part indispensable in textile product quality testing link.Traditional measurement
The method of yarn dyed fabric density be specialty testing staff with the help of pick glass, observe by the naked eye analysis and complete.Use pick glass
Although it is simple and practical to measure Density, but there is detection time length, inefficient shortcoming, also it is vulnerable to the skilled of testing staff
Degree and the impact of individual's subjective sensation.
Along with the fast development of image processing and artificial intelligence, the research worker of weaving neighborhood start by computer technology by
Step is applied to quality of textile products detection, the most just includes the device automatically measuring Density with digitized.Can be from existing skill
Art (CN201110174101.7;CN201210094860.7) learn the automatic measurement of Density, be mostly based on one-sided image
It is digitized measurement to complete.But yarn dyed fabric is to be interweaved by warp thread and weft yarn to form, filling yarn is the one of fabric
Face presents periodically sink-float, so only cannot obtain complete yarn information from yarn dyed fabric one-sided image, thus affects yarn
The accuracy of density measure.
Summary of the invention
The measuring method that it is an object of the invention to provide a kind of yarn dyed fabric density and the measurement utilizing the method to design thereof
The device of yarn dyed fabric density.The measuring method of a kind of yarn dyed fabric density, utilizes affine transformation to complete the front-back two-sided image of yarn dyed fabric
Coupling, utilize Wavelet Fusion algorithm to be merged by front-back two-sided image, then obtain fusion image by Fourier transformation
Spectrogram, utilize the characteristic frequency peak dot in spectrogram obtain reconstruct filling yarn image and calculate thread density.One
Kind utilize the measurement apparatus of the yarn dyed fabric density that this yarn dyed fabric density measuring method designs, mainly include five parts: CCD phase
Machine, standard light source, with standard color block and the sample holder of characteristic matching point, close camera bellows, data handling machine.For realizing
Object above, the invention provides the density measuring method of a kind of yarn dyed fabric, comprises the following steps:
1) front-back two-sided for yarn dyed fabric image is carried out image co-registration and obtain fusion image;
2) fusion image is obtained spectrogram by Fourier transform;Spectrogram is processed the filling yarn figure obtaining reconstruct
Picture, then calculates yarn dyed fabric density according to the filling yarn image of reconstruct.
Step 1) front-back two-sided for yarn dyed fabric image carried out image co-registration obtain fusion image:
Front-back two-sided for yarn dyed fabric image is completed front-back two-sided images match by affine transformation, then utilizes double-deck small echo
Conversion blending algorithm processes and obtains fusion image.
As preferably, complete front-back two-sided images match process by affine transformation and specifically include following steps:
A, image segmentation and Sobel edge edge detective operators is utilized to extract place, three limits of feature triangle straight line;
B, Radon transformation calculations is utilized to go out the linear equation on three limits;
C, calculating triangular apex coordinate obtain its focus point coordinate;
D, using center of gravity as characteristic matching point, obtained the front-back two-sided image mated by affine transformation.
As preferably, in utilizing Wavelet Fusion algorithm to be merged by front-back two-sided image, front-back two-sided image enters
The process that row merges specifically includes step:
If the textile image that S is input, SA is the low frequency subgraph picture that ground floor wavelet decomposition obtains, and SH is horizontal high-frequent
Image, SV is vertical high frequency subimage, and SD is diagonal angle high frequency subimage;SSA, SSH, SSV and SSD are respectively the little wavelength-division of the second layer
Solve low frequency subgraph as corresponding four subimages of SA;
A) utilize double-deck wavelet decomposition fabric front-back two-sided image S1 and S2, obtain the subimage after it decomposes;
B) the horizontal high-frequent subimage that direct picture S1 and verso images S2 obtains after double-deck wavelet decomposition is extracted respectively
SSH1 and SSH2;In horizontal high-frequent subimage, calculate centered by each pixel, in 3x3 region, amount to 9 pixels
Local variance value, if DSSH1And DSSH2Represent the local variance value of calculated SSH1 and SSH2, then fusion image the 3rd respectively
In layer horizontal high-frequent subimage SSH, the value of respective pixel point can obtain by below equation:
Wherein, m, n are respectively picture level direction pixel number and vertical direction pixel number;
C) use and B) identical computational methods, utilize SSV1 and SSV2, SSA1 and SSA2, SSD1 and SSD2 can obtain
Fusion image third layer vertical high frequency subimage SSV and diagonal angle high frequency subimage SSD and front low frequency subgraph are as SSA;
D) utilize the SSH, SSV and the SSD that calculate and SSA, obtain fusion image the by 2-d discrete wavelet inverse transformation
Two layers of low frequency subgraph are as SA;
E) use and step B) to D) the horizontal high-frequent subimage SH of the identical method calculating fusion image second layer, vertically
High frequency subimage SV and diagonal angle high frequency subimage SD;
F) utilize SH, SV, SD and the SA calculated, finally give fusion image S by 2-d discrete wavelet inverse transformation.
Step 2) fusion image is obtained spectrogram by Fourier transform, spectrogram is processed and obtains filling yarn reconstruct
Figure, then calculates yarn dyed fabric density according to the filling yarn image of reconstruct.
As preferably, fusion image is obtained spectrogram by Fourier transform, spectrogram is processed and obtains through weft yarn
Line reconstruct figure, then calculates yarn dyed fabric density according to the filling yarn image of reconstruct, specifically includes following steps:
1, fast Fourier transform technology is utilized to obtain the spectrogram of fusion image;
2, utilize peak dot filtering to extract in spectrogram and be positioned at the characteristic frequency point both horizontally and vertically gone up, represent warp respectively
Yarn and weft yarn cycle;
3, utilize the peak dot information extracted, obtain filling yarn reconstruct figure by Fourier inversion and calculate yarn
Density, as it is furthermore preferred that the computing formula of thread density is:
Wherein, in formula: R represents the resolution gathering image;Sw, ShBeing width and the height of original image respectively, unit is
Inch;X, y are respectively original image pixel count both horizontally and vertically;dj, dwIt is respectively warp count and weft count.
A kind of yarn dyed fabric density measuring equipment utilizing the method to design, mainly includes five parts: CCD camera, standard
Light source, with standard color block and the sample holder of characteristic matching point, close camera bellows, data handling machine.CCD camera, standard
Light source, sample holder with standard color block and characteristic matching point are placed in closing camera bellows;Sample holder is vertically placed on camera bellows
On bottom centerline;Yarn dyed fabric sample to be measured is positioned in sample holder;Standard light source is symmetrically disposed at yarn dyed fabric both sides;At color
The symmetrically placed CCD camera in fabric both sides;CCD camera is connected with data handling machine;
After opening standard light source, the CCD camera shooting front-back two-sided image of yarn dyed fabric, image information transmission is processed to data
Computer, data handling machine utilizes the described corresponding algorithm of yarn dyed fabric density measuring method to complete yarn dyed fabric density measure.
Preferably, sample holder includes the two pieces of grip blocks mutually clamped, and the surface of grip block is provided with 24 color calibration color lumps
Triangle is mated with para-position;Between grip block, the magnet adsorption by being mutually matched clamps.Preferably, yarn dyed fabric density measure dress
Putting Plays light source is four, and symmetry is placed in the right and left of sample holder.
In the present invention, the front-back two-sided image of yarn dyed fabric is gathered by front-back two-sided image capturing system;Utilize affine change
Change the one_to_one corresponding realizing front-back two-sided image pixel-class, complete two-sided para-position coupling;By figure based on double-deck wavelet transformation
As blending algorithm, the gray-scale map of front-back two-sided image is merged;Fusion image is obtained by fast Fourier transform technology
Spectrogram;The survey of yarn dyed fabric density is completed finally by extracting the characteristic frequency point of corresponding yarn cycle information in spectrogram
Amount.
Accompanying drawing explanation
Fig. 1 is the yarn dyed fabric density measuring equipment in the present invention;1-camera bellows in figure, 2-computer, 3-CCD camera, 4-marks
Quasi-optical source, 5-sample holder;
Fig. 2 is the sample holder schematic diagram in yarn dyed fabric density measuring equipment;7-match point, 8-standard color block, 9-rectangle
Magnetic stripe;
Fig. 3 is the measuring method flow chart of yarn dyed fabric density in the present invention;FFT is two-dimensional fast fourier transform, IFFT
For two dimension Fast Fourier Transform Inverse;
Fig. 4 is double-deck wavelet decomposition tree schematic diagram in the present invention;
Fig. 5 is example sample fabric face gradation of image figure in the present invention;
Fig. 6 is example sample fabric backing gradation of image figure in the present invention;
Fig. 7 is fusion image in the present invention;
Fig. 8 is small echo blending algorithm flow chart in the present invention;
Fig. 9 is spectrogram and the filling yarn reconstruct figure of fusion image in the present invention;A-fusion image spectrogram, b-level
Two peak dots on direction, two peak dots in c-vertical direction, d-warp thread reconstruct figure, e-weft yarn reconstruct figure.
Detailed description of the invention
Below in conjunction with specific embodiments and the drawings, the present invention is expanded on further.
Fig. 1 is yarn dyed fabric density measuring equipment, and it mainly includes 5 parts: 1, two symmetrically placed high resolution CCD
Camera, for gathering the front-back two-sided image of yarn dyed fabric;2, the sample holder of a set of autonomous Design, as in figure 2 it is shown, sample holder
Surface comprises four characteristic matching points for carrying out the para-position of front-back two-sided image and mating, and 24 colour standard color lumps be used for into
Row color of image is calibrated;Inside sample holder, symmetry fixes four rectangle magnetic stripes, keeps certain when making fabric sample held
Power.3, four standard light source symmetries are placed in the right and left of sample holder, are used for providing bilateral uniform irradiation.4, a closing
Camera bellows, for get rid of CCD camera gather image time ambient light impact.5, a data handling machine, for collection
Image process and analyze.
In the present embodiment, the resolution of CCD camera is 14,000,000 pixels.During use, utilize sample holder to clamp and knit
Thing is vertically placed on two camera centre positions, the most corresponding camera of fabric tow sides.Guarantee camera bellows does not has the external world
After light enters, opening four standard light sources, two cameras shoot simultaneously, can collect the image of fabric.
By arranging the calibration color lump of 24 colors in sample holder so that the present invention after collecting the image of fabric, energy
Enough according to calibration color lump, color is proofreaded, make the fabric color collected closer to real color, reduce and gather image
Aberration.
Present embodiment additionally provides the measuring method of a kind of yarn dyed fabric density, first with front-back two-sided image acquisition system
System gathers the front-back two-sided image of yarn dyed fabric, after extracting the subimage containing characteristic matching point, is mated by affine transformation
The front-back two-sided image completed, utilizes Wavelet Fusion algorithm to be merged by front-back two-sided image, then passes through fast Fourier
Conversion obtains the spectrogram of fusion image, utilizes the characteristic frequency peak dot in spectrogram to obtain the filling yarn image of reconstruct,
After calculate thread density.Concrete algorithm performs flow chart as shown in Figure 3.
After collecting the front-back two-sided image of fabric, extract the subimage containing matching characteristic point for front-back two-sided image
Para-position with mate,
Extract place, three limits of feature triangle straight line first with image segmentation and Sobel edge edge detective operators, utilize
After Radon transformation calculations goes out the linear equation on three limits, obtain its focus point coordinate by calculating triangular apex coordinate, will weight
The heart, as characteristic matching point, obtains the front-back two-sided image mated, it is achieved front-back two-sided image finally by affine transformation
The one_to_one corresponding of Pixel-level.After fabric positive and negative images match completes, Wavelet Fusion algorithm is utilized to be carried out by front-back two-sided image
Merge, strengthen the periodic structure information of yarn in image, measure for thread density.The mathematic(al) representation of wavelet transformation is such as
Under:
In formula: a is scale factor, b is translation vector.
