CN108519066A - A kind of objective evaluation method of the fabric flatness based on four sidelight source images - Google Patents
A kind of objective evaluation method of the fabric flatness based on four sidelight source images Download PDFInfo
- Publication number
- CN108519066A CN108519066A CN201810613634.2A CN201810613634A CN108519066A CN 108519066 A CN108519066 A CN 108519066A CN 201810613634 A CN201810613634 A CN 201810613634A CN 108519066 A CN108519066 A CN 108519066A
- Authority
- CN
- China
- Prior art keywords
- similarity
- fabric
- grade
- feature
- fabric sample
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
- G01B11/303—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces using photoelectric detection means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention discloses a kind of objective evaluation methods of the fabric flatness based on four sidelight source images;Including step:Using identical four side light sources image collecting device, each grade stereoscopic plastic standard specimen and fabric sample to be evaluated are acquired, the data group of each acquisition target is respectively obtained;The each data group collected is pre-processed;Each data group after pretreatment is subjected to feature extraction, obtains the feature of plastics standard specimen or fabric sample;The feature extracted using each data group, while using the similarity evaluation model of design, fabric sample characteristics and each grade standard specimen characteristic similarity are calculated, it is to carry out objective evaluation according to the wrinkle grade to fabric sample with the similarity.The present invention has high accuracy of detection, has the characteristics that objective, stable, reproducible, automation.
Description
Technical field
The present invention relates to a kind of properties of textile test methods, particularly relate to a kind of fabric flatness based on image procossing
Assessment method.
Background technology
The daily process for washing shield and industrial washing of family leads to the change of its appearance features to the various influences of fabric generation,
Reduce its aesthetic feeling and use value.Therefore, maintain the evaluation of the performance of original appearance features in textile trade after being protected to fabric washing
Easily and in quality monitoring there is critical role.After evaluation to fabric flatness refers to washed to fabric and drying process, protect
The evaluation of its original flat very performance of appearance is held, the appearance after which protects fabric washing has great influence, is appearance of fabrics
With the important evaluation index of performance.Therefore, U.S. textile chemist has formulated relevant standard (such as with printing and dyeing Shi Xiehui
AATCC 124) to fabric flatness carry out standard division;It is flat that GB/T 13769 has also formulated the washed rear appearance of evaluation fabric
The test method of whole degree.In above-mentioned standard, the evaluation of fabric flatness, which depends under evaluating member observation caliber environment, knits
The appearance of object, and it is carried out with standard form to the subjective assessment of comparison completion.Such subjective method is dependent on evaluating member
The influence of physiology, psychology and environmental factor, precision is uncontrollable, can not reproduce.Although being still widely used in product examine of weaving at present
Survey field, but it is difficult to meet the demands such as the stabilization in practical application to fabric flatness evaluation method, reproducible, automation.Cause
This, needs the objective evaluation that flatness is carried out to fabric.
Invention content
The technical problem to be solved by the present invention is to propose a kind of stabilization, it is reproducible, automation based on four side light source figures
The objective evaluation method of the fabric flatness of picture.
The present invention uses following technical scheme to solve above-mentioned technical problem
A kind of objective evaluation method of the fabric flatness based on four sidelight source images, is as follows:
Step 1, it using identical four side light sources image collecting device, acquires each grade stereoscopic plastic standard specimen and waits for that evaluation is knitted
Object sample respectively obtains the data group of each acquisition target;
Step 2, each data group collected to step 1 pre-processes;
Step 3, feature extraction is carried out to each data group after pretreatment, obtains the spy of plastics standard specimen or fabric sample
Sign;
Step 4, the feature extracted using each data group, while using the similarity evaluation model of design, calculating is knitted
Object sample characteristics and each grade standard specimen characteristic similarity are to carry out visitor according to the wrinkle grade to fabric sample with the similarity
See evaluation.
As the present invention is based on the further preferred sides of the fabric smoothness objective-ranking method of four sidelight source images
Case, in step 1, the identical four side light sources image collecting device of the utilization acquires each grade stereoscopic plastic standard specimen and waits for
Fabric sample is evaluated, the data group of each acquisition target is respectively obtained, refers specifically to that acquisition target is positioned over Image Acquisition successively
On platform, it is separately turned on and is fixed on strip-shaped light source of the length of four side of acquisition platform more than pickup area, and utilize and be fixed on figure
As the CCD camera on acquisition platform holder, the gray level image for carrying out vertical direction to acquisition target respectively acquires, acquisition gained four
Width gray level image constitutes the data group of the acquisition target.
As the present invention is based on the further preferred sides of the fabric smoothness objective-ranking method of four sidelight source images
Case, it is in step 2, described to pre-process each data group collected, it is to four width figures in each data group
As data are pre-processed respectively, image data set after pretreatment is constituted, specifically, the pretreatment to each image data
It mainly includes the following steps that:
Step 2.1, noise reduction is carried out to greyscale image data using median filter to image data;
Step 2.2, using the image data after medium filtering, the mean value of its all pixels data is sought, medium filtering is obtained
The global mean value of image afterwards;
Step 2.3, using the image data after medium filtering, Two-Dimensional Quadratic fitting of a polynomial is carried out, and from fitting result
In subtract the global mean value of image after medium filtering, obtain the global illumination deviation of image;
Step 2.4, the global illumination deviation of gained image is subtracted from the image data after medium filtering, realizes image
Global illumination uniformity correction, obtain image data after pretreatment.
As the present invention is based on the further preferred sides of the fabric smoothness objective-ranking method of four sidelight source images
Case, described carries out feature extraction by each data group after pretreatment, obtains the feature of plastics standard specimen or fabric sample, is
Using the imaging features to fabric crease under side light source environment, to four width picture numbers in each data group after pretreatment
According to extraction fold sharpness distribution, collectively forms the feature of each data group, specifically, to each figure after pretreatment respectively
As the feature extraction of data mainly includes the following steps that:
Step 3.1, the marginal position in image data after pretreatment is positioned using Canny operators;
Step 3.2, using gained marginal position, the exhausted of greatest gradient of the image border point position on direction of illumination is calculated
To value, referred to as fold acutance;
Step 3.3, according to picture size, the frequency of certain amount maximum fold acutance Data-Statistics its each value before taking,
Referred to as fold sharpness distribution;
As the present invention is based on the further preferred sides of the fabric smoothness objective-ranking method of four sidelight source images
Case, the feature extracted using each data group, while using the similarity evaluation model of design, calculating fabric sample
Feature and each grade standard specimen characteristic similarity are to carry out objective comment according to the wrinkle grade to fabric sample with the similarity
It is fixed, specifically, to the feature that the data group of each fabric sample is extracted, the objective evaluation of wrinkle grade include mainly with
Lower step:
Step 4.1, each acutance in four fold sharpness distributions included in the feature using fabric sample point
Cloth calculates related coefficient with four fold sharpness distributions in the feature of six grade plastic standard specimens respectively, respectively constitutes a 6x4
Similarity matrix, elements A i, j represent the jth of the sharpness distribution of fabric sample and the plastics standard specimen of i-th of grade in matrix
The related coefficient of a sharpness distribution can obtain four similarity matrixs for each fabric sample;
Step 4.2, four similarity matrixs obtained by the feature using each fabric sample, to the every of each similarity matrix
A line maximizing obtains the unilateral similarity vector of four 6 dimensions, and element Bi represents the fabric corresponding to the vector in each vector
Fold sharpness distribution and i-th of grade four fold sharpness distributions of plastics standard specimen maximum similarity, for each fabric
Sample can obtain four unilateral similarity vectors;
Step 4.3, it is summed it up using four unilateral similarity vectors of gained, obtains total similarity vector of one 6 dimensions, element vector
Plain Ci represents total similarity of fabric sample and the plastics standard specimen of i-th of grade;
Step 4.4, using total similarity vector of gained, dimension where its maximum value, the corresponding plastics mark of the dimension are taken
Sample grade is the objective evaluation grade of fabric sample.
The present invention has the following technical effects using above technical scheme is compared with the prior art:
The present invention is directed to the shortcomings of existing fabric testing flatness method subjectivity is strong, stability is poor, repeatable difference,
The objective evaluation method for proposing the fabric flatness based on four sidelight source images reduces evaluating member physiology, psychology and objective
Influence of the factors such as environment to evaluation result, the objective stabilization of evaluation result can evaluate the flat of different fabric samples true and reliablely
Whole degree.
Description of the drawings
Fig. 1 is the objective evaluation method flow schematic diagram of the fabric flatness based on four sidelight source images of the present invention;
Fig. 2 is the greyscale image data that the side light source of 1 plastics standard specimens of DP collects, and light source is located at image acquisition region
Upside;
Fig. 3 is the Canny edge detection schematic diagrames of image in Fig. 2;
Fig. 4 is the fold sharpness distribution histogram of Fig. 1;
Fig. 5 is total similarity vector schematic diagram of test fabric sample.
Specific implementation mode
Technical scheme of the present invention is described in further detail below in conjunction with the accompanying drawings:
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
The present invention provides a kind of objective evaluation method of the fabric flatness based on four sidelight source images, feature exists
In this method is as follows:
Step 1, it using identical four side light sources image collecting device, acquires each grade stereoscopic plastic standard specimen and waits for that evaluation is knitted
Object sample respectively obtains the data group of each acquisition target;
Step 2, each data group collected to step 1 pre-processes;
Step 3, feature extraction is carried out to each data group after pretreatment, obtains the spy of plastics standard specimen or fabric sample
Sign;
Step 4, the feature extracted using each data group, while using the similarity evaluation model of design, calculating is knitted
Object sample characteristics and each grade standard specimen characteristic similarity are to carry out visitor according to the wrinkle grade to fabric sample with the similarity
See evaluation.
As a preferred embodiment, it is that the fabric based on four sidelight source images of the preferred embodiment of the present invention is smooth with reference to figure 1
The objective evaluation method flow diagram of degree.
The method of the present embodiment includes the following steps:
Step 1:Using identical four side light sources image collecting device, acquires each grade stereoscopic plastic standard specimen and wait for that evaluation is knitted
Object sample respectively obtains the data group of each acquisition target in this step, acquisition target be all plastics standard specimens and, fabric sample
This.Plastics standard specimen shares 6, DP 1, DP 2, DP 3, DP 3.5, DP 4, the DP 5 of respectively GB/T 13769 offers, by suitable
Sequence is defined as the plastics standard specimen of the 1st to the 6th grade.Fabric sample shares 1 piece.The size of acquisition platform is 40cm × 40cm,
Four side light sources are that size is 60cm × 5cm, are individually fixed at the outside 15cm at four edge of acquisition platform, with acquisition platform
Sides aligned parallel.CCD camera model Canon EOS 200D are placed in right over acquisition platform center at 50cm, vertically flat to acquisition
Platform carry out greyscale image data acquisition, pickup area actual size be 20cm × 30cm, acquisition image data for 648 pixels ×
432 pixels, gray value interval are [0,255].Entire harvester is placed in a darkroom.
By above-mentioned apparatus, to all acquisition targets, including 6 plastics standard specimens and 1 piece of sample cloth, four bats are carried out respectively
It takes the photograph.In above-mentioned four shootings, shooting every time is separately turned on the light source of four sides, obtains the gray-scale map that four width correspond to different side light sources
Picture constitutes the data group of acquisition target.It is the greyscale image data that the side light source of 1 plastics standard specimens of DP collects with reference to figure 2,
Light source is located at the upside of image acquisition region.
Step 2:The each data group collected is pre-processed
In this step, four width image datas in each data group are pre-processed respectively, are constituted after pretreatment
Image data set specifically the pretreatment of each image data is mainly included the following steps that:
Step 2.1, if image data is matrix I, image data carries out greyscale image data using median filter
Noise reduction, it is preferred that it is 3 × 3 to select filter size, and filtered image is matrix Im.
Step 2.2, using the image data after medium filtering, the mean value of its all pixels data is sought, medium filtering is obtained
The global mean value of image afterwards, it is m to enable the overall situation mean value;
Step 2.3, using the image data after medium filtering, Two-Dimensional Quadratic fitting of a polynomial, acquired results one are carried out
With the matrix F of original image I equidimensions, and after subtracting medium filtering in fitting result image global mean value m, obtain image
Global illumination deviation D, is shown below:
D=F-m
Step 2.4, the global illumination deviation D of gained image is subtracted from the image data Im after medium filtering, is realized
The global illumination uniformity of image is corrected, and is obtained image data Ip after pretreatment, is shown below:
Ip=Im-D
Step 3:Each data group after pretreatment is subjected to feature extraction, obtains the spy of plastics standard specimen or fabric sample
Sign
In this step, using the imaging features to fabric crease under side light source environment, to each after pretreatment
Four width image datas in data group extract fold sharpness distribution, collectively form the feature of each data group respectively, specifically,
The feature extraction of each image data after pretreatment is mainly included the following steps that:
Step 3.1, the marginal position in image data after pretreatment is positioned using Canny operators, it is preferred that respectively
It is respectively 0.1 and 0.05 to take lower threshold value on Canny operators, and it is 1 to take filter variance, is the Canny of image in Fig. 2 with reference to figure 3
Edge detection schematic diagram;
Step 3.2, using gained marginal position, the exhausted of greatest gradient of the image border point position on direction of illumination is calculated
To value, referred to as fold acutance.The zoning size of the absolute value of above-mentioned greatest gradient, it is preferred that when direction of illumination is image
When vertical direction, 5 × 1 are taken as, when direction of illumination is image level direction, is taken as 1 × 5;
Step 3.3, according to the pixel of 648 pixel of picture size × 432, n maximum fold acutancees count it and respectively take before taking
The frequency H of value is the vector that dimension is 256, referred to as fold sharpness distribution.Preferably, above-mentioned selection number n takes 3240, by
Following formula acquires:
N=α × (h × w)
Wherein, h, w are respectively the pixels tall and width of image, and ɑ is figure parameters, it is preferred that value 3.Reference chart
4, it is the fold sharpness distribution histogram of Fig. 1.
Step 4:The feature extracted using each data group, while using the similarity evaluation model of design, calculating is knitted
Object sample characteristics and each grade standard specimen characteristic similarity are to carry out visitor according to the wrinkle grade to fabric sample with the similarity
See evaluation
In this step, to the feature that the data group of each fabric sample is extracted, the objective evaluation of wrinkle grade
It mainly includes the following steps that:
Step 4.1, each acutance in four fold sharpness distributions included in the feature using fabric sample point
Cloth calculates related coefficient with four fold sharpness distributions in the feature of six grade plastic standard specimens respectively, respectively constitutes a 6x4
Similarity matrix A, elements A in matrixi,jRepresent the jth of the sharpness distribution of fabric sample and the plastics standard specimen of i-th of grade
The related coefficient of a fold sharpness distribution can obtain four similarity matrixs for each fabric sample;Specifically, matrix A can be by
Following formula acquires:
AI, j=cov (HmI, j, H) and i=1,2,3...6j=1,2,3,4
Wherein, Hmi,jFor j-th of fold sharpness distribution of the plastics standard specimen of i-th of grade, H is four pleats of fabric sample
Wrinkle sharpness distribution in any one, cov () be correlation coefficient function.
Step 4.2, four similarity matrixs obtained by the feature using each fabric sample, to the every of each similarity matrix
A line maximizing, obtain four 6 dimension unilateral similarity vector B, it is each vector in element BiRepresent knitting corresponding to the vector
The maximum similarity of the fold sharpness distribution of object and four fold sharpness distributions of plastics standard specimen of i-th of grade, is knitted for each
Object sample can obtain four unilateral similarity vectors;To any one unilateral similarity vector B, calculating can be by following equation table
It reaches:
Step 4.3, (3) utilize four unilateral similarity vectors of gained to sum it up, and obtain total similarity vector of one 6 dimensions, to
Secondary element CiRepresent total similarity of fabric sample and the plastics standard specimen of i-th of grade;Its calculation formula is as follows:
Wherein,For j-th of fabric sample and the unilateral similarity vector of plastics standard specimen, and the plastics standard specimen is i-th
The plastics standard specimen of a grade.
Step 4.4, using total similarity vector of gained, dimension where its maximum value, the corresponding plastics mark of the dimension are taken
Sample grade is the objective evaluation grade of fabric sample.It is total similarity vector schematic diagram of test fabric sample with reference to figure 5,
Understand that the fabric sample belongs to grade DP 2.
Those of ordinary skills in the art should understand that:The above is only a specific embodiment of the present invention, and
It is not used in the limitation present invention, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done,
It should be included within protection scope of the present invention.
Claims (5)
1. a kind of objective evaluation method of the fabric flatness based on four sidelight source images, which is characterized in that be as follows:
Step 1, using identical four side light sources image collecting device, each grade stereoscopic plastic standard specimen and fabric sample to be evaluated are acquired
This, respectively obtains the data group of each acquisition target;
Step 2, each data group collected to step 1 pre-processes;
Step 3, feature extraction is carried out to each data group after pretreatment, obtains the feature of plastics standard specimen or fabric sample;
Step 4, the feature extracted using each data group, while using the similarity evaluation model of design, calculating fabric sample
Eigen and each grade standard specimen characteristic similarity are to carry out objective comment according to the wrinkle grade to fabric sample with the similarity
It is fixed.
2. the fabric smoothness objective-ranking method according to claim 1 based on four sidelight source images, feature
Be, in step 1, the identical four side light sources image collecting device of the utilization, acquire each grade stereoscopic plastic standard specimen and
Fabric sample to be evaluated, respectively obtains the data group of each acquisition target, refers specifically to that acquisition target is positioned over image and is adopted successively
Collect on platform, is separately turned on and is fixed on strip-shaped light source of the length of four side of acquisition platform more than pickup area, and utilize and be fixed on
CCD camera on Image-capturing platform holder, the gray level image for carrying out vertical direction to acquisition target respectively acquire, acquisition gained
Four width gray level images constitute the data group of the acquisition target.
3. the fabric smoothness objective-ranking method according to claim 1 based on four sidelight source images, feature
It is:In step 2, described to pre-process each data group collected, it is to four width in each data group
Image data is pre-processed respectively, constitutes image data set after pretreatment, specifically, to the pre- place of each image data
Reason mainly includes the following steps that:
Step 2.1, noise reduction is carried out to greyscale image data using median filter to image data;
Step 2.2, using the image data after medium filtering, the mean value of its all pixels data is sought, is schemed after obtaining medium filtering
The global mean value of picture;
Step 2.3, using the image data after medium filtering, Two-Dimensional Quadratic fitting of a polynomial is carried out, and subtract from fitting result
The global mean value for removing image after medium filtering, obtains the global illumination deviation of image;
Step 2.4, the global illumination deviation of gained image is subtracted from the image data after medium filtering, realizes the whole of image
Body illumination uniformity is corrected, and image data after pretreatment is obtained.
4. the fabric smoothness objective-ranking method according to claim 1 based on four sidelight source images, feature
It is, described carries out feature extraction by each data group after pretreatment, obtains the feature of plastics standard specimen or fabric sample,
It is using the imaging features to fabric crease under side light source environment, to four width images in each data group after pretreatment
Data extract fold sharpness distribution, the feature of each data group are collectively formed, specifically, to each after pretreatment respectively
The feature extraction of image data mainly includes the following steps that:
Step 3.1, the marginal position in image data after pretreatment is positioned using Canny operators;
Step 3.2, using gained marginal position, the absolute of greatest gradient of the image border point position on direction of illumination is calculated
Value, referred to as fold acutance;
Step 3.3, according to picture size, the frequency of a certain number of its each value of maximum fold acutance Data-Statistics before taking, referred to as
Fold sharpness distribution.
5. the fabric smoothness objective-ranking method according to claim 1 based on four sidelight source images, feature
It is, the feature extracted using each data group, while using the similarity evaluation model of design, calculates fabric sample
Eigen and each grade standard specimen characteristic similarity are to carry out objective comment according to the wrinkle grade to fabric sample with the similarity
It is fixed, specifically, to the feature that the data group of each fabric sample is extracted, the objective evaluation of wrinkle grade include mainly with
Lower step:
Step 4.1, each sharpness distribution in four fold sharpness distributions included in the feature using fabric sample, point
Related coefficient is not calculated with four fold sharpness distributions in the feature of six grade plastic standard specimens, respectively constitutes the phase of a 6x4
Like degree matrix, elements A i in matrix, j represent the sharpness distribution of fabric sample and the plastics standard specimen of i-th of grade j-th are sharp
The related coefficient of degree distribution can obtain four similarity matrixs for each fabric sample;
Step 4.2, four similarity matrixs obtained by the feature using each fabric sample, to every a line of each similarity matrix
Maximizing obtains the unilateral similarity vectors of four 6 dimensions, and element Bi represents the pleat of the fabric corresponding to the vector in each vector
The maximum similarity of the four fold sharpness distributions of plastics standard specimen for sharpness distribution and i-th of the grade of wrinkling, for each fabric sample,
Four unilateral similarity vectors can be obtained;
Step 4.3, it is summed it up using four unilateral similarity vectors of gained, obtains total similarity vector of one 6 dimensions, vector element Ci
Represent total similarity of fabric sample and the plastics standard specimen of i-th of grade;
Step 4.4, using total similarity vector of gained, dimension where its maximum value, corresponding plastics standard specimen of the dimension etc. are taken
Grade is the objective evaluation grade of fabric sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810613634.2A CN108519066B (en) | 2018-06-14 | 2018-06-14 | Method for objectively evaluating fabric flatness based on four-side light source image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810613634.2A CN108519066B (en) | 2018-06-14 | 2018-06-14 | Method for objectively evaluating fabric flatness based on four-side light source image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108519066A true CN108519066A (en) | 2018-09-11 |
CN108519066B CN108519066B (en) | 2020-04-28 |
Family
ID=63427540
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810613634.2A Active CN108519066B (en) | 2018-06-14 | 2018-06-14 | Method for objectively evaluating fabric flatness based on four-side light source image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108519066B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109238182A (en) * | 2018-10-08 | 2019-01-18 | 江南大学 | A kind of objective ranking method of fabric flatness based on Fourier spectrum feature |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100335876B1 (en) * | 1999-11-08 | 2002-05-10 | 김혜정 | Wrinkle/seam pucker analyzer for textile fabric |
CN1519556A (en) * | 2003-01-23 | 2004-08-11 | 友达光电股份有限公司 | Method for analyzing roughness on surface of film |
CN1523352A (en) * | 2003-09-12 | 2004-08-25 | 东华大学 | Fabric planeness gradation objective evaluation method |
CN1534294A (en) * | 2002-06-06 | 2004-10-06 | 香港理工大学 | Textile surface analysis method and its system |
CN1971274A (en) * | 2006-12-08 | 2007-05-30 | 东华大学 | Method for assessing smoothness level of dress material based on point model |
CN101706443A (en) * | 2009-03-27 | 2010-05-12 | 上海工程技术大学 | Smoothness evaluation method of seams of clothing fabrics |
CN104616291A (en) * | 2015-01-15 | 2015-05-13 | 东华大学 | Sparse coding-based fabric appearance flatness evaluation method |
CN104794684A (en) * | 2014-01-17 | 2015-07-22 | 复旦大学 | Automatic plaque assay method based on virus plaque image |
CN105258656A (en) * | 2015-10-27 | 2016-01-20 | 浙江理工大学 | Washed fabric twisted flatness testing device and method |
CN106529544A (en) * | 2016-10-31 | 2017-03-22 | 中山大学 | Fabric flatness objective evaluation method and fabric flatness objective evaluation device based on unsupervised machine learning |
-
2018
- 2018-06-14 CN CN201810613634.2A patent/CN108519066B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100335876B1 (en) * | 1999-11-08 | 2002-05-10 | 김혜정 | Wrinkle/seam pucker analyzer for textile fabric |
CN1534294A (en) * | 2002-06-06 | 2004-10-06 | 香港理工大学 | Textile surface analysis method and its system |
CN1519556A (en) * | 2003-01-23 | 2004-08-11 | 友达光电股份有限公司 | Method for analyzing roughness on surface of film |
CN1523352A (en) * | 2003-09-12 | 2004-08-25 | 东华大学 | Fabric planeness gradation objective evaluation method |
CN1971274A (en) * | 2006-12-08 | 2007-05-30 | 东华大学 | Method for assessing smoothness level of dress material based on point model |
CN101706443A (en) * | 2009-03-27 | 2010-05-12 | 上海工程技术大学 | Smoothness evaluation method of seams of clothing fabrics |
CN104794684A (en) * | 2014-01-17 | 2015-07-22 | 复旦大学 | Automatic plaque assay method based on virus plaque image |
CN104616291A (en) * | 2015-01-15 | 2015-05-13 | 东华大学 | Sparse coding-based fabric appearance flatness evaluation method |
CN105258656A (en) * | 2015-10-27 | 2016-01-20 | 浙江理工大学 | Washed fabric twisted flatness testing device and method |
CN106529544A (en) * | 2016-10-31 | 2017-03-22 | 中山大学 | Fabric flatness objective evaluation method and fabric flatness objective evaluation device based on unsupervised machine learning |
Non-Patent Citations (1)
Title |
---|
董长虹: "《Matlab图像处理与应用》", 31 January 2004 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109238182A (en) * | 2018-10-08 | 2019-01-18 | 江南大学 | A kind of objective ranking method of fabric flatness based on Fourier spectrum feature |
CN109238182B (en) * | 2018-10-08 | 2020-05-12 | 江南大学 | Fourier spectrum characteristic-based objective fabric flatness rating method |
Also Published As
Publication number | Publication date |
---|---|
CN108519066B (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106030653B (en) | For generating the image processing system and image processing method of high dynamic range images | |
CN109285194B (en) | Camera calibration board and camera calibration data acquisition method | |
CN106204509B (en) | Infrared and visible light image fusion method based on regional characteristics | |
CN104715477B (en) | The image analysis method of woven fabric count based on multiple dimensioned and multizone | |
CN103345617B (en) | Chinese medicine knows method for distinguishing and system thereof | |
CN106680086A (en) | Video extensometer applied to high-speed tensile experiment of plastic material | |
JP2010045613A (en) | Image identifying method and imaging device | |
CN109938737A (en) | A kind of human body body type measurement method and device based on deep learning critical point detection | |
CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
CN110268420A (en) | In the picture detect background objects on exotic computer implemented method, in the picture detect background objects on exotic equipment and computer program product | |
CN108519066A (en) | A kind of objective evaluation method of the fabric flatness based on four sidelight source images | |
CN111627043A (en) | Simple human body curve acquisition method based on marker and feature filter | |
CN106997583A (en) | A kind of underwater robot adaptive image enhancement and feature extracting method | |
Honda et al. | Make my day-high-fidelity color denoising with near-infrared | |
Bevilacqua et al. | Vignetting correction by exploiting an optical microscopy image sequence | |
CN104992426B (en) | A kind of multi-layer image blending algorithm for light field micro-imaging | |
CN106127781A (en) | The measuring method of a kind of yarn dyed fabric density and device | |
CN111272673A (en) | Non-pure-color cloth color difference detection system and detection method | |
CN110245575B (en) | Human body type parameter capturing method based on human body contour line | |
CN111044517A (en) | Three-dimensional feature-based fabric fold grade evaluation method | |
CN108734674B (en) | OCT image blind restoration method for improving NAS-RIF | |
CN111640144A (en) | Multi-view jacquard fabric pattern segmentation algorithm | |
Tawheed | Recording and Documentation of Historical Textiles and Their Role in Conservation and Sustainability Processes | |
Wang et al. | Identification and extraction of circular markers in 3D reconstruction | |
Billingsley | Digital image processing for information extraction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |