CN110108362A - The adaptive online test method of color difference and device based on SLIC super-pixel segmentation - Google Patents
The adaptive online test method of color difference and device based on SLIC super-pixel segmentation Download PDFInfo
- Publication number
- CN110108362A CN110108362A CN201910306411.6A CN201910306411A CN110108362A CN 110108362 A CN110108362 A CN 110108362A CN 201910306411 A CN201910306411 A CN 201910306411A CN 110108362 A CN110108362 A CN 110108362A
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- super
- color
- seed point
- 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
- 230000011218 segmentation Effects 0.000 title claims abstract description 38
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 22
- 238000010998 test method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000001914 filtration Methods 0.000 claims abstract description 23
- 238000004737 colorimetric analysis Methods 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims description 29
- 238000012937 correction Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 17
- 239000004744 fabric Substances 0.000 abstract description 11
- 241000114727 Acetes chinensis Species 0.000 abstract description 5
- 239000004753 textile Substances 0.000 description 9
- 230000000694 effects Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J2003/467—Colour computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Spectrometry And Color Measurement (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of adaptive online test method of color difference based on SLIC super-pixel segmentation and devices, and wherein method includes: to carry out Image Acquisition to sample to be detected by online linear array CCD camera;The image collected is subjected to gaussian filtering process and is transformed into and device-independent uniform color space;Image is pre-processed using super-pixel segmentation method;Colorimetry is carried out using CIELDE2000 colour difference formula, obtains calculated result;Checkout result is compared with preset color difference threshold, exports comparison result.To plain color cloth acetes chinensis low efficiency existing for solving in current industry, the not high situation of the degree of automation saves many operands, greatly improves detection efficiency.
Description
Technical field
The present invention relates to the technical fields based on machine vision to acetes chinensis, more particularly to one kind to be based on SLIC super-pixel
The adaptive online test method of the color difference of segmentation and device.
Background technique
For textile, color enriches its appearance as an important feature.The quality of textile dyeing quality is also
Evaluate a key factor of textile product quality.Therefore, textile Online color-difference measurement has important in the textile industry
Meaning.Color difference reflects two dyed fabric samples in chroma, the general performance color-aware of three color-values of lightness and tone
Difference is one of the important parameter for examining product.Enterprise in the actual production process can be raw using the colour table that client provides as standard
Produce the textile product for meeting customer demand.Client, can contrast product and original when whether examination textile product dyeing quality is up to standard
There are the color difference and gloss of sample, the two is completely the same, thinks that textile product color meets the requirements.
Although having introduced some advanced technical equipment, the detection water of printed fabrics color difference by the development of industrial technology
It is flat that biggish gap is still had compared with developed countries.There are still many enterprises cannot fully achieve to textile sample
The detection of this progress online mode.Therefore it studies one kind completely new automated detection system and competition is adapted to relevant enterprises such as weavings
More fierce modernization market, has great significance and practical value.
Summary of the invention
The present invention is intended to provide a kind of overcome the problems, such as one of above problem or at least be partially solved any of the above-described base
In the adaptive online test method of the color difference of SLIC super-pixel segmentation and device.
In order to achieve the above objectives, technical solution of the present invention is specifically achieved in that
One aspect of the present invention provides a kind of adaptive online test method of the color difference based on SLIC super-pixel segmentation
And device, comprising: Image Acquisition is carried out to sample to be detected by online linear array CCD camera;The image collected is carried out
Gaussian filtering process is simultaneously transformed into and device-independent uniform color space;Image is located in advance using super-pixel segmentation method
Reason;Colorimetry is carried out using CIELDE2000 colour difference formula, obtains calculated result;By checkout result and preset color difference threshold
It is compared, exports comparison result.
Wherein, the image collected is subjected to gaussian filtering process and be transformed into and device-independent uniform color space
Include: that the image that will be collected is cut, obtains image to be processed;According to the different setting conversion ginsengs of working flare and the elevation angle
Number;Gaussian filtering process is carried out to image to be processed, and carries out gamma correction;To the image after correction according to conversion parameter into
The conversion of row color space.