Wavelet transformation is divided into continuous wavelet transform and wavelet transform.Owing to the digital signal of image is discrete type,
Therefore use discrete wavelet that image is carried out conversion process.Two dimension off-line wavelet transformation and inverse transformation expression formula thereof are as follows:
In formula: a is scale factor, b is translation vector.
Select to use double-deck wavelet transformation respectively fabric positive and negative image to be decomposed, its wavelet decomposition tree such as Fig. 4 institute
Show.Wherein, S is the textile image of input, and SA is the low frequency subgraph picture that ground floor wavelet decomposition obtains, and SH is horizontal high-frequent subgraph
Picture, SV is vertical high frequency subimage, and SD is diagonal angle high frequency subimage;SSA, SSH, SSV and SSD are respectively second layer wavelet decomposition
Low frequency subgraph is as corresponding four subimages of SA.
Assume that S1 represents the fabric face image mated, as shown in Figure 5;S2 represents the gray-scale map of verso images, as
Shown in Fig. 6.S represents fusion image, then front-back two-sided Image Fusion based on wavelet transformation is specific as follows, its flow process such as figure
Shown in 8:
(1) utilize double-deck wavelet transform to decompose fabric front-back two-sided image S1 and S2, obtain the son after it decomposes
Image.
(2) the horizontal high-frequent subimage that direct picture S1 and verso images S2 obtains after double-deck wavelet decomposition is extracted respectively
SSH1 and SSH2.In subimage, calculate the local variance amounting to 9 pixels centered by each pixel in 3x3 region
Value, it is assumed that DSSH1And DSSH2Represent the local variance value of calculated SSH1 and SSH2, then fusion image third layer level respectively
In high frequency subimage, the value of respective pixel point can obtain by below equation:
Wherein m, n represent the pixel count of horizontal direction and vertical direction successively.
(3) utilize the SSH, SSV and the SSD that calculate and SSA, obtain fusion image the by 2-d discrete wavelet inverse transformation
Two layers of low frequency subgraph are as SA.
(4) method identical with (2nd) step is used to calculate the horizontal high-frequent subimage of the fusion image second layer, vertical high frequency
Subimage SV and diagonal angle high frequency subimage SD.
(5) utilize SH, SV, SD and the SA calculated, finally give fusion image S by 2-d discrete wavelet inverse transformation,
As shown in Figure 7.
After being merged by front-back two-sided for fabric image by double-deck wavelet transformation, utilize two-dimensional fast fourier transform
(FFT) and inverse transformation (IFFT) technology obtains the spectrogram of fusion image, extract the cyclic component in spectrogram, finally record
Yarn dyed fabric filling yarn density.
Assume two-dimensional discrete function f (x, y) represents fusion image, then its Fourier transformation and inverse transformation expression formula are as follows:
In formula: u, v are frequency variable, u=0,1 ..., M-1, v=0,1 ..., N-1.Due to the digital signal of image be from
Dissipate type, therefore use discrete Fourier transform that image is processed.Two dimensional discrete Fourier transform and inverse transformation thereof are expressed
Formula is as follows:
In formula: u=0,1 ..., M-1, v=0,1 ..., N-1.When the data volume of picture is the biggest, discrete fourier becomes
The treatment effeciency of scaling method is relatively low.Therefore, the fast Fourier grown up on the basis of two dimensional discrete Fourier transform
Mapping algorithm is widely used in image processing field.
