CN102980659B - Digitalized characterization method of monochrome tight fabric surface color - Google Patents
Digitalized characterization method of monochrome tight fabric surface color Download PDFInfo
- Publication number
- CN102980659B CN102980659B CN201210442477.6A CN201210442477A CN102980659B CN 102980659 B CN102980659 B CN 102980659B CN 201210442477 A CN201210442477 A CN 201210442477A CN 102980659 B CN102980659 B CN 102980659B
- Authority
- CN
- China
- Prior art keywords
- value
- average
- image
- pixel
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
The invention discloses a digitalized characterization method of monochrome tight fabric surface color. Digital imaging on the surface of monochrome tight fabric and colors of a picture after the digital imaging are transferred to a hue, saturation and intensity (HIS) space from a red, green and blue (RGB) space, and then an average value S and an average value I of pixels of the whole picture are computed; according to the average value S and the average value I, gap pixels and abnormal pixels of the picture are removed so as to obtain a processed picture; color information of the pixels in the processed picture is used as effective color information for fabric faces. Average value computing is carried out on RGB values of the pixels, and therefore a RGB color value of the fabric can be obtained. According to a range of the average value S of the picture pixels and a range of the average value I of the picture pixels in the HIS color space, the digitalized characterization method processes a fabric digital image; by removing the abnormal points of the pixels of overexposure and insufficient exposure, the pixels representing yarn gaps are removed; and by carrying out average value computing on the final pixels, the RGB color value of the fabric can be obtained.
Description
Technical field
The present invention relates to the characterization technique of monochromatic close weave surface color, more particularly, relate to a kind of digitizing characterizing method of monochromatic close weave surface color.
Background technology
In the world, textile industry is from being designed into production, then to quality inspection, the automation and intelligentification of this chain is the trend of the times of catering to era development, and computer technology and Information Technology Development also provide such facility.Fabric face quality inspection field is emphasis, and up to the present this link is substantially all consuming time, the manual detection of consumptive material, the greatly upgrading of the whole industry of restriction.In the analysis of fabric construction, large quantity research has been carried out in the aspects such as fabric defects, obtains outstanding achievement.Its main feature is to fabric is converted into digital picture, utilizes Digital image technology to analyze fabric digital picture, obtains corresponding cloth surface information.The digitizing of fabric face color is being characterized, and less in the correlative study of the poor grading of these basic enterprising circumstances in which people get things ready for a trip.
The most of research of Chinese scholars concentrates on the identification of fabric digital image texture and Digital Image Segmentation, the aspects such as pattern-recognition.Chung-Feng Jeffrey Kuo, Chung-Yang Shih etc. delivered research paper in 2005, provided a kind of new decorative pattern of automatic analysis PRINTED FABRIC and the method for color in literary composition.Concrete grammar comprises fuzzy C-mean algorithm method (FCM), specific threshold clustering procedure (SC criterion).Scanner obtains after digital picture, through mean filter, then utilizes FCM and SC criterion to carry out cluster to image slices vegetarian refreshments, thereby calculates lines and the color of image.Chih-Yuan Kao, the people such as Chung-Feng Jeffrey Kuo, with 2009, utilize wavelet transformation to carry out filtering to the digital picture of fabric, adopt the color feature value of CIELAB color space presentation video.Then utilize gray level co-occurrence matrixes to calculate the eigenwert of quality structure in image.Self-organizing map neural network is used to color segmentation operation.RuruPan, the people such as Weidong Gao in sub-ox in 2011 color cluster method in the application in identification automatically of yarn dyed fabric texture.In experiment, they utilize fuzzy C-mean algorithm method that the interlacing point of fabric is divided into two groups, utilize BP neural network to identify fabric face image, finally utilize gray level co-occurrence matrixes to extract the quality feature of fabric.
In some domestic researchs, Liu Suyi, Liu Jing Jing etc. has carried out the research of fabric aberration, and its main method is, be digital picture by stamp and solid coloured cloth scanning, then intercept certain area fabric digital picture, the rgb value of this area is transformed into after CIELab value, calculate its DE value; For PRINTED FABRIC, the method that research is taked is that selected decorative pattern part is carried out to Colorimetry, finally utilizes value of chromatism to evaluate aberration.2008, Huang Yue etc. [5], in the partitioning algorithm research of Alzheimer's disease hippocampus micro-image, mentioned the method that classify of image element and pixel colouring information are analyzed.In research, taking the rgb value of pixel as basis, utilize fuzzy C-mean algorithm method (FCM) to carry out cluster analysis to the pixel in picture, extract live part thereby cut apart picture, utilize mathematical morphology that required part is carried out to removal of impurities and edge extracting.
Up to the present, utilizing in the problem of Digital Image Processing quality of textile products detection field, the research proportion of fabric quality and yarn qualities is larger, characterizes the exploration of fabric color quality method and formulate still to belong to blank.
Summary of the invention
For the defect existing in prior art, the object of this invention is to provide a kind of digitizing characterizing method of monochromatic close weave surface color, the digitizing chromatic measuring system by computing machine treatment technology is for fabric color digitized measurement and sign.
For achieving the above object, the present invention adopts following technical scheme:
A digitizing characterizing method for monochromatic close weave surface color, the concrete steps of this digitizing characterizing method are:
A. digital imagery is carried out in monochromatic close weave surface, and the color of the picture after digital imagery is transformed into HSI space from rgb space, calculate average S value and the average I value of all pixels of picture in its entirety;
B. according to the average S value in steps A and average I value, this picture is removed space pixel and removed unusual pixel processing, obtain picture after treatment;
C. the effective colouring information as cloth cover for the colouring information of the pixel in picture after treatment, calculates rgb value value of averaging of these pixels, thereby obtains the RGB color value of this piece fabric.
The concrete steps of described steps A are: digital imagery is carried out in monochromatic close weave surface, image is carried out to initialization, image is decomposed into respectively to the bivector of R, G, tri-components of B;
Tri-components of RGB are carried out to translation operation, obtain the bivector of the S component of image in HSI space and the bivector of I value component, S, the I component value of averaging are calculated to average S value and the average I value of image.
The concrete steps of described step B are: if average S value be less than 0.15 and on average I value be less than at 0.1 o'clock, this picture is not processed.
The concrete steps of described step B are: if average S value be less than 0.15 and average I value be more than or equal at 0.1 o'clock, image is gone to the processing of yarn space.
Described concrete steps of going to yarn space to process are: utilize the process of convolution of carrying out in image X-direction and Y direction on R, the G of Sobel operator to image, B component, obtain a secondary gradient image;
Average gray value to gray level image in gradient map calculates, in the time that the gray-scale value of any one pixel in this figure is greater than average gray value, in former figure, be the point that represents yarn space with the pixel of this pixel present position, the pixel of correspondence position in former figure is removed, obtain the image of removing yarn space.
The concrete steps of described step B are: if average S value be more than or equal to 0.15 and average I value be more than or equal at 0.1 o'clock, first image is removed to the processing of yarn space, and then image is removed to unusual pixel processing.
The concrete steps that process in described removal yarn space are: utilize the process of convolution of carrying out in image X-direction and Y direction on R, the G of Sobel operator to image, B component, obtain a secondary gradient image;
Average gray value to gray level image in gradient map calculates, in the time that the gray-scale value of any one pixel in this figure is greater than average gray value, in former figure, be the point that represents yarn space with the pixel of this pixel present position, the pixel of correspondence position in former figure is removed, obtain the image of removing yarn space;
The concrete steps of the unusual pixel processing of described removal are: calculate the average S value of removing the image slices vegetarian refreshments behind yarn space, the pixel of image is lined by line scan, if the S value of this pixel is less than 0.5 times of average S value, this point is removed.
The digitizing characterizing method of a kind of monochromatic close weave surface color of the present invention is by the analysis to textile image, according to image in HSI color space, the scope of the average S value of image slices vegetarian refreshments and the scope of I value are processed fabric digital picture, effectively represented the pixel colouring information of fabric color, by removing over-exposed and not enough pixel singular point, remove the pixel that represents yarn space, by final pixel is done to mean value calculation, thereby obtain the RGB color value of this fabric.
Brief description of the drawings
Fig. 1 is the principle schematic of the digitizing characterizing method of a kind of monochromatic close weave surface color of the present invention;
Fig. 2 is the principle schematic of removing yarn space in Fig. 1;
Fig. 3 is the principle schematic of removing unusual pixel in Fig. 1.
Embodiment
Further illustrate technical scheme of the present invention below in conjunction with accompanying drawing and embodiment.
The digitizing characterizing method that refers to a kind of monochromatic close weave surface color shown in Fig. 1, the concrete steps of this digitizing characterizing method are:
Digital imagery is carried out on 11. pairs of monochromatic close weave surfaces, and the color of the picture after digital imagery is transformed into HSI space from rgb space, calculates average S value and the average I value of all pixels of picture in its entirety;
12. according to the average S value in steps A and average I value, and this picture is removed space pixel and removed unusual pixel processing, obtains picture after treatment;
13. colouring informations for the pixel in picture after treatment, as effective colouring information of cloth cover, calculate rgb value value of averaging of these pixels, thereby obtain the RGB color value of this piece fabric.
The concrete steps of described step 11 are: digital imagery is carried out in monochromatic close weave surface, image is carried out to initialization, image is decomposed into respectively to the bivector of R, G, tri-components of B;
Tri-components of RGB are carried out to translation operation, obtain the bivector of the S component of image in HSI space and the bivector of I value component, S, the I component value of averaging are calculated to average S value and the average I value of image.
If average S value be less than 0.15 and on average I value be less than at 0.1 o'clock, this picture is not processed.
If average S value be less than 0.15 and average I value be more than or equal at 0.1 o'clock, image is gone to the processing of yarn space.The concrete steps of going to yarn space to process are: utilize the process of convolution of carrying out in image X-direction and Y direction on R, the G of Sobel operator to image, B component, obtain a secondary gradient image, in gradient map, gray scale height is the region that color is different from low place, and the yarn space that the pixel that gray scale is high is fabric, average gray value to gray level image in gradient map calculates, in the time that the gray-scale value of any one pixel in this figure is greater than average gray value, in former figure, be the point that represents yarn space with the pixel of this pixel present position, the pixel of correspondence position in former figure is removed, obtain the image of removing yarn space, wherein X-axis is the horizontal coordinate in plane of delineation space, Y-axis is the along slope coordinate in plane of delineation space, specifically shown in Figure 2.
If average S value be more than or equal to 0.15 and average I value be more than or equal at 0.1 o'clock, first image is removed to the processing of yarn space, and then image is removed to unusual pixel processing.Remove the concrete steps of processing in yarn space described above, no longer repeat at this.The concrete steps that refer to again the unusual pixel processing of the removal shown in Fig. 3 are: calculate the average S value of removing the image slices vegetarian refreshments behind yarn space, pixel to image is lined by line scan, if the S value of this pixel is less than 0.5 times of average S value, this point is removed.
It should be noted that, so-called unusual pixel is the pixel of the over-exposed or no-reflection of cloth cover in image.
Those of ordinary skill in the art will be appreciated that, above embodiment is only for object of the present invention is described, and not as limitation of the invention, as long as in essential scope of the present invention, variation, modification to the above embodiment all will drop in the scope of claim of the present invention.
Claims (3)
1. a digitizing characterizing method for monochromatic close weave surface color, is characterized in that:
The concrete steps of this digitizing characterizing method are:
A. digital imagery is carried out in monochromatic close weave surface, and the color of the picture after digital imagery is transformed into HSI space from rgb space, calculate average S value and the average I value of all pixels of picture in its entirety;
B. according to the average S value in steps A and average I value, this picture is removed space pixel and removed unusual pixel processing, obtain picture after treatment;
C. the effective colouring information as cloth cover for the colouring information of the pixel in picture after treatment, calculates rgb value value of averaging of these pixels, thereby obtains the RGB color value of this piece fabric;
The concrete steps of described step B are:
If average S value be less than 0.15 and on average I value be less than at 0.1 o'clock, this picture is not processed;
If average S value be less than 0.15 and average I value be more than or equal at 0.1 o'clock, image is gone to the processing of yarn space;
If average S value be more than or equal to 0.15 and average I value be more than or equal at 0.1 o'clock, first image is removed to the processing of yarn space, and then image is removed to unusual pixel processing;
Described concrete steps of going to yarn space to process are: utilize the process of convolution of carrying out in image X-direction and Y direction on R, the G of Sobel operator to image, B component, obtain a secondary gradient image; Average gray value to gray level image in gradient map calculates, in the time that the gray-scale value of any one pixel in this figure is greater than average gray value, in former figure, be the point that represents yarn space with the pixel of this pixel present position, the pixel of correspondence position in former figure is removed, obtain the image of removing yarn space.
2. digitizing characterizing method according to claim 1, is characterized in that:
The concrete steps of described steps A are: digital imagery is carried out in monochromatic close weave surface, image is carried out to initialization, image is decomposed into respectively to the bivector of R, G, tri-components of B;
Tri-components of RGB are carried out to translation operation, obtain the bivector of the S component of image in HSI space and the bivector of I value component, S, the I component value of averaging are calculated to average S value and the average I value of image.
3. digitizing characterizing method according to claim 1, is characterized in that:
The concrete steps of the unusual pixel processing of described removal are: calculate the average S value of removing the image slices vegetarian refreshments behind yarn space, the pixel of image is lined by line scan, if the S value of this pixel is less than 0.5 times of average S value, this point is removed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210442477.6A CN102980659B (en) | 2012-11-07 | 2012-11-07 | Digitalized characterization method of monochrome tight fabric surface color |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210442477.6A CN102980659B (en) | 2012-11-07 | 2012-11-07 | Digitalized characterization method of monochrome tight fabric surface color |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102980659A CN102980659A (en) | 2013-03-20 |
CN102980659B true CN102980659B (en) | 2014-10-08 |
Family
ID=47854887
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210442477.6A Expired - Fee Related CN102980659B (en) | 2012-11-07 | 2012-11-07 | Digitalized characterization method of monochrome tight fabric surface color |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102980659B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751446A (en) * | 2015-01-06 | 2015-07-01 | 金陵科技学院 | Digital pattern feature based tie-dyeing process prediction method |
CN105354864A (en) * | 2015-09-25 | 2016-02-24 | 浙江大学 | Textile tissue color replacement simulation method with relatively high truth |
CN105803623B (en) * | 2016-04-18 | 2017-08-04 | 南京航空航天大学 | A kind of computer graphical recognition methods of composite microscopical structure |
CN106485288B (en) * | 2016-12-21 | 2023-11-28 | 上海工程技术大学 | Automatic identification method for colored fabric tissue |
CN114324189B (en) * | 2021-12-22 | 2023-06-02 | 江苏恒力化纤股份有限公司 | Method for evaluating color uniformity of warp and weft yarns of woven fabric |
CN116934749B (en) * | 2023-09-15 | 2023-12-19 | 山东虹纬纺织有限公司 | Textile flaw rapid detection method based on image characteristics |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398392A (en) * | 2007-09-26 | 2009-04-01 | 中国科学院自动化研究所 | Cotton impurity high speed real-time detection method based on HSI color space |
CN102332154A (en) * | 2011-10-18 | 2012-01-25 | 中国农业大学 | Method and system for enhancing color images of cotton pseudo foreign fibers under non-uniform illumination |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101094752B1 (en) * | 2009-06-30 | 2011-12-16 | 호서대학교 산학협력단 | Lane Classification Method Using Statistical Model of HSI Color Information |
US8884980B2 (en) * | 2010-09-24 | 2014-11-11 | Taaz, Inc. | System and method for changing hair color in digital images |
-
2012
- 2012-11-07 CN CN201210442477.6A patent/CN102980659B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398392A (en) * | 2007-09-26 | 2009-04-01 | 中国科学院自动化研究所 | Cotton impurity high speed real-time detection method based on HSI color space |
CN102332154A (en) * | 2011-10-18 | 2012-01-25 | 中国农业大学 | Method and system for enhancing color images of cotton pseudo foreign fibers under non-uniform illumination |
Non-Patent Citations (2)
Title |
---|
基于HIS空间的彩色绣花图样的轮廓提取算法研究;胡少凛等;《北京服装学院学报》;20120131;第32卷(第1期);正文第65-66页 * |
胡少凛等.基于HIS空间的彩色绣花图样的轮廓提取算法研究.《北京服装学院学报》.2012,第32卷(第1期),正文第65-66页. |
Also Published As
Publication number | Publication date |
---|---|
CN102980659A (en) | 2013-03-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102980659B (en) | Digitalized characterization method of monochrome tight fabric surface color | |
CN107845087B (en) | Method and system for detecting uneven brightness defect of liquid crystal panel | |
CN110322522B (en) | Vehicle color recognition method based on target recognition area interception | |
CN109507192B (en) | Magnetic core surface defect detection method based on machine vision | |
CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
CN104483326B (en) | High-voltage line defects of insulator detection method and system based on depth belief network | |
CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
CN108416766B (en) | Double-side light-entering type light guide plate defect visual detection method | |
Quan et al. | The method of the road surface crack detection by the improved Otsu threshold | |
CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
CN106296691B (en) | Pavement disease recognition methods based on image analysis | |
CN111047655A (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
Samarawickrama et al. | Matlab based automated surface defect detection system for ceremic tiles using image processing | |
CN109166111B (en) | Electronic ink screen defect detection method and system | |
CN110096980A (en) | Character machining identifying system | |
CN109781737A (en) | A kind of detection method and its detection system of hose surface defect | |
CN113793337A (en) | Locomotive accessory surface abnormal degree evaluation method based on artificial intelligence | |
CN109064439B (en) | Partition-based single-side light-entering type light guide plate shadow defect extraction method | |
Abbas et al. | Automated pavement distress detection using image processing techniques | |
TWI512284B (en) | Bubble inspection system for glass | |
CN113706461A (en) | Micro-defect identification system of insulating blanket based on image identification | |
CN109580618A (en) | A method of floating product grade is judged based on foam color | |
CN106960424B (en) | Tubercle bacillus image segmentation and identification method and device based on optimized watershed algorithm | |
CN106558044A (en) | The resolution measuring method of image module | |
CN111210419B (en) | Micro magnetic shoe surface defect detection method based on human visual characteristics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141008 Termination date: 20211107 |
|
CF01 | Termination of patent right due to non-payment of annual fee |