CN102830045A - Fabric spray rating objective evaluating method based on image processing - Google Patents
Fabric spray rating objective evaluating method based on image processing Download PDFInfo
- Publication number
- CN102830045A CN102830045A CN2012102625145A CN201210262514A CN102830045A CN 102830045 A CN102830045 A CN 102830045A CN 2012102625145 A CN2012102625145 A CN 2012102625145A CN 201210262514 A CN201210262514 A CN 201210262514A CN 102830045 A CN102830045 A CN 102830045A
- Authority
- CN
- China
- Prior art keywords
- fabric
- image
- spray
- grade
- area ratio
- 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
Images
Landscapes
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to a fabric spray rating objective evaluating method based on image processing. The existing method is not ideal in evaluation result and poorer in consistency, and meanwhile larger evaluation errors can be resulted from fatigue. The method comprises the following steps: firstly carrying out a fabric spraying ability experiment to obtain a fabric spraying image and carrying out preprocessing on the image; secondly carrying out boundary detection, morphology processing and extracting and calculating the area of a circular detection region; subsequently calculating moist area, and calculating a fabric moist area ratio; and finally determining demarcation values of six spray ratings of the fabric in an AATCC (American association of textile chemists and colorists) fabric spray standard picture, and determining the spray rating of the fabric according to the moist area ratio and spray rating boundary lines. The influence of mental and environmental factors and the like to judgment results is reduced, so that the method is relatively more objective.
Description
Technical field
The invention belongs to textile garment performance test field, relate in particular to a kind of method that fabric spray rating is evaluated.
Background technology
The getting wet property of fabric (also claiming water repellency) is meant that under the artificial rainer of appointment fabric is resisted the ability that drinks up the rain through the stipulated time.When fabric was got wet performance rating, traditional assessment method was that evaluation person comes contrast test lining and standard model photo to reach a conclusion through human eye under certain illumination condition.This method can receive evaluation person's physiology, psychology and influence from social surroundings, often causes evaluation result undesirable, and consistance is relatively poor, can produce bigger evaluated error because of fatigue simultaneously.
Summary of the invention
The objective of the invention is to problem to existence in the above fabric spray rating evaluation; Propose a kind of simple to operate, utilization computer image processing technology and fabric spray rating is carried out the method for objective evaluation; To replace the artificial visually examine, realize quick, easy, objective spray rating evaluation.
The inventive method is specifically:
Step 1. is carried out the experiment of getting wet property of fabric according to U.S. textile chemist and printing and dyeing teacher association criterion AATCC22-2005 " textile water repellency test spray process ", and obtains the fabric image that gets wet.
The step 2. pair fabric image that gets wet carries out the pre-service of gray processing, histogram equalization and medium filtering.
The step 3. pair pretreated fabric image that gets wet carries out rim detection with the roberts operator, expands then, the morphology of burn into refinement handles.
Step 4. morphology extracts and obtains circular detection zone area after handling.
The step 5. pair pretreated fabric image that gets wet carries out rim detection with the canny operator to humidification zones.
Step 6. is extracted the circular detection zone after the rim detection with Photoshop, negates to confirming fabric behind the circular detection zone image that gets wet, and obtains wetted area after the corrosion treatment.
Step 7. is calculated fabric wetted area ratio according to wetted area and circular detection zone area.
Step 8. is calculated the wetted area ratio of 6 spray ratings in getting wet property of the AATCC fabric standard photographs with above step.
Step 9. is confirmed the cut off value of 6 spray ratings of fabric, with 0 grade and 1 grade be example, establish cut off value and do
X 0: the cut off value that obtains 0 grade and 1 grade according to computes
X 0
Wherein,
R 0It is the wetted area ratio of 0 grade standard appearance photograph;
R 1It is the wetted area ratio of 1 grade standard appearance photograph.
Step 10. is confirmed the spray rating of fabric according to wetted area ratio and spray rating separatrix.
Beneficial effect of the present invention: compare traditional naked eyes subjective determination, reduced the influence to result of determination such as psychology, environmental factor based on the method for objectively evaluating of Flame Image Process, therefore more objective comparatively speaking; Aspect judgement efficient, subjective determination can produce visual fatigue because of working long hours of people, and Computer Processing then frees the people from continue contrast, so assess effectiveness is higher.
Description of drawings
Fig. 1 is the get wet preprocessing process of image of fabric;
Fig. 2 is the image processing process of circular surveyed area;
Fig. 3 is the processing procedure of humidification zones;
Fig. 4 shines for getting wet property of AATCC fabric grade evaluation standard sample.
Embodiment
Below in conjunction with accompanying drawing the present invention is described further.
The implementation step of the inventive method is:
1. carry out the experiment of getting wet property of fabric according to U.S. textile chemist and printing and dyeing teacher association criterion AATCC22-2005 " textile water repellency test spray process ", and obtain the fabric image that gets wet with digital camera.
2. pre-service: the fabric image that gets wet is carried out the pre-service of coloured image gray processing, histogram equalization and medium filtering, like Fig. 1 (a) and (b), (c).
(1) coloured image gray processing: the image that obtains from digital camera is colored RGB image, at first converts thereof into gray level image.
Conversion formula is:
; Gray (i wherein; J) for the conversion after black white image at (i; J) gray-scale value at some place, R, G, B are respectively redness, green and blue sub value.
(2) histogram equalization: the gradation of image scope behind the gray processing is too little, contrasts not obviously, in order to strengthen the contrast of gray level image, gray level image is carried out histogram equalization handle.Its calculation procedure is following:
1. list the gray level of original image
,
I=0,1 ..., k ... L-1, wherein L is the number of gray level;
2. add up the number of pixels of each gray level
,
I=0,1 ..., k ... L-1
3. calculate the frequency of each gray level of original image histogram
Wherein
nBe the total number of pixels of original image;
4. calculate cumulative distribution function
;
5. use the gray level that following formula calculates the output image after shining upon
Number for output gray level:
, wherein,
INTFor rounding symbol;
6. statistics is shone upon the number of pixels
of back gray levels at different levels;
7. calculate output image histogram
;
8. use the mapping relations of
and
to revise the gray level of original image, be approximately equally distributed output image thereby obtain histogram.
(3) denoising: in order to remove high frequency noise, topography is carried out smoothing processing, the median filter of selection 3 * 3 is handled histogram-equalized image.Job step is following:
1. template is roamed in image, and certain location of pixels in template center and the image is overlapped;
2. read the gray-scale value of each respective pixel under the template;
3. these gray-scale values are formed a line from small to large;
4. find out in the middle of coming in these values;
5. this intermediate value is composed the pixel to the corresponding templates center.
3. get wet circular detection zone rim detection and area of fabric extracts
(1) the pretreated fabric image that gets wet is carried out rim detection with the roberts operator, like Fig. 2 (a).
Rim detection is for target is identified from background.Basic thought is to utilize the edge to strengthen operator, gives prominence to the local edge in the image, defines " edge strength " of pixel then, extracts the edge point set through the method that threshold values is set.The roberts operator is a kind of operator that utilizes local difference operator to seek the edge, and this operator only uses 2 * 2 neighborhoods of current pixel, and expression formula is:
(2) to roberts operator edge detection image expand, the morphology of corrosion and refinement handles, and sees Fig. 2 (b), (c), (d) respectively.
Expand: because detected marginal existence is discontinuous and be not single pixel phenomenon, couple together in order to make discontinuous edge, present embodiment adopts 3 * 3 decussate texture element to carry out expansion process.A is expanded to
with the B structural element, and its meaning is:
Corrosion:, the image after the expansion is corroded operation in order to remove a little or noise such as short-term.
AUse
BThe structural element corrosion does
, its meaning is:
Refinement:, the image after the corrosion is carried out micronization processes again in order to make the edge unit picture elementization.Its algorithm is:
1. distribute with image memory headroom of a size, zero clearing is used for calculating;
2. scan entire image,, judge whether (8 directions) all is impact point around it if run into impact point (white point); If not; The counter of corresponding point position is constant, but (8 directions) all is impact point on every side, and the counter of corresponding point position adds 1;
3. single pass is that point on the zero corresponding original image becomes background (black) with counter after intact;
4. multiple scanning does not always all change to the pixel of original image;
5. releasing memory space.
(3) area of circular surveyed area extracts: according to AATCC (U.S. textile chemist and printing and dyeing Shi Xiehui) examination criteria; The edge of surveyed area is circular metal frame; So come the circular surveyed area of rapid extraction by the Magnetic Lasso Tool in the Photoshop image processing software,, then circle contour carried out complementary operation like Fig. 2 (e); Like Fig. 2 (f), obtain circular surveyed area area again
S 2
4. the get wet detection of humidification zones and the extraction of wetted area of fabric
(1) with the canny operator pretreated image is carried out hygrometric profit edges of regions and detect, like Fig. 3 (a), the process of canny operator edge detection algorithm:
1. gaussian filtering smoothed image;
2. utilize the amplitude and the direction of differentiating operator compute gradient;
3. gradient magnitude being used non-maximum value suppresses;
4. adopt " dual threshold " method to detect and adjoining edge.
(2) extract circular surveyed area with Photoshop, negate then and corrosion treatment, ask wetted area at last
S 1Circular detection zone extracts sees Fig. 3 (b), negates and sees Fig. 3 (c), and Fig. 3 (d) is seen in corrosion.
5. the calculating of wetted area ratio
According to wetted area
S 1With the surveyed area area
S 2, compare R according to computes fabric wetted area.
6. fabric spray rating objective evaluation
(1) standard specimen with getting wet property of AATCC fabric grade evaluation carries out IMAQ with scanner, and is as shown in Figure 4, extracts the wetted area ratio of 6 spray ratings in the standard specimen then in order to the step of epigraph processing and feature extraction, is respectively
R 0,
R 1,
R 2,
R 3,
R 4,
R 5
(2) calculate the separatrix that fabric spray rating is divided, with 0 grade and 1 grade be example, establish cut off value and do
X 0: obtain according to computes
X 0,
In like manner try to achieve 1 grade with 2 grades cut off value
X 12 grades with 3 grades cut off value
X 23 grades with 4 grades cut off value
X 34 grades with 5 grades cut off value
X 4
(3) according to the wetted area ratio
RWith the spray rating separatrix, confirm fabric spray rating.
If
X 0≤
R, then fabric spray rating is 0 grade;
If
X 1≤
R＜
X 0, then fabric spray rating is 1 grade;
If
X 2≤
R＜
X 1, then fabric spray rating is 2 grades;
If
X 3≤
R＜
X 2, then fabric spray rating is 3 grades;
If
X 4≤
R＜
X 3, then fabric spray rating is 4 grades;
If
R＜X
4, then fabric spray rating is 5 grades.
Being merely preferred embodiment of the present invention in sum, is not to be used for limiting practical range of the present invention.Be that all equivalences of doing according to the content of claim of the present invention change and revision, be technological category of the present invention.
Claims (1)
1. based on the fabric spray rating objective evaluation method of Flame Image Process, it is characterized in that this method may further comprise the steps:
Step 1. is carried out the experiment of getting wet property of fabric according to U.S. textile chemist and printing and dyeing teacher association criterion AATCC22-2005 " textile water repellency test spray process ", and obtains the fabric image that gets wet;
The step 2. pair fabric image that gets wet carries out the pre-service of gray processing, histogram equalization and medium filtering;
The step 3. pair pretreated fabric image that gets wet carries out rim detection with the roberts operator, expands then, the morphology of burn into refinement handles;
Step 4. morphology extracts and obtains circular detection zone area after handling;
The step 5. pair pretreated fabric image that gets wet carries out rim detection with the canny operator to humidification zones;
Step 6. is extracted the circular detection zone after the rim detection with Photoshop, negates to confirming fabric behind the circular detection zone image that gets wet, and obtains wetted area after the corrosion treatment;
Step 7. is calculated fabric wetted area ratio according to wetted area and circular detection zone area;
Step 8. is calculated the wetted area ratio of 6 spray ratings in getting wet property of the AATCC fabric standard photographs with above step;
Step 9. is confirmed the cut off value of 6 spray ratings of fabric, with 0 grade and 1 grade be example, establish cut off value and do
X 0: the cut off value that obtains 0 grade and 1 grade according to computes
X 0
Wherein,
R 0It is the wetted area ratio of 0 grade standard appearance photograph;
R 1It is the wetted area ratio of 1 grade standard appearance photograph;
Step 10. is confirmed the spray rating of fabric according to wetted area ratio and spray rating separatrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102625145A CN102830045A (en) | 2012-07-26 | 2012-07-26 | Fabric spray rating objective evaluating method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102625145A CN102830045A (en) | 2012-07-26 | 2012-07-26 | Fabric spray rating objective evaluating method based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102830045A true CN102830045A (en) | 2012-12-19 |
Family
ID=47333258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102625145A Pending CN102830045A (en) | 2012-07-26 | 2012-07-26 | Fabric spray rating objective evaluating method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102830045A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392441A (en) * | 2014-11-18 | 2015-03-04 | 浙江理工大学 | Method for detecting and evaluating spray rating of high anti-noise fabric based on image processing |
| JP2017194389A (en) * | 2016-04-21 | 2017-10-26 | パナソニックＩｐマネジメント株式会社 | Evaluation method for resin impregnation of resin molding glass fiber |
| CN108645814A (en) * | 2018-06-28 | 2018-10-12 | 浙江理工大学 | A kind of high spectrum image acquisition method of the wetting zones of multicolour cloth for identification |
| CN108693093A (en) * | 2018-04-13 | 2018-10-23 | 浙江肯特科技股份有限公司 | A kind of the water resistance detection device and method of fabric |
| CN109164014A (en) * | 2018-06-28 | 2019-01-08 | 浙江理工大学 | A kind of multicolour cloth wetting zones recognition methods based on Hyperspectral imagery processing |
| WO2021131418A1 (en) * | 2019-12-25 | 2021-07-01 | ダイキン工業株式会社 | Blemish evaluation method, droplet evaluation method, repellent evaluation method, and repellent evaluation device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6162839A (en) * | 1984-09-03 | 1986-03-31 | Unitika Ltd | Method and apparatus for measuring water repellency |
| CN101196511A (en) * | 2007-12-21 | 2008-06-11 | 五邑大学 | Fabric spray rating detecting method and its detecting equipment |
| JP2009031562A (en) * | 2007-07-27 | 2009-02-12 | Nikon Corp | Light receiving element, light receiver, focus detecting device, camera |
-
2012
- 2012-07-26 CN CN2012102625145A patent/CN102830045A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6162839A (en) * | 1984-09-03 | 1986-03-31 | Unitika Ltd | Method and apparatus for measuring water repellency |
| JP2009031562A (en) * | 2007-07-27 | 2009-02-12 | Nikon Corp | Light receiving element, light receiver, focus detecting device, camera |
| CN101196511A (en) * | 2007-12-21 | 2008-06-11 | 五邑大学 | Fabric spray rating detecting method and its detecting equipment |
Non-Patent Citations (11)
| Title |
|---|
| AMERICAN ASSOCIATION OF TEXTILE CHEMISTRY AND COLORISTS: "《AATC Test Method22-2005》", 31 December 2006 * |
| YOUNG JIN JEONG ET AL: "Objective Measurement of Water Repellency of Fabric Using Image Analysis(I) Methodology of Image Processing", 《FIBERS AND POLYMERS》 * |
| 刘兴建: "关于数字图像处理中直方图均衡化的探讨", 《硅谷》 * |
| 刘娜 等: "一种改进的的对比度灰度图像边缘识别方法", 《计算机时代》 * |
| 刘成霞: "基于图像处理的针织物拒水性能客观评价研究", 《针织工业》 * |
| 周金和 等: "一种有选择的图像灰度化方法", 《计算机工程》 * |
| 彭召意: "16位位图的灰度化处理方法", 《中国包装工程》 * |
| 徐辉: "基于matlab的图像增强技术的分析与研究", 《湖北第二师范学院学报》 * |
| 朱桂英: "织物防水性能自动识别系统的研究", 《产业与科技论坛》 * |
| 杨小冈: "一种实用的图像滤波算法", 《计算机应用》 * |
| 高浩军 等: "中值滤波在图像处理中的应用", 《电子工程师》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392441A (en) * | 2014-11-18 | 2015-03-04 | 浙江理工大学 | Method for detecting and evaluating spray rating of high anti-noise fabric based on image processing |
| CN104392441B (en) * | 2014-11-18 | 2018-04-27 | 浙江理工大学 | High anti-noise fabric spray rating detecting appraisal method based on image procossing |
| JP2017194389A (en) * | 2016-04-21 | 2017-10-26 | パナソニックＩｐマネジメント株式会社 | Evaluation method for resin impregnation of resin molding glass fiber |
| CN108693093A (en) * | 2018-04-13 | 2018-10-23 | 浙江肯特科技股份有限公司 | A kind of the water resistance detection device and method of fabric |
| CN108645814A (en) * | 2018-06-28 | 2018-10-12 | 浙江理工大学 | A kind of high spectrum image acquisition method of the wetting zones of multicolour cloth for identification |
| CN109164014A (en) * | 2018-06-28 | 2019-01-08 | 浙江理工大学 | A kind of multicolour cloth wetting zones recognition methods based on Hyperspectral imagery processing |
| CN109164014B (en) * | 2018-06-28 | 2020-11-06 | 浙江理工大学 | Hyperspectral image processing-based method for identifying wetting area of multicolor fabric |
| CN108645814B (en) * | 2018-06-28 | 2020-12-15 | 浙江理工大学 | Hyperspectral image acquisition method for identifying wetting area of multicolor fabric |
| WO2021131418A1 (en) * | 2019-12-25 | 2021-07-01 | ダイキン工業株式会社 | Blemish evaluation method, droplet evaluation method, repellent evaluation method, and repellent evaluation device |
| JP2021103111A (en) * | 2019-12-25 | 2021-07-15 | ダイキン工業株式会社 | Stain evaluation method, waterdrop evaluation method, repellent evaluation method, and repellent evaluation device |
| JP7054010B2 (en) | 2019-12-25 | 2022-04-13 | ダイキン工業株式会社 | Stain evaluation method, water droplet evaluation method, repellent evaluation method and repellent evaluation device |
| KR20220084415A (en) * | 2019-12-25 | 2022-06-21 | 다이킨 고교 가부시키가이샤 | A stain evaluation method, a number evaluation method, a release evaluation method, and a release evaluation apparatus |
| CN114761785A (en) * | 2019-12-25 | 2022-07-15 | 大金工业株式会社 | Stain evaluation method, water drop evaluation method, repellent evaluation method, and repellent evaluation device |
| KR102498511B1 (en) | 2019-12-25 | 2023-02-10 | 다이킨 고교 가부시키가이샤 | Stain evaluation method, number evaluation method, release evaluation method, and release evaluation device |
| CN114761785B (en) * | 2019-12-25 | 2023-09-29 | 大金工业株式会社 | Stain evaluation method, water drop evaluation method, dial evaluation method, and dial evaluation device |
| TWI824209B (en) * | 2019-12-25 | 2023-12-01 | 日商大金工業股份有限公司 | Speck evaluation method, water droplet evaluation method, repellent agent evaluation method and repellent agent evaluation device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102830045A (en) | Fabric spray rating objective evaluating method based on image processing | |
| US20220237811A1 (en) | Method for Testing Skin Texture, Method for Classifying Skin Texture and Device for Testing Skin Texture | |
| CN102156996B (en) | Image edge detection method | |
| CN108022233A (en) | A kind of edge of work extracting method based on modified Canny operators | |
| CN102201120B (en) | Multifeature-based target object contour detection method | |
| CN108280823A (en) | The detection method and system of the weak edge faults of cable surface in a kind of industrial production | |
| CN103778627B (en) | A kind of marine site based on SAR image oil spilling detection method | |
| Li et al. | A multi-scale fusion scheme based on haze-relevant features for single image dehazing | |
| CN109344724A (en) | A kind of certificate photo automatic background replacement method, system and server | |
| JP2012011137A5 (en) | ||
| CN101430763B (en) | Detection method for on-water bridge target in remote sensing image | |
| CN105913415A (en) | Image sub-pixel edge extraction method having extensive adaptability | |
| CN104574418A (en) | Pressure vessel weld defect identification method and device based on neural network | |
| CN101246593B (en) | Color image edge detection method and apparatus | |
| CN103177260B (en) | A kind of coloured image boundary extraction method | |
| CN105741281B (en) | Method for detecting image edge based on neighborhood dispersion | |
| JP5753055B2 (en) | Skin image analysis apparatus and skin image analysis method | |
| CN102024156A (en) | Method for positioning lip region in color face image | |
| CN102819850A (en) | Method for detecting edge of color image on basis of local self-adaption color difference threshold | |
| CN102306378B (en) | Image enhancement method | |
| CN109658391A (en) | A kind of radius of circle measurement method being fitted based on contour mergence and convex closure | |
| CN106228541A (en) | Screen positioning method and device in visual inspection | |
| CN104700417A (en) | Computer image based automatic identification method of timber knot flaws | |
| CN114972397A (en) | Infrared image defect contour detection method for wind power blade composite material | |
| CN105787912A (en) | Classification-based step type edge sub pixel localization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20121219 |