Utilize fast Fourier transform technology, woven fabric picture can be changed to frequency domain from transform of spatial domain, and obtain phase
The spectrogram answered.Peak dot in spectrogram represents the periodic structure information of fabric, two peaks on the horizontal line of initial point
Point correspond to warp thread periodical information, and two peak dots on the vertical line of initial point correspond to weft yarn periodical information.Elected
After determining the peak dot in both direction, filling yarn original image can be reconstructed by Fast Fourier Transform Inverse, such as Fig. 9 institute
Show: original fusion image S obtains fusion image spectrogram a, fusion image spectrogram a through Fourier transform and extracts level side
Peak dot figure c on peak dot figure b upwards and vertical direction, then peak dot figure reconstructs warp thread reconstruct figure by inverse fourier transform
D and weft yarn reconstruct figure e.Utilizing filling yarn reconstruct figure, can accurately calculate the thread density of fabric, computing formula is as follows:
In formula: R represents the resolution gathering image;Sw, ShBeing width and the height of original image respectively, unit is inch;
X, y are respectively original image pixel count both horizontally and vertically;dj, dwIt is respectively warp count and weft count.
The fabric warp density that this example finally records is 70.3 pieces/inch, and weft count is 51.6 pieces/inch, manually
What pick glass recorded is 70.1/ inch through weft count, and 50.9/ inch, both errors are only 0.28% and 1.37% respectively.
The respective embodiments described above are to realize the specific embodiment of the present invention, it will be understood by those skilled in the art that
And in actual applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
Claims (8)
1. the measuring method of a yarn dyed fabric density, it is characterised in that comprise the following steps: 1) by front-back two-sided for yarn dyed fabric image
Carry out image co-registration and obtain fusion image;2) fusion image is obtained spectrogram by Fourier transform, spectrogram is processed
To the filling yarn image of reconstruct, then calculate yarn dyed fabric density according to the filling yarn image of reconstruct.
The measuring method of yarn dyed fabric density the most according to claim 1, it is characterised in that: by front-back two-sided for yarn dyed fabric image
Complete images match by affine transformation, then utilize double-deck Wavelet Transform Fusion algorithm to obtain fusion image.
The measuring method of yarn dyed fabric density the most according to claim 2, it is characterised in that: described completed by affine transformation
Images match comprises the following steps:
A, image segmentation and Sobel edge edge detective operators is utilized to extract place, three limits of feature triangle straight line;
B, Radon transformation calculations is utilized to go out the linear equation on three limits;
C, calculating triangular apex coordinate obtain its focus point coordinate;
D, using center of gravity as characteristic matching point, obtained the front-back two-sided image mated by affine transformation.
4. according to the measuring method of the yarn dyed fabric density described in Claims 2 or 3, it is characterised in that:
Described double-deck wavelet image blending algorithm comprises the following steps: setting the S textile image as input, SA is that ground floor is little
The low frequency subgraph picture that Wave Decomposition obtains, SH is horizontal high-frequent subimage, and SV is vertical high frequency subimage, and SD is diagonal angle high frequency subgraph
Picture;SSA, SSH, SSV and SSD are respectively second layer wavelet decomposition low frequency subgraph as corresponding four subimages of SA;
A) double-deck wavelet decomposition fabric front-back two-sided image S1 and S2, the subimage after being decomposed are utilized;
B) the horizontal high-frequent subimage SSH1 that direct picture S1 and verso images S2 obtains after double-deck wavelet decomposition is extracted respectively
And SSH2;In horizontal high-frequent subimage, calculate the local amounting to 9 pixels centered by each pixel in 3x3 region
Variance yields, if DSSH1And DSSH2Represent the local variance value of calculated SSH1 and SSH2, then fusion image third layer water respectively
In flat high frequency subimage SSH, the value of respective pixel point can obtain by below equation:
Wherein, m representative picture horizontal direction pixel number, n represents vertical direction pixel number;
C) use and B) identical computational methods, utilize SSV1 and SSV2, SSA1 and SSA2, SSD1 and SSD2 can be merged
Image third layer vertical high frequency subimage SSV and diagonal angle high frequency subimage SSD and front low frequency subgraph are as SSA;
D) utilize SSH, SSV and the SSD calculated and SSA, obtain the fusion image second layer by 2-d discrete wavelet inverse transformation
Low frequency subgraph is as SA;
E) use and step B) to D) the horizontal high-frequent subimage SH of the identical method calculating fusion image second layer, vertical high frequency
Subimage SV and diagonal angle high frequency subimage SD;
F) utilize SH, SV, SD and the SA calculated, finally give fusion image S by 2-d discrete wavelet inverse transformation.
5. according to the measuring method of the yarn dyed fabric density described in claim 1 or 2 or 3, it is characterised in that: measure yarn dyed fabric density
Data handling procedure in, image obtains spectrogram by fast Fourier transform,
The characteristic frequency peak dot in spectrogram is utilized to obtain filling yarn reconstruct figure through Fourier inversion and calculate yarn
Density;The computing formula of thread density is:
Wherein, in formula: R represents the resolution gathering image;Sw, ShBeing width and the height of original image respectively, unit is English
Very little;X, y are respectively original image pixel count both horizontally and vertically;dj, dwIt is respectively warp count and weft count.
6. a yarn dyed fabric density measuring equipment for the measuring method of yarn dyed fabric density according to claim 1, its feature
Be: mainly include five parts: CCD camera, standard light source, with standard color block and the sample holder of characteristic matching point, envelope
Close camera bellows, data handling machine;
CCD camera, standard light source, sample holder with standard color block and characteristic matching point are placed in closing camera bellows;Sample presss from both sides
Tool is vertically placed on camera bellows bottom centerline;Yarn dyed fabric sample to be measured is positioned in sample holder;Standard light source is symmetrically placed
On yarn dyed fabric both sides;In the symmetrically placed CCD camera in yarn dyed fabric both sides;CCD camera is connected with data handling machine;
After opening standard light source, the CCD camera shooting front-back two-sided image of yarn dyed fabric, image information transmission is processed to data and calculates
Machine, computer completes yarn dyed fabric density measure.
Yarn dyed fabric density measuring equipment the most according to claim 6, it is characterised in that: sample holder includes mutually clamping
Two pieces of grip blocks, the surface of grip block is provided with 24 color calibration color lumps and para-position coupling triangle;By mutual between grip block
The magnet adsorption clamping joined.
Yarn dyed fabric density measuring equipment the most according to claim 6, it is characterised in that: yarn dyed fabric density measuring equipment is got the bid
Quasi-optical source is four, and symmetry is placed in the right and left of sample holder.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610504660.2A CN106127781A (en) | 2016-06-30 | 2016-06-30 | The measuring method of a kind of yarn dyed fabric density and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610504660.2A CN106127781A (en) | 2016-06-30 | 2016-06-30 | The measuring method of a kind of yarn dyed fabric density and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106127781A true CN106127781A (en) | 2016-11-16 |
Family
ID=57467869
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610504660.2A Pending CN106127781A (en) | 2016-06-30 | 2016-06-30 | The measuring method of a kind of yarn dyed fabric density and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106127781A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107655893A (en) * | 2017-11-15 | 2018-02-02 | 佛山鑫进科技有限公司 | A kind of Density COMPUTER DETECTION device |
CN110111287A (en) * | 2019-04-04 | 2019-08-09 | 上海工程技术大学 | A kind of fabric multi-angle image emerging system and its method |
CN112330673A (en) * | 2020-12-11 | 2021-02-05 | 武汉纺织大学 | Woven fabric density detection method based on image processing |
CN112630414A (en) * | 2020-12-30 | 2021-04-09 | 常州创度信息技术有限公司 | Fabric density measuring method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102288608A (en) * | 2011-06-20 | 2011-12-21 | 江南大学 | Novel method for automatically detecting density of woven fabric |
CN104346818A (en) * | 2014-10-27 | 2015-02-11 | 江南大学 | Automatic measurement method of woven fabric density |
-
2016
- 2016-06-30 CN CN201610504660.2A patent/CN106127781A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102288608A (en) * | 2011-06-20 | 2011-12-21 | 江南大学 | Novel method for automatically detecting density of woven fabric |
CN104346818A (en) * | 2014-10-27 | 2015-02-11 | 江南大学 | Automatic measurement method of woven fabric density |
Non-Patent Citations (4)
Title |
---|
RUI ZHANG 等: "An investigation of density measurement method for yarn-dyed woven fabrics based on dual-side fusion technique", 《MEASUREMENT SCIENCE AND TECHNOLOGY》 * |
张杰 等: "基于双面成像的色织物密度自动测量技术", 《河北科技大学学报》 * |
张杰: "基于双面成像技术的织物纹理与颜色特征分析", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
张瑞 等: "基于图像处理技术的织物组织识别研究现状", 《棉纺织技术》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107655893A (en) * | 2017-11-15 | 2018-02-02 | 佛山鑫进科技有限公司 | A kind of Density COMPUTER DETECTION device |
CN110111287A (en) * | 2019-04-04 | 2019-08-09 | 上海工程技术大学 | A kind of fabric multi-angle image emerging system and its method |
CN112330673A (en) * | 2020-12-11 | 2021-02-05 | 武汉纺织大学 | Woven fabric density detection method based on image processing |
CN112330673B (en) * | 2020-12-11 | 2021-07-06 | 武汉纺织大学 | Woven fabric density detection method based on image processing |
CN112630414A (en) * | 2020-12-30 | 2021-04-09 | 常州创度信息技术有限公司 | Fabric density measuring method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106127781A (en) | The measuring method of a kind of yarn dyed fabric density and device | |
WO2018028103A1 (en) | Unmanned aerial vehicle power line inspection method based on characteristics of human vision | |
Yin et al. | A novel image fusion algorithm based on nonsubsampled shearlet transform | |
CN104361314B (en) | Based on infrared and transformer localization method and device of visual image fusion | |
CN105147311B (en) | For the visualization device sub-scanning localization method and system in CT system | |
CN103414861B (en) | A kind of method of projector frame self-adaptive Geometry rectification | |
CN105654121A (en) | Complex jacquard fabric defect detection method based on deep learning | |
CN109887020B (en) | Plant organ separation method and system | |
CN103471523B (en) | A kind of detection method of arabidopsis profile phenotype | |
CN112733950A (en) | Power equipment fault diagnosis method based on combination of image fusion and target detection | |
CN106174830A (en) | Garment dimension automatic measurement system based on machine vision and measuring method thereof | |
CN102200433A (en) | Device and method for measuring leaf area based on computer vision | |
CN106485288A (en) | A kind of automatic identifying method of yarn dyed fabric tissue | |
CN105678767A (en) | SoC software and hardware collaborative design-based cloth surface blemish detection method | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
CN105184777A (en) | Painted design fabric defect detection method based on image decomposition | |
CN103454276A (en) | Textile form and style evaluation method based on dynamic sequence image | |
CN109255785A (en) | A kind of bearing open defect detection system | |
CN103591887B (en) | A kind of detection method of arabidopsis region phenotype | |
CN103593840B (en) | Method for detecting phenotype of Arabidopsis | |
CN105608674B (en) | A kind of image enchancing method based on image registration, interpolation and denoising | |
Hua et al. | Kinect-based real-time acquisition algorithm of crop growth depth images | |
CN210377552U (en) | Fruit is multiaspect image acquisition device for classification | |
CN202204479U (en) | Virtual optical extensometer | |
CN107341808A (en) | Simulative lunar soil hardness vision detection system and measuring method based on rut image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161116 |