Wherein, carrying out pretreatment to image using super-pixel segmentation method includes: the super picture for dividing the image into predetermined number
Seed point is arranged in each super-pixel in element;Calculate the gradient value of all pixels in each 3 × 3 neighborhood of seed point, movement kind
Son point is denoted as new seed point to the smallest position of gradient value;Phase is searched in the region of 2S × 2S centered on new seed point
It like pixel, is clustered, and distributes class label for similar pixel point;Row distance degree is clicked through to each similar pixel searched
Amount, determine each similar pixel point to seed point color distance and space length;Determine the face of each super-pixel in image
Whole super-pixel color feature values of color characteristic value, the color feature value of each generic pixel and image.
Wherein, Colorimetry is carried out using CIELDE2000 colour difference formula, obtaining calculated result includes: to calculate L*a*b* color
Lightness L, coloration a, coloration b, at heart chroma C in color spaceab;Calculate L ', a ' b ', tone h 'abIt is empty with CIEL*a*b* color
Between middle a* axis regulatory factor G;Calculate luminosity equation Δ L, chroma difference Δ Cab, hue difference Δ H 'ab;Calculate weighting function SL, SC, SH
With rotation function RT, RC;Determine correction coefficient KL, KC, KH;Pass through formulaIt calculates and obtains calculated result.
On the other hand the present invention separately provides a kind of adaptive on-line measuring device of the color difference based on SLIC super-pixel segmentation,
It include: acquisition module, for carrying out Image Acquisition to sample to be detected by online linear array CCD camera;Conversion module, being used for will
The image collected carries out gaussian filtering process and is transformed into and device-independent uniform color space;Preprocessing module is used
Image is pre-processed in using super-pixel segmentation method;Computing module, for carrying out color using CIELDE2000 colour difference formula
Difference calculates, and obtains calculated result;Comparison module, for checkout result to be compared with preset color difference threshold, output is compared
As a result.
Wherein, the image collected is carried out gaussian filtering process especially by such as under type and is transformed by conversion module
It is obtained to be processed with device-independent uniform color space: conversion module specifically for cutting the image collected
Image;According to the different setting conversion parameters of working flare and the elevation angle;Gaussian filtering process is carried out to image to be processed, and is carried out
Gamma correction;Color space conversion is carried out according to conversion parameter to the image after correction.
Wherein, preprocessing module pre-processes image using super-pixel segmentation method especially by such as under type: pre- place
It manages module and seed point is set in each super-pixel specifically for dividing the image into the super-pixel of predetermined number;It calculates each
The gradient value of all pixels in 3 × 3 neighborhood of seed point, mobile seed point are denoted as new seed to the smallest position of gradient value
Point;Similar pixel point is searched in the region of 2S × 2S centered on new seed point, is clustered, and is similar pixel point minute
With class label;Row distance measurement is clicked through to each similar pixel for searching, determine each similar pixel point to seed point face
Color distance and space length;Determine the color feature value of each super-pixel in image, the color feature value of each generic pixel
And whole super-pixel color feature values of image.
Wherein, computing module carries out Colorimetry using CIELDE2000 colour difference formula especially by such as under type, obtains
Calculated result: computing module, specifically for calculating lightness L, coloration a, coloration b, at heart chroma C in L*a*b* color spaceab;
Calculate L ', a ' b ', tone h 'abWith the regulatory factor G of a* axis in CIEL*a*b* color space;It is poor to calculate luminosity equation Δ L, chroma
ΔCab, hue difference Δ H 'ab;Calculate weighting function SL, SC, SHWith rotation function RT, RC;Determine correction coefficient KL, KC, KH;Pass through
FormulaIt calculates and obtains calculated result.
It can be seen that a kind of color difference based on SLIC super-pixel segmentation provided through the embodiment of the present invention is adaptively online
Detection method and device, solve in current industry existing to plain color cloth acetes chinensis low efficiency, and the degree of automation is not high
Situation, save many operands, greatly improve detection efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the stream of the adaptive online test method of the color difference provided in an embodiment of the present invention based on SLIC super-pixel segmentation
Cheng Tu;
Fig. 2 is the one of the adaptive online test method of the color difference provided in an embodiment of the present invention based on SLIC super-pixel segmentation
Kind specific flow chart;
Fig. 3 is the knot of the adaptive on-line measuring device of the color difference provided in an embodiment of the present invention based on SLIC super-pixel segmentation
Structure schematic diagram.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Fig. 1 shows the adaptive online test method of the color difference based on SLIC super-pixel segmentation provided in an embodiment of the present invention
Flow chart, referring to Fig. 1, the adaptive on-line checking side of the color difference provided in an embodiment of the present invention based on SLIC super-pixel segmentation
Method, comprising:
S1 passes through online line array CCD (Charge Coupled Device, charge coupling device imaging sensor) camera
Image Acquisition is carried out to sample to be detected.
Specifically, sample to be detected is plain color cloth, and detection method provided by the invention is the color difference reality for plain color cloth
Existing detection.
The image collected is carried out gaussian filtering process and is transformed into and device-independent uniform color space by S2.
As an optional embodiment of the embodiment of the present invention, this step be can specifically include: the figure that will be collected
As being cut, image to be processed is obtained;According to the different setting conversion parameters of working flare and the elevation angle;Image to be processed is carried out
Gaussian filtering process, and carry out gamma correction;Color space conversion is carried out according to conversion parameter to the image after correction.
The image collected is subjected to gaussian filtering process and is converted when it is implemented, can execute in the following way
To the step of with device-independent uniform color space:
S21 first carries out Gaussian linear the disposal of gentle filter to acquired image, passes through formulaInto
The filtering processing of row Gaussian linear, wherein σ indicates Gaussian Distribution Parameters, and σ value eventually determines the width of filter, σ value and smooth
Being positively correlated property of Chengdu.
S22: the space CIELAB will be transformed into from RGB to treated image:
Specifically utilize following formula:
The wherein tristimulus values X in this stepn、Yn、ZnThere are six kinds of modes it can be selected that parameter according to working flare and the elevation angle
Table is as follows:
Wherein, if X/Xn、Y/Yn、Z/ZnValue be greater than
Alternatively, more specifically, can execute in the following way the image collected carrying out gaussian filtering process
And the step of being transformed into device-independent uniform color space:
S21: the original RGB image of acquisition is carried out the image to be processed for being cut to 400 × 400 pixel sizes.
S22: carry out systemic presupposition to detection system illumination light ring environment: different light sources and light angle are in later period color
Space conversion parameter has a certain impact, it is therefore desirable to which according to six kinds demarcated at present, often meeting mode is preselected, and is set.Its
In, six kinds of normal meeting modes may refer to table 1.
S23: carrying out smoothed image using Gaussian filter to the image of above-mentioned 400 × 400 pixel and inhibit noise processed,
Then gamma correction is carried out to it, in order to improve the contrast of color image, so that later period SLIC super-pixel segmentation can be avoided to produce
Raw a large amount of tiny areas;Gaussian filtering is exactly the process being weighted and averaged to entire image, the value of each pixel, all
It is obtained after being weighted averagely by other pixel values in itself and neighborhood.The concrete operations of gaussian filtering are: with a mould
Each of plate (or convolution, mask) scan image pixel, with the weighted average gray scale of pixel in the determining neighborhood of template
Value goes the value of alternate template central pixel point to use.Gaussian filter is for inhibiting the noise of Normal Distribution to have very much
Effect.
Wherein, gamma correction is mainly to original RGB image non-linearization, by following formula to RGB three
It is converted in channel;
Wherein, the value range of r, g, b triple channel is [0,255].
S24: the image by above step treated 400 × 400 pixels is carried out color space conversion, RGB-XYZ-
CIELAB。
If X/Xn、Y/Yn、Z/ZnValue be greater than
Wherein Xn、Yn、ZnValue is according to the value set in step S22.
S3 pre-processes image using super-pixel segmentation method.
As an optional embodiment of the embodiment of the present invention, this step be can specifically include: divide the image into pre-
If seed point is arranged in each super-pixel in the super-pixel of number;Calculate all pixels in each 3 × 3 neighborhood of seed point
Gradient value, mobile seed point are denoted as new seed point to the smallest position of gradient value;2S × 2S centered on new seed point
Region in search for similar pixel point, clustered, and for similar pixel point distribute class label;To each similar picture searched
Vegetarian refreshments carry out distance metric, determine each similar pixel point to seed point color distance and space length;It determines every in image
Whole super-pixel color characteristics of the color feature value of one super-pixel, the color feature value of each generic pixel and image
Value.
Pretreated step is carried out to image using super-pixel segmentation method when it is implemented, can execute in the following way
It is rapid:
S31: initialization seed point.According to the super-pixel number of setting, seed point is uniformly distributed in image.Assuming that figure
Piece has M pixel, the default super-pixel for being divided into K identical sizes, then the size of each super-pixel is M/K, adjacent kind
Son point distance be approximately
S32: calculating the gradient value of all pixels in 3 × 3 neighborhood of seed point, and mobile seed point is the smallest to gradient value
Position is denoted as new seed point.It is possible thereby to which seed point is avoided to fall near profile and border, Clustering Effect is influenced.
S33: searching for similar pixel point again, clustered in the region of 2S × 2S centered on seed point, and is it
Distribute class label.
S34: distance metric, the color distance including each pixel to seed point are carried out to each pixel searched
And space length, calculation method are as follows:
In formula, dlabFor color distance, dsFor space length, S ' is the distance metric of two pixels, and D is between seed point
Distance, m is balance parameters.
S35: the color feature value of each super-pixel in the image divided is set as Vi=(L, B, A), i=1,2,
3 ..., K, the color feature value of each generic pixel are vi=(l, a, b), j=1,2,3 ..., M/K, thenThe super-pixel color feature value one-dimensional vector [V of entire imagei=(L, A, B)T], i
=1,2,3 ..., K is indicated.
S4 carries out Colorimetry using CIELDE2000 colour difference formula, obtains calculated result.
As an optional embodiment of the embodiment of the present invention, this step be can specifically include: calculate L*a*b* color
Lightness L, coloration a, coloration b, at heart chroma C in spaceab;Calculate L ', a ' b ', tone h 'abWith CIEL*a*b* color space
The regulatory factor G of middle a* axis;Calculate luminosity equation Δ L, chroma difference Δ Cab, hue difference Δ H 'ab;Calculate weighting function SL, SC, SHWith
Rotation function RT, RC;Determine correction coefficient KL, KC, KH;Pass through formulaIt calculates and obtains calculated result.
Colorimetry is carried out using CIELDE2000 colour difference formula when it is implemented, can execute in the following way, is obtained
The step of to calculated result:
Following formula specifically can be used and carry out Colorimetry:
Steps are as follows for calculating in formula:
S41: lightness L, the coloration a, coloration b, at heart chroma C in L*a*b* color space are calculatedab。
S42: L ', a ' b ', tone h ' are calculatedabWith the regulatory factor G of a* axis in CIEL*a*b* color space.
In formulaFor testing image Cab1With standard picture Cab2Arithmetic mean of instantaneous value.
S43: luminosity equation Δ L, chroma difference Δ C are calculatedab, hue difference Δ H 'ab。
S44: weighting function S is calculatedL, SC, SHWith rotation function RT, RC。
S45: wherein KL, KC, KHIt is the correction coefficient determined according to actual service conditions.Under the conditions of CIE standard observation,
Default value can be set as KL=KC=KH=1.
Checkout result is compared S5 with preset color difference threshold, exports comparison result.
Specifically, calculated result is compared with the threshold values set in system in advance, if met the requirements, is judged
Product qualification up to standard then judges that product is not up to standard unqualified if it does not meet the requirements.I.e. if calculated result meets the requirements, table
Bright sample to be detected meets the requirements, i.e., color difference meets the requirements, if calculated result is undesirable, shows that sample to be detected is not inconsistent
It closes and requires, i.e., color difference is undesirable.
It can be seen that for during cloth red ink paste used for seals, cloth Online color-difference measurement accuracy rate is low, slow-footed problem, mentions
Detection method of the invention out.Article to be detected is being acquired, image is being pre-processed, the thought based on super-pixel, using letter
Single linear iteration clusters (SLIC, simple linear iterative clustering) algorithm, to similar features
Adjacent pixel is clustered, and forms compact-sized, approaches uniformity block of pixels, each block of pixels is a super-pixel.With super
Pixel replaces multiple similar pixels in block of pixels, respectively the color characteristic of extraction standard image and image to be detected.Using suitable
Colour difference formula carries out Colorimetry.This method can efficiently reduce data meter on the basis of guaranteeing accuracy rate of testing result
Calculation amount improves detection efficiency.
Hereinafter, it is adaptive to illustrate the color difference provided in an embodiment of the present invention based on SLIC super-pixel segmentation by taking Fig. 2 as an example
Online test method is answered, but the present invention is not limited thereto:
CCD camera acquires image to sample to be detected (pure color cloth);
Set light conditions;
Gaussian filter handles the image of acquisition;
To treated, image carries out super-pixel segmentation;
Extract super-pixel color characteristic;
CIEDE2000 colour difference formula calculates color difference;
The value of chromatism being calculated is compared with preset threshold, and judges whether sample to be detected is qualified.
It can be seen that the adaptive on-line checking of the color difference based on SLIC super-pixel segmentation provided through the embodiment of the present invention
Method has merged the detection environment of light conditions and angle under a variety of situations, and the scope of application is wider, and the degree of automation is relatively
Height can satisfy the testing requirements of current most plain color cloth.And detection method provided in an embodiment of the present invention and current
It is compared using the more method of acetes chinensis pixel-by-pixel, fast with more speed, precision is good, improves the effect of detection efficiency.
Fig. 3 shows the adaptive on-line measuring device of the color difference based on SLIC super-pixel segmentation provided in an embodiment of the present invention
Structural schematic diagram, should adaptive on-line measuring device of color difference based on SLIC super-pixel segmentation be applied to it is above-mentioned super based on SLIC
The adaptive online test method of color difference of pixel segmentation, below only adaptively examines the color difference based on SLIC super-pixel segmentation online
The structure for surveying device is briefly described, and it is adaptive to please refer to the above-mentioned color difference based on SLIC super-pixel segmentation for other unaccomplished matters
The related description of online test method is answered, details are not described herein.It is provided in an embodiment of the present invention to be based on the super picture of SLIC referring to Fig. 3
The adaptive on-line measuring device of color difference of element segmentation, comprising:
Acquisition module 301, for carrying out Image Acquisition to sample to be detected by online linear array CCD camera;
Conversion module 302, for by the image collected carry out gaussian filtering process and be transformed into it is device-independent
Uniform color space;
Preprocessing module 303, for being pre-processed using super-pixel segmentation method to image;
Computing module 304 obtains calculated result for carrying out Colorimetry using CIELDE2000 colour difference formula;
Comparison module 305 exports comparison result for checkout result to be compared with preset color difference threshold.
As an optional embodiment of the embodiment of the present invention, conversion module 302 will be acquired especially by such as under type
Obtained image carries out gaussian filtering process and is transformed into and device-independent uniform color space: conversion module 302, specific to use
It is cut in by the image collected, obtains image to be processed;According to the different setting conversion parameters of working flare and the elevation angle;
Gaussian filtering process is carried out to image to be processed, and carries out gamma correction;Color is carried out according to conversion parameter to the image after correction
Color space conversion.
As an optional embodiment of the embodiment of the present invention, preprocessing module 303 is used especially by such as under type
Super-pixel segmentation method pre-processes image: preprocessing module 303, specifically for dividing the image into the super picture of predetermined number
Seed point is arranged in each super-pixel in element;Calculate the gradient value of all pixels in each 3 × 3 neighborhood of seed point, movement kind
Son point is denoted as new seed point to the smallest position of gradient value;Phase is searched in the region of 2S × 2S centered on new seed point
It like pixel, is clustered, and distributes class label for similar pixel point;Row distance degree is clicked through to each similar pixel searched
Amount, determine each similar pixel point to seed point color distance and space length;Determine the face of each super-pixel in image
Whole super-pixel color feature values of color characteristic value, the color feature value of each generic pixel and image.
As an optional embodiment of the embodiment of the present invention, computing module 304 is used especially by such as under type
CIELDE2000 colour difference formula carries out Colorimetry, obtains calculated result: computing module 304, is specifically used for calculating L*a*b* color
Lightness L, coloration a, coloration b, at heart chroma C in color spaceab;Calculate L ', a ' b ', tone h 'abAnd CIEL*a*b* color space
The regulatory factor G of middle a* axis;Calculate luminosity equation Δ L, chroma difference Δ Cab, hue difference Δ H 'ab;Calculate weighting function SL, SC, SHWith
Rotation function RT, RC;Determine correction coefficient KL, KC, KH;Pass through formulaIt calculates and obtains calculated result.
It can be seen that the adaptive on-line checking of the color difference based on SLIC super-pixel segmentation provided through the embodiment of the present invention
Device has merged the detection environment of light conditions and angle under a variety of situations, and the scope of application is wider, and the degree of automation is relatively
Height can satisfy the testing requirements of current most plain color cloth.And detection method provided in an embodiment of the present invention and current
It is compared using the more method of acetes chinensis pixel-by-pixel, fast with more speed, precision is good, improves the effect of detection efficiency.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (8)
1. a kind of adaptive online test method of color difference based on SLIC super-pixel segmentation characterized by comprising
Image Acquisition is carried out to sample to be detected by online linear array CCD camera;
The image collected is subjected to gaussian filtering process and is transformed into and device-independent uniform color space;
Described image is pre-processed using super-pixel segmentation method;
Colorimetry is carried out using CIELDE2000 colour difference formula, obtains calculated result;
The checkout result is compared with preset color difference threshold, exports comparison result.
2. the method according to claim 1, wherein described carry out gaussian filtering process for the image collected
And it is transformed into and includes: with device-independent uniform color space
The image collected is cut, image to be processed is obtained;
According to the different setting conversion parameters of working flare and the elevation angle;
Gaussian filtering process is carried out to the image to be processed, and carries out gamma correction;
Color space conversion is carried out according to the conversion parameter to the image after correction.
3. the method according to claim 1, wherein described carry out in advance described image using super-pixel segmentation method
Processing includes:
Described image is divided into the super-pixel of predetermined number, seed point is set in each super-pixel;
Calculate the gradient value of all pixels in each 3 × 3 neighborhood of the seed point, the mobile seed point to gradient value minimum
Position be denoted as new seed point;
Similar pixel point is searched in the region of 2S × 2S centered on the new seed point, is clustered, and is the phase
Class label is distributed like pixel;
Row distance measurement is clicked through to each similar pixel for searching, determine each similar pixel point to seed point color
Distance and space length;
Determine the color feature value of each super-pixel in described image, the color feature value of each generic pixel and the figure
Whole super-pixel color feature values of picture.
4. the method according to claim 1, wherein described carry out colour difference meter using CIELDE2000 colour difference formula
It calculates, obtaining calculated result includes:
Calculate lightness L, the coloration a, coloration b, at heart chroma C in L*a*b* color spaceab;
Calculate L ', a ' b ', tone h 'abWith the regulatory factor G of a* axis in CIEL*a*b* color space;
Calculate luminosity equation Δ L, chroma difference Δ Cab, hue difference Δ H 'ab;
Calculate weighting function SL, SC, SHWith rotation function RT, RC;
Determine correction coefficient KL, KC, KH;
Pass through formulaIt calculates and obtains calculated result.
5. a kind of adaptive on-line measuring device of color difference based on SLIC super-pixel segmentation characterized by comprising
Acquisition module, for carrying out Image Acquisition to sample to be detected by online linear array CCD camera;
Conversion module, for the image collected to be carried out gaussian filtering process and is transformed into and device-independent homogeneous color
Space;
Preprocessing module, for being pre-processed using super-pixel segmentation method to described image;
Computing module obtains calculated result for carrying out Colorimetry using CIELDE2000 colour difference formula;
Comparison module exports comparison result for the checkout result to be compared with preset color difference threshold.
6. device according to claim 5, which is characterized in that the conversion module will be acquired especially by such as under type
To image gaussian filtering process and be transformed into and device-independent uniform color space:
The conversion module obtains image to be processed specifically for cutting the image collected;According to working flare and
The different setting conversion parameters at the elevation angle;Gaussian filtering process is carried out to the image to be processed, and carries out gamma correction;To school
Image after just carries out color space conversion according to the conversion parameter.
7. device according to claim 5, which is characterized in that the preprocessing module is especially by such as under type using super
Pixel split plot design pre-processes described image:
The preprocessing module is set in each super-pixel specifically for described image to be divided into the super-pixel of predetermined number
Set seed point;Calculate the gradient value of all pixels in each 3 × 3 neighborhood of the seed point, the mobile seed point to gradient
It is worth the smallest position and is denoted as new seed point;Similar pixel is searched in the region of 2S × 2S centered on the new seed point
Point, is clustered, and distributes class label for the similar pixel point;Row distance degree is clicked through to each similar pixel searched
Amount, determine each similar pixel point to seed point color distance and space length;Determine that each in described image is super
Whole super-pixel color feature values of the color feature value of pixel, the color feature value of each generic pixel and described image.
8. device according to claim 5, which is characterized in that the computing module is used especially by such as under type
CIELDE2000 colour difference formula carries out Colorimetry, obtains calculated result:
The computing module, specifically for calculating lightness L, coloration a, coloration b, at heart chroma C in L*a*b* color spaceab;
Calculate L ', a ' b ', tone h 'abWith the regulatory factor G of a* axis in CIEL*a*b* color space;It is poor to calculate luminosity equation Δ L, chroma
ΔCab, hue difference Δ H 'ab;Calculate weighting function SL, SC, SHWith rotation function RT, RC;Determine correction coefficient KL, KC, KH;Pass through
FormulaIt calculates and obtains calculated result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910306411.6A CN110108362A (en) | 2019-04-17 | 2019-04-17 | The adaptive online test method of color difference and device based on SLIC super-pixel segmentation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910306411.6A CN110108362A (en) | 2019-04-17 | 2019-04-17 | The adaptive online test method of color difference and device based on SLIC super-pixel segmentation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110108362A true CN110108362A (en) | 2019-08-09 |
Family
ID=67485555
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910306411.6A Pending CN110108362A (en) | 2019-04-17 | 2019-04-17 | The adaptive online test method of color difference and device based on SLIC super-pixel segmentation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110108362A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110672209A (en) * | 2019-10-24 | 2020-01-10 | 福建屹立智能化科技有限公司 | Online detection method for warp knitting cloth color difference |
CN112488997A (en) * | 2020-11-18 | 2021-03-12 | 浙江大学 | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation |
CN112861920A (en) * | 2021-01-15 | 2021-05-28 | 佛山科学技术学院 | Palm oil heating time prediction system and method |
CN115761013A (en) * | 2022-11-11 | 2023-03-07 | 东华大学 | Cloth color difference detection method based on texture classification |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105354599A (en) * | 2015-11-25 | 2016-02-24 | 安徽创世科技有限公司 | Color recognition method based on improved SLIC super-pixel segmentation algorithm |
CN107016691A (en) * | 2017-04-14 | 2017-08-04 | 南京信息工程大学 | Moving target detecting method based on super-pixel feature |
CN107248154A (en) * | 2017-05-27 | 2017-10-13 | 江苏理工学院 | A kind of cloth aberration real-time on-line detecting method |
CN109141640A (en) * | 2018-08-03 | 2019-01-04 | 深圳市销邦科技股份有限公司 | Acetes chinensis method, system, equipment and storage medium based on machine vision |
-
2019
- 2019-04-17 CN CN201910306411.6A patent/CN110108362A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105354599A (en) * | 2015-11-25 | 2016-02-24 | 安徽创世科技有限公司 | Color recognition method based on improved SLIC super-pixel segmentation algorithm |
CN107016691A (en) * | 2017-04-14 | 2017-08-04 | 南京信息工程大学 | Moving target detecting method based on super-pixel feature |
CN107248154A (en) * | 2017-05-27 | 2017-10-13 | 江苏理工学院 | A kind of cloth aberration real-time on-line detecting method |
CN109141640A (en) * | 2018-08-03 | 2019-01-04 | 深圳市销邦科技股份有限公司 | Acetes chinensis method, system, equipment and storage medium based on machine vision |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110672209A (en) * | 2019-10-24 | 2020-01-10 | 福建屹立智能化科技有限公司 | Online detection method for warp knitting cloth color difference |
CN112488997A (en) * | 2020-11-18 | 2021-03-12 | 浙江大学 | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation |
CN112488997B (en) * | 2020-11-18 | 2022-04-29 | 浙江大学 | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation |
CN112861920A (en) * | 2021-01-15 | 2021-05-28 | 佛山科学技术学院 | Palm oil heating time prediction system and method |
CN115761013A (en) * | 2022-11-11 | 2023-03-07 | 东华大学 | Cloth color difference detection method based on texture classification |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110108362A (en) | The adaptive online test method of color difference and device based on SLIC super-pixel segmentation | |
CN108020519B (en) | Virtual multi-light-source spectrum reconstruction method based on color constancy | |
CN107144353B (en) | A kind of textile chromatism measurement method based on digital camera | |
CN1844550B (en) | Textile and yarn analysis system based on two-side scanning technology | |
CN109671113B (en) | Color measuring and matching method of colored spun fabric based on image technology | |
CN109211918B (en) | Fabric bow weft detection method based on weft trend | |
JP7078175B2 (en) | Inspection equipment and method | |
CN109685822A (en) | A kind of automatically stingy drawing method | |
CN114693676B (en) | Optical detection method and device for bleaching defects of new material textiles | |
CN105787508A (en) | Textile color identification method and system | |
CN106023886A (en) | LED point-by-point brightness color scale correcting method and system | |
CN109919899A (en) | The method for evaluating quality of image based on multispectral imaging | |
CN110644216B (en) | Automatic color fastness grading device of fabrics | |
CN114235153B (en) | Digital camera-based fabric color digital measurement method | |
CN106937018B (en) | The color mapping method of textile inkjet printing and dyeing is used for based on RBF neural | |
CN114972158A (en) | Intelligent digital system for color measurement and color matching of textiles | |
Pan et al. | Measuring linear density of threads in single‐system‐mélange color fabrics with FCM algorithm | |
CN110044485B (en) | Image type fabric color measuring method | |
JP2021196304A (en) | Color change evaluation method of fiber product or the like | |
CN107516331A (en) | A kind of bamboo cane method for sorting colors and system | |
Vazquez-Corral et al. | Color constancy algorithms: Psychophysical evaluation on a new dataset | |
CN112488997B (en) | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation | |
CN115797260B (en) | Color changing method and system for visual high-fidelity textile fabric | |
CN108931299B (en) | Chroma measuring device and method based on embedded camera | |
CN104537626B (en) | Conversion method from CIELAB color systems to Munsell Color Order System |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |