CN106198542A - A kind of WARP-KNITTING technique fast analyser based on smart mobile phone and method - Google Patents
A kind of WARP-KNITTING technique fast analyser based on smart mobile phone and method Download PDFInfo
- Publication number
- CN106198542A CN106198542A CN201610522846.0A CN201610522846A CN106198542A CN 106198542 A CN106198542 A CN 106198542A CN 201610522846 A CN201610522846 A CN 201610522846A CN 106198542 A CN106198542 A CN 106198542A
- Authority
- CN
- China
- Prior art keywords
- image
- mobile phone
- fabric
- smart mobile
- textile
- 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
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1765—Method using an image detector and processing of image signal
- G01N2021/177—Detector of the video camera type
Abstract
The invention discloses a kind of WARP-KNITTING technique based on smart mobile phone quickly to analyze, including the server for WARP-KNITTING image being processed, analyzing, and for carrying out the smart mobile phone of fabric positive and negative image acquisition, smart mobile phone can carry out pretreatment and carry out information with server and pass mutually image;The invention also discloses a kind of WARP-KNITTING technique rapid analysis method, smart mobile phone gathers the front-back two-sided image of WARP-KNITTING and is sent to server, server receive described in the textile image that sends of smart mobile phone and carry out processing, analyzing, then analysis result is sent to smart mobile phone;Said apparatus and method is used WARP-KNITTING to be carried out technique and quickly analyzes, it is achieved that WARP-KNITTING industrial analysis automatization, digitized requirement, easy to use, it is simple to popularize;And user can obtain the technique information of fabric whenever and wherever possible, improve industrial analysis efficiency, eliminate the technical threshold of industrial analysis.
Description
Technical field
The invention belongs to fabric weaving field, particularly to one weaving image processing field.
Background technology
WARP-KNITTING organizational structure and its performance have extremely close relation, affect the strength of fabric, draftability, fabric wind
Lattice and feel etc., therefore, the analysis to WARP-KNITTING organizational structure is a problem extremely having researching value.But traditional warp
Fabric contextual analysis of organization method is all manual analysis, utilizes microscope and the magnifier with scale to complete, and analyzes process
Dull, dull, analysis efficiency is relatively low, and requires higher to analyzing personnel's technology.Increase and weaving row along with labor cost
Industry automaticity promotes, automatization, Weigh sensor WARP-KNITTING organizational structure become one urgently to be resolved hurrily and there is application
The problem of prospect.
Along with the development of computer technology, Morden Image Processing Technology application in textile manufacturing is gradually extensive, warp knit
The automatic analysis method of fabric construction starts to find application, and existing fabric construction autoanalyzer method is mainly by scanner or number
The computer software part composition that the image collecting device of camera and fabric construction are analyzed, the method yet suffer from following deficiency it
Place: 1) scanner or digital camera operation complexity, the most portable, user's popularity is the highest, it is impossible to meet user whenever and wherever possible
The purpose used;2) woven fabric is far from each other with the Knitting Principle of WARP-KNITTING, and it is relatively simple woven that device is applicable to structure
Thing, cannot be suitable for for baroque warp-knitted fabric.
Summary of the invention
In view of the foregoing, it is an object of the invention to provide a kind of WARP-KNITTING technique based on smart mobile phone quickly to divide
Analysis apparatus, its simple and convenient, it is possible to automatically measure and identify that the art flower width of fabric, art flower are high, finished product horizontal stroke is close, finished product is indulged
Close, organizational structure and pass circulation etc., improves WARP-KNITTING industrial analysis efficiency, meets the requirement that user uses whenever and wherever possible.
Present invention also offers a kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone.
For achieving the above object, the present invention is by the following technical solutions:
A kind of WARP-KNITTING technique fast analyser based on smart mobile phone, including smart mobile phone and server, described
Smart mobile phone is used for gathering the front-back two-sided image of fabric and sending to server, and described server is used for receiving described smart mobile phone
The textile image that sends also carries out processing, analyzing, and then analysis result is sent to smart mobile phone.
Further, described smart mobile phone is provided with
Photographic head, is used for shooting and gather the front-back two-sided image of fabric;
Image the first pretreatment module, is used for judging picture quality and carry out corresponding white balance to process and framing sanction
Cut;
Image sending module, for sending textile image to server.
Information receiving module, for receiving the fabric analysis result that server sends.
Further, described server is provided with
Image receiver module, for receiving the textile image sent by smart mobile phone sending module;
Image the second pretreatment module, the textile image for receiving image receiver module carries out gray processing and processes also
Detect whether containing fabric;
Image processing module, for through second pretreatment module process after textile image carry out threshold transformation, from
Adaptive filtering, fast Fourier transform, rim detection etc. process, and obtain the periodic feature of textile processes positive and negative image respectively
Point;
Fabric analysis module, for textile image Weave parameters is analyzed, is calculated, show that fabric analysis is tied
Really, including art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc.;
Result feedback module, for being sent to smart mobile phone client by fabric analysis result.
A kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone, comprises the following steps:
S1 smart mobile phone gathers WARP-KNITTING dual-side image and is sent to server;
S2 server receive described in the textile image that sends of smart mobile phone and carry out processing, analyzing, then by analysiss knot
Fruit is sent to smart mobile phone.
Further, described step S1 specifically include following step by step:
S11 detects ambient lighting, is obtained the illumination value of surrounding by the light sensor of smart mobile phone, presets
Illumination value span, when ambient lighting value is not in default scope, Image Acquisition failure;
S12 textile image preview, arranges fabric shooting preview frame, and it is pre-that user makes fabric be presented on by adjustment camera site
Look in frame and guarantee preview pane at least contains the textile image of a complete cycle size;
S13 for the first time pretreatment: by smart mobile phone the image collected in step S11 is amplified 3-6 times laggard
Row location cutting and processing based on the AWB carrying out dynamic threshold, meets the fabric figure of fabric analysis requirement to obtain
Picture;
S14 textile image sends, and the textile image obtained in step S13 is sent extremely by the image sending module of smart mobile phone
Server.
Further, in described step pretreatment S13 for the first time, white balancing treatment method includes:
Textile image is YC by RGB patten transformation by S131bCr, divide the image into N number of part after converting, count respectively
Calculate the C of each partbAnd CrMeansigma methods Mb、MrAnd both mean square deviations Db、Dr, computational methods are as follows:
Meansigma methods M in the S132 statistics each region of textile imageb、MrAnd mean square deviation Db、DrAs whole image value (
After need to cast out Db<0.05MbAnd/or Dr<0.05MrTime value);
S133 determines the white reference point in textile image as follows,
|Cb(i,j)-(Mb+Db×sign(Mb)) | < 1.5 × Db
|Cr(i,j)-(Mr+Dr×sign(Mr)) | < 1.5 × Dr
Before brightness value, the white reference point of 10% is as final white reference point;
S134 calculates textile image each white reference point average brightness Rav, Gav, Bav, the gain R of each passagegain, Ggain,
BgainWith image at YCbCrThe maximum Y of Y under patternmax;
R ' G ' the B ' that the S135 calculating each passage of textile image is final:
R '=R × Rgain
G '=G × Ggain
B '=B × Bgain
Further, described step S2 include following step by step:
S21 textile image receives, and it is pre-that server receiver module receives the warp sent by smart mobile phone image sending module
Textile image after reason;
S22 textile image pretreatment, the textile image that step S21 is received by server the second pretreatment module carries out ash
Degreeization processes and detects whether containing fabric;
S23 textile image processes, and the image after step S22 is processed by image processing module carries out threshold transformation, self adaptation
Filtering, fast Fourier transform, rim detection etc. process, and obtain the periodic feature point of textile processes positive and negative image respectively;
S24 textile image is analyzed, and the image in step S23 is analyzed by fabric analysis module, show that fabric analysis is tied
Really, including art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc.;
S25 analysis result is fed back, and the fabric analysis result drawn in step S24 is sent to intelligence by result feedback module
In mobile phone.
Preferably, the image gray processing in described step S22 is processed and is converted by below equation:
Gray (i, j)=0.11R (i, j)+0.59G (i, j)+0.3B (i, j)
Preferably, described step S23 includes following sub-step:
S231 threshold transformation, uses the fabric tow sides image binaryzation that the method for threshold transformation will be extracted, image ash
The threshold transformation method of degree is as follows:
S232, by the noise in Adaptive noise cancellation fabric two-face image, adjusts filtering according to the local variance of image
Output, it is ensured that image border and detail of the high frequency.
The spatial domain image of textile processes direct picture is converted to frequency spectrum by fast Fourier transform (FFT) by S233
Figure:
S234 carries out rim detection to the textile processes verso images after step S231, S232 process, and obtains fabric
The edge graph of technical back.
Preferably, described step S24 includes following sub-step:
Textile processes front frequency domain figure picture after the process of S241 server images processing module is in the horizontal and vertical directions
Having the bright band of the regularity of distribution, horizontal direction bright band to represent fabric line information, vertical direction bright band represents fabric stringer information, point
Other frequency domain figure picture is both horizontally and vertically projected;
The central point of S242 selected level (vertically) direction projection image, along vertical (horizontal) direction point by point scanning image ash
Degree, until scanning this pixel when gray value is 255 as starting point, continues along vertical (horizontal) direction point by point scanning, until
Scanning next time and stop when gray value is 255, pixel count m (n) of writing scan, adjacent the two of m (n) extremely fabric are horizontal
Frequency between row (stringer).
The image resolution ratio of S243 smart mobile phone 100 shooting is r (pixel/inch), the textile image size of location cutting
For M × N (pixel), the art flower width W of described fabricidth, art flower height Height, the horizontal close W of finished productPCClose C is indulged with finished productPCPermissible
It is expressed as:
Width=n
Height=m
Textile processes verso images after the process of S244 server 200 image processing module 230, to the fabric edge extracted
In figure, multiple target areas parameters for shape characteristic is identified, and uses element marking method to judge pixel-by-pixel, obtains tissue and follows
Coil underlap edge parameters in ring, and then analyze, calculate the organizational structure of fabric and pass circulation.
After using technique scheme, the present invention, compared with background technology, has the advantage that
1, the present invention obtains textile image information by smart mobile phone, utilizes the online wireless technology of smart mobile phone by fabric
Image information is sent to long-range high-performance server, it is achieved that WARP-KNITTING industrial analysis automatization, digitized requirement, letter
Single easy-to-use, it is simple to popularize;
2, the present invention can automatically identify WARP-KNITTING information and be analyzed, calculates, and user can obtain whenever and wherever possible and knit
The technique information of thing, including art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc., carries
High technology analysis efficiency, eliminates the technical threshold of industrial analysis.
Accompanying drawing explanation
Fig. 1 is that a kind of WARP-KNITTING technique fast analyser interface based on smart mobile phone of the present invention is with reference to figure;
Fig. 2 is the schematic flow sheet of WARP-KNITTING technique rapid analysis method of the present invention;
Fig. 3 a is WARP-KNITTING fabric face image after cutting in a kind of embodiment;
Fig. 3 b is WARP-KNITTING fabric backing image after cutting in a kind of embodiment;
Fig. 4 a is Fig. 3 a fabric face image after threshold transformation;
Fig. 4 b is Fig. 3 b fabric backing image after threshold transformation;
Fig. 5 is the textile processes front spectrogram after the treated resume module of 4a;
Fig. 6 is the textile processes opposite longitudinal side edge figure after the treated resume module of 4a.
Detailed description of the invention:
In order to make the object of the invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, to the present invention
It is described further.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, but is not used to limit this
Bright.
Embodiment
The invention discloses a kind of WARP-KNITTING technique fast analyser based on smart mobile phone, including smart mobile phone and
Server, wherein:
Smart mobile phone is used for gathering the front-back two-sided image of fabric and being sent to server, is provided with photographic head, image
First pretreatment module and image sending module and information receiving module;Photographic head is used for shooting and gathering textile image;Image
First pretreatment module is used for judging textile image quality and carry out white balance to process and framing cutting;Image sending module
For sending textile image to server;Information receiving module is for receiving the fabric analysis result that server sends.
Server is for receiving textile image that smart mobile phone sends and carrying out processing, analyze and calculating, and by analysiss knot
Fruit is sent to smart mobile phone, and server arranges image receiver module, image the second pretreatment module, image processing module, fabric
Analyze module and result fabric analysis result feedback module.Image receiver module is sent by smart mobile phone sending module for receiving
Textile image;Image the second pretreatment module is smoothed for the textile image receiving receiver module and detects
No have fabric;Image processing module textile image after processing the second pretreatment module carries out threshold transformation, self adaptation
Filtering, fast Fourier transform, rim detection etc. process, and obtain the periodic feature point of textile processes positive and negative image respectively;
Fabric analysis module textile image after processing image processing module carries out Weave parameters analysis, calculating, draws
Fabric analysis result, including art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc.;Knot
Really feedback module, for being sent to smart mobile phone by the analysis result of fabric analysis module.
With reference to Fig. 1 and Fig. 2, a kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone, with a kind of double comb spies
In as a example by section's WARP-KNITTING, it comprises the following steps:
S1 smart mobile phone gathers the front-back two-sided image of WARP-KNITTING and is sent to server, and this step is through following real step by step
Existing:
S11 detects ambient lighting, obtains ambient lighting value by smart mobile phone light sensor, and this step needs to set in advance
Good illumination span, if ambient lighting value is not in default scope, then Image Acquisition failure;
S12 textile image preview, arranges fabric shooting preview frame, and user can make fabric be presented on by adjusting picture-taking position
In preview pane and guarantee preview pane at least contains the textile image of a complete cycle size;
S13 for the first time pretreatment: by smart mobile phone the image collected in step S11 is amplified 3-6 times laggard
Row location cutting and processing based on the AWB carrying out dynamic threshold, meets the fabric figure of fabric analysis requirement to obtain
Picture;(with reference to Fig. 3 a and Fig. 3 b), it is as follows that white balance processes concrete grammar:
It is YC by textile image by RGB patten transformationbCr, divide the image into N number of part after converting, calculate every respectively
The C of individual partbAnd CrMeansigma methods Mb、MrAnd both mean square deviations Db、Dr, computational methods are as follows:
Meansigma methods M in the statistics each region of textile imageb、MrAnd mean square deviation Db、DrAs the value of whole image, if certain portion
The mean square deviation divided is less than normal, omits and (casts out Db<0.05MbAnd/or Dr<0.05MrTime value), it is to avoid because distribution of color uniformly shadow
Ring analysis result;
Determine the white reference point in textile image as follows, if to take it bright for the pixel being tentatively set to white reference point
Before angle value, 10% as final white reference point:
|Cb(i,j)-(Mb+Db×sign(Mb)) | < 1.5 × Db
|Cr(i,j)-(Mr+Dr×sign(Mr)) | < 1.5 × Dr
Calculate textile image each white reference point average brightness Rav, Gav, Bav, the gain R of each passagegain, Ggain, Bgain
With image at YCbCrThe maximum Y of Y under patternmax:
R ' G ' the B ' that the calculating each passage of textile image is final:
R '=R × Rgain
G '=G × Ggain
B '=B × Bgain
S14 textile image sends, and the textile image obtained in step S13 is sent extremely by the image sending module of smart mobile phone
Server.
S2 server receive described in the textile image that sends of smart mobile phone and carry out processing, analyzing, then by analysiss knot
Fruit is sent to smart mobile phone, and this step realizes step by step through following:
S21 server receiver module receives the fabric figure after pretreatment sent by smart mobile phone image sending module
Picture;
The textile image that step is received by S22 server the second pretreatment module carries out gray processing process and detects whether
Containing fabric, gray processing is converted by below equation:
Gray (i, j)=0.11R (i, j)+0.59G (i, j)+0.3B (i, j)
S23 textile image processes, and the textile processes image after step S22 is processed by image processing module carries out threshold value change
Change, adaptive-filtering, fast Fourier transform, rim detection etc. process, and obtain the cycle of textile processes positive and negative image respectively
Property characteristic point, concrete grammar is as follows:
S231 selectes fabric two-face gray level image threshold value T, if certain grey scale pixel value is less than T in textile image, then and pixel ash
Angle value is set to 0, if certain grey scale pixel value is more than T, then grey scale pixel value is set to 255, by textile image binaryzation (with reference to Fig. 4 a and
Fig. 4 b), the threshold transformation method of gradation of image is as follows:
S232, by the noise in Adaptive noise cancellation fabric two-face image, adjusts filtering according to the local variance of image
Output, it is ensured that image border and detail of the high frequency.
The spatial domain image of textile processes direct picture is converted to spectrogram by fast Fourier transform (FFT) by S233
(with reference to Fig. 5):
S234 carries out rim detection to the textile processes verso images after step S231, S232 process, and obtains fabric
The edge graph (with reference to Fig. 6) of technical back.
S24 textile image is analyzed, and the image after step S23 is processed by server fabric analysis module is analyzed, and draws
Fabric analysis result, including art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc., tool
Body method is as follows:
Textile processes front frequency domain figure picture after server images processing module processes has point in the horizontal and vertical directions
The bright band of cloth rule, horizontal direction bright band represents fabric line information, and vertical direction bright band represents fabric stringer information, the most right
Frequency domain figure picture both horizontally and vertically projects;
The central point of selected level (vertically) direction projection image, along vertical (horizontal) direction point by point scanning gradation of image,
Until scanning this pixel when gray value is 255 as starting point, continue along vertical (horizontal) direction point by point scanning, until next
Secondary scanning stops when gray value is 255, pixel count m (n) of writing scan, and adjacent two lines of m (n) extremely fabric are (vertical
Frequency between OK).
The image resolution ratio of smart mobile phone shooting is r (pixel/inch), and the textile image size of location cutting is M × N
(pixel), then the art flower width of fabric, art flower is high, finished product is horizontal close and finished product is indulged and close can be expressed as:
Width=n
Height=m
Textile processes verso images after the process of server images processing module, to multiple mesh in the fabric edge figure extracted
Mark region shape characteristic parameter is identified, and uses element marking method to judge pixel-by-pixel, obtains the coil in Weaving Cycle
Underlap edge parameters, and then analyze, calculate the organizational structure of fabric and pass circulation.
S25 analysis result is fed back, and the fabric analysis result drawn in step S24 is sent to intelligence hands by result feedback module
In machine, and analysis result is shown to user.
Utilizing said method to monitor different WARP-KNITTING continuously, contrast with manual measurement, result is as shown in the table:
WARP-KNITTING density measure error in length and breadth
As can be seen from the above table, use the WARP-KNITTING technique rapid analysis method of the present invention, can effectively must apply to
The analysis of multiple different fabric construction, and analysis result and the error less (respectively less than 6%) of manual analysis, ensureing accurately
On the premise of degree, it is possible to effective must improve analysis speed.
The foregoing is only the preferred embodiment of the present invention, but the present invention is not limited to this, be familiar with the skill in this field
Any change that the detailed description of the invention of the present invention is done by art personnel is all without departing from the scope of claims of the present invention.Cause
This, as long as the improvement made on the basis of its general principles and conversion, be regarded as falling into the protection model of the present invention
In enclosing.
Claims (10)
1. a WARP-KNITTING technique fast analyser based on smart mobile phone, including to WARP-KNITTING image
Reason, the server analyzed, it is characterised in that also include the smart mobile phone for carrying out fabric positive and negative image acquisition, described intelligence
Expert's machine can carry out pretreatment and carry out information with server and pass mutually image.
WARP-KNITTING technique fast analyser the most according to claim 1, it is characterised in that smart mobile phone is provided with
Photographic head, for shooting and gather the front-back two-sided image of technique of fabric;
Image the first pretreatment module, is used for judging picture quality and carry out corresponding white balance to process and framing cutting;
Image sending module, for sending textile image to server;
Information receiving module, for receiving the fabric analysis result that server sends.
WARP-KNITTING technique fast analyser the most according to claim 1 and 2, it is characterised in that: described server
On be provided with
Image receiver module, for receiving the textile image sent by smart mobile phone sending module;
Image the second pretreatment module, be smoothed for textile image that image receiver module is received and detect be
No containing fabric;
Image processing module, for carrying out threshold transformation, self adaptation to the textile image after the second pretreatment module processes
Filtering, fast Fourier transform, rim detection etc. process, and obtain the periodic feature point of textile processes positive and negative image respectively;
Fabric analysis module, for textile image Weave parameters is analyzed, is calculated, draws fabric analysis result, bag
Include art flower width, art flower is high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and passes circulation etc.;
Result feedback module, for being sent to smart mobile phone client by fabric analysis result.
4. a WARP-KNITTING technique rapid analysis method based on smart mobile phone, comprises the following steps:
S1 smart mobile phone gathers the front-back two-sided image of WARP-KNITTING and is sent to server, including:
S12 textile image gathers: user makes fabric be presented in preview pane by adjusting camera site and guarantees in preview pane extremely
Contain the textile image of a complete cycle size less;
S13 pretreatment for the first time: it is fixed to carry out after the image collected in step S11 being amplified 3-6 times by smart mobile phone
Position cutting and processing based on the AWB carrying out dynamic threshold, meets the textile image of fabric analysis requirement to obtain;
S14 image sends: the textile image passing through pretreatment for the first time in step S12 is sent out by the image sending module of smart mobile phone
Deliver to server.
S2 server receive described in the textile image that sends of smart mobile phone and carry out processing, analyzing, then analysis result is sent out
Deliver to smart mobile phone.
A kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone the most according to claim 4, its feature exists
In, described step S2 includes:
S21 textile image receives: server receives pretreated to be knitted through first by what smart mobile phone image sending module sent
Object image;
S22 second time pretreatment: the textile image that step S21 is received by server carries out gray processing process;
S23 textile image processes: the image after step S22 gray processing carries out threshold transformation, adaptive-filtering, quick Fu respectively
In leaf transformation, edge detection process, to obtain the periodic feature point of textile processes positive and negative image;
S24 textile image is analyzed: is analyzed by the periodic feature point of the positive and negative image in step S23, draws fabric
Analysis result, described fabric analysis result includes that art flower width, art flower are high, finished product horizontal stroke is close, finished product is indulged close, organizational structure and wears
Through circulation etc.;
S25 analysis result is fed back: described fabric analysis result fed back in smart mobile phone.
6. according to a kind of based on smart mobile phone the WARP-KNITTING technique rapid analysis method described in claim 4 or 5, its feature
Being, in described step pretreatment S13 for the first time, white balancing treatment method includes:
Textile image is YC by RGB patten transformation by S131bCr, divide the image into N number of part after converting, calculate every respectively
The C of individual partbAnd CrMeansigma methods Mb、MrAnd both mean square deviations Db、Dr, computational methods are as follows:
Meansigma methods M in the S132 statistics each region of textile imageb、MrAnd mean square deviation Db、DrValue as whole image;
S133 determines the white reference point in textile image as follows,
|Cb(i,j)-(Mb+Db×sign(Mb)) | < 1.5 × Db
|Cr(i,j)-(Mr+Dr×sign(Mr)) | < 1.5 × Dr
Before brightness value, the white reference point of 10% is as final white reference point;
S134 calculates textile image each white reference point average brightness Rav, Gav, Bav, the gain R of each passagegain, Ggain, Bgain
With image at YCbCrThe maximum Ymax of Y under pattern;
R ' G ' the B ' that the S135 calculating each passage of textile image is final:
R '=R × Rgain
G '=G × Ggain
B '=B × Bgain。
A kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone the most according to claim 6, its feature exists
In, when step S133 uses the statistical data in step S132, cast out Db<0.05MbAnd/or Dr<0.05MrTime value.
A kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone the most according to claim 5, its feature exists
In, the gray processing in described step S22 has been converted by below equation:
Gray (i, j)=0.11R (i, j)+0.59G (i, j)+0.3B (i, j).
A kind of WARP-KNITTING technique rapid analysis method based on smart mobile phone the most according to claim 8, its feature exists
In, described step S23 includes:
S231 threshold transformation: use the method further two-value of image by the fabric tow sides gray processing of extraction of threshold transformation
Changing, the threshold transformation method of gradation of image is as follows:
S232 adaptive-filtering: by the noise in Adaptive noise cancellation fabric two-face image, according to the local variance of image
Adjust filtering output, it is ensured that image border and detail of the high frequency.
S233 carries out fast Fourier transform (FFT) by following formula and the spatial domain image of textile processes direct picture is converted to frequency
Spectrogram:
S234 carries out rim detection to the textile processes verso images after step S231, S232 process, and obtains textile processes
The edge graph of reverse side.
10., according to a kind of based on smart mobile phone the WARP-KNITTING technique rapid analysis method described in claim 5,8,9, it is special
Levying and be, described step S24 textile image analysis includes following sub-step:
S241 textile processes front frequency domain figure picture after S23 processes has the bright of the regularity of distribution in the horizontal and vertical directions
Band, horizontal direction bright band represents fabric line information, and vertical direction bright band represents fabric stringer information, enters frequency domain figure picture respectively
Row both horizontally and vertically projects;
The central point of S242 selected level direction projection image, vertically point by point scanning gradation of image, until scanning ash
Using this pixel as starting point when angle value is 255, continue vertically point by point scanning, until scan gray value be next time
Stopping when 255, the pixel count m of writing scan, described m are the frequency between adjacent two lines of fabric;Selected vertical direction
The central point of projection picture, in the horizontal direction point by point scanning gradation of image, make this pixel until scanning when gray value is 255
For starting point, continue point by point scanning in the horizontal direction, stop when gray value is 255 until scan next time, writing scan
Pixel count n, described n are the frequency between adjacent two stringers of fabric;
The art flower width W of fabric described in S243idth, art flower height Height, the horizontal close W of finished productPCClose C is indulged with finished productPCTable can be distinguished
It is shown as:
Width=n
Height=m
Wherein r=pixel/inch, for described can only the resolution of image of mobile phone shooting, M, N are the textile image of location cutting
Pixel size;
Multiple target areas parameters for shape characteristic in the fabric edge figure extracted, for the verso images of fabric, is known by S244
Not, element marking method is used to judge pixel-by-pixel, the coil underlap edge parameters in acquisition Weaving Cycle, and then analyze,
Calculate the organizational structure of fabric and pass circulation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610522846.0A CN106198542B (en) | 2016-07-05 | 2016-07-05 | A kind of knitted fabric industrial analysis method based on smart mobile phone |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610522846.0A CN106198542B (en) | 2016-07-05 | 2016-07-05 | A kind of knitted fabric industrial analysis method based on smart mobile phone |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106198542A true CN106198542A (en) | 2016-12-07 |
CN106198542B CN106198542B (en) | 2017-10-20 |
Family
ID=57465306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610522846.0A Active CN106198542B (en) | 2016-07-05 | 2016-07-05 | A kind of knitted fabric industrial analysis method based on smart mobile phone |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106198542B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108729011A (en) * | 2018-05-16 | 2018-11-02 | 东华大学 | For automatic assembly line to the system for rapidly identifying and method of garment piece fabric positive and negative |
CN108921819A (en) * | 2018-05-29 | 2018-11-30 | 黎明职业大学 | A kind of cloth examination device and method based on machine vision |
CN109635758A (en) * | 2018-12-18 | 2019-04-16 | 武汉市蓝领英才科技有限公司 | Wisdom building site detection method is dressed based on the high altitude operation personnel safety band of video |
CN111325707A (en) * | 2018-12-13 | 2020-06-23 | 深圳中科飞测科技有限公司 | Image processing method and system, and detection method and system |
CN112734383A (en) * | 2021-01-12 | 2021-04-30 | 浙江理工大学 | Method for automatically identifying clothing process |
CN113205476A (en) * | 2020-08-04 | 2021-08-03 | 黄永芹 | Platform and method for intelligently identifying germ target |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149325A (en) * | 2007-10-09 | 2008-03-26 | 浙江理工大学 | Textile water-proof performance automatic detection method and detection system |
US20090256947A1 (en) * | 2008-04-15 | 2009-10-15 | Sony Corporation | Method and apparatus for performing touch-based adjustments within imaging devices |
CN102523366A (en) * | 2011-12-13 | 2012-06-27 | 上海工程技术大学 | Automatic fabric weaving style analyzing system and method |
CN102788793A (en) * | 2012-03-31 | 2012-11-21 | 江南大学 | Method for measuring density of weft knitted fabric based on spectrum analysis |
CN103604937A (en) * | 2013-11-22 | 2014-02-26 | 青岛大学 | Fabric analysis system and method based on biaxial mechanical stretch processing |
CN104730073A (en) * | 2015-02-16 | 2015-06-24 | 中国土产畜产进出口总公司 | Quantitative analysis method and system for dishes contained in plates |
CN105675601A (en) * | 2016-03-04 | 2016-06-15 | 江苏大学 | System and detection method for rapidly detecting catechol and derivatives thereof on site |
CN205352932U (en) * | 2015-12-14 | 2016-06-29 | 高安来 | Portable pesticide residue detecting system |
-
2016
- 2016-07-05 CN CN201610522846.0A patent/CN106198542B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149325A (en) * | 2007-10-09 | 2008-03-26 | 浙江理工大学 | Textile water-proof performance automatic detection method and detection system |
US20090256947A1 (en) * | 2008-04-15 | 2009-10-15 | Sony Corporation | Method and apparatus for performing touch-based adjustments within imaging devices |
CN102523366A (en) * | 2011-12-13 | 2012-06-27 | 上海工程技术大学 | Automatic fabric weaving style analyzing system and method |
CN102788793A (en) * | 2012-03-31 | 2012-11-21 | 江南大学 | Method for measuring density of weft knitted fabric based on spectrum analysis |
CN103604937A (en) * | 2013-11-22 | 2014-02-26 | 青岛大学 | Fabric analysis system and method based on biaxial mechanical stretch processing |
CN104730073A (en) * | 2015-02-16 | 2015-06-24 | 中国土产畜产进出口总公司 | Quantitative analysis method and system for dishes contained in plates |
CN205352932U (en) * | 2015-12-14 | 2016-06-29 | 高安来 | Portable pesticide residue detecting system |
CN105675601A (en) * | 2016-03-04 | 2016-06-15 | 江苏大学 | System and detection method for rapidly detecting catechol and derivatives thereof on site |
Non-Patent Citations (2)
Title |
---|
常淑华等: "双目立体视觉匹配的预处理技术", <吉林大学学报> * |
王梅嘉等: "基于Android平台的苹果叶病害远程识别系统", <计算机工程与设计> * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108729011A (en) * | 2018-05-16 | 2018-11-02 | 东华大学 | For automatic assembly line to the system for rapidly identifying and method of garment piece fabric positive and negative |
CN108921819A (en) * | 2018-05-29 | 2018-11-30 | 黎明职业大学 | A kind of cloth examination device and method based on machine vision |
CN108921819B (en) * | 2018-05-29 | 2021-02-02 | 黎明职业大学 | Cloth inspecting device and method based on machine vision |
CN111325707A (en) * | 2018-12-13 | 2020-06-23 | 深圳中科飞测科技有限公司 | Image processing method and system, and detection method and system |
CN109635758A (en) * | 2018-12-18 | 2019-04-16 | 武汉市蓝领英才科技有限公司 | Wisdom building site detection method is dressed based on the high altitude operation personnel safety band of video |
CN109635758B (en) * | 2018-12-18 | 2021-07-09 | 武汉市蓝领英才科技有限公司 | Intelligent building site video-based safety belt wearing detection method for aerial work personnel |
CN113205476A (en) * | 2020-08-04 | 2021-08-03 | 黄永芹 | Platform and method for intelligently identifying germ target |
CN112734383A (en) * | 2021-01-12 | 2021-04-30 | 浙江理工大学 | Method for automatically identifying clothing process |
CN112734383B (en) * | 2021-01-12 | 2024-04-12 | 浙江理工大学 | Method for automatically identifying clothing technology |
Also Published As
Publication number | Publication date |
---|---|
CN106198542B (en) | 2017-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106198542B (en) | A kind of knitted fabric industrial analysis method based on smart mobile phone | |
CN102297867B (en) | Detection system for assembly quality of wiring harness | |
DE102009001555B4 (en) | Image processing device | |
CN105426828B (en) | Method for detecting human face, apparatus and system | |
CN101582160B (en) | Foreground detection method and device as well as adaptive threshold adjusting method and device | |
CN201512707U (en) | Printing error detection device based on intelligent camera | |
CN102665047A (en) | Exposure control method for imaging of complementary metal-oxide-semiconductor (CMOS) image sensor | |
CN102523366B (en) | Automatic fabric weaving style analyzing system and method | |
CN101916370A (en) | Method for processing non-feature regional images in face detection | |
CN105847708B (en) | Line-scan digital camera automatic exposure method of adjustment based on image histogram analysis and system | |
CN103699877A (en) | Method and system for improving face recognition effects | |
CN114926436A (en) | Defect detection method for periodic pattern fabric | |
CN105100632A (en) | Adjusting method and apparatus for automatic exposure of imaging device, and imaging device | |
CN103973990A (en) | Wide dynamic fusion method and device | |
DE102009029391A1 (en) | Image processing apparatus and image processing method | |
CN105678767A (en) | SoC software and hardware collaborative design-based cloth surface blemish detection method | |
DE69918609T2 (en) | Automatic method for detecting changes between two images | |
CN114004834B (en) | Method, equipment and device for analyzing foggy weather condition in image processing | |
CN103458158B (en) | The control method of time of exposure of line-scan digital camera and system thereof | |
CN101582163B (en) | Method for capturing clearest human face in video monitor images | |
CN109727198B (en) | Image brightness optimization method based on skin color detection | |
CN110288623A (en) | The data compression method of unmanned plane marine cage culture inspection image | |
CN109594319A (en) | A kind of pck count intelligent detection device and method | |
CN106093051A (en) | Paper roll tangent plane burr detection method based on machine vision and device | |
CN105787931A (en) | Seal image detection method